Nikolas LessmannPhD candidate
e-mail: n [dot] lessmann [at] umcutrecht [dot] nl
Phone: +31 88 75 56682
Linkedin
Biography:
Nikolas studied Biomedical Engineering at the University of Lübeck, Germany. For his Bachelor’s thesis, he worked on X-ray based tracking to improve transbronchial biopsy of pulmonary nodules. He then spent one year at Philips Research in Hamburg, where he worked on automatic analysis of chest CT images for the detection of pulmonary embolism and on automatic segmentation of the pulmonary lobes. He is currently working on automatic calcium scoring and early detection of osteoporosis in lung cancer CT screening.
Journal Articles |
|
| 1. | N. Lessmann, C.I. Sánchez, L. Beenen, L.H. Boulogne, M. Brink, E. Calli, J. Charbonnier, T. Dofferhoff, W.M. van Everdingen, P.K. Gerke, B. Geurts, H.A. Gietema, M. Groeneveld, L. van Harten, N. Hendrix, W. Hendrix, H.J. Huisman, I. Išgum, C. Jacobs, R. Kluge, M. Kok, J. Krdzalic, B. Lassen-Schmidt, K. van Leeuwen, J. Meakin, M. Overkamp, T. van Rees Vellinga, E.M. van Rikxoort, R. Samperna, C. Schaefer-Prokop, S. Schalekamp, E.T. Scholten, C. Sital, L. Stöger, J. Teuwen, K. Vaidhya Venkadesh, C. de Vente, M. Vermaat, W. Xie, B. de Wilde, M. Prokop, B. van Ginneken Automated assessment of CO-RADS and chest CT severity scores in patients with suspected COVID-19 using artificial intelligence Journal Article Radiology, 298 (1), pp. E18-E28, 2021. @article{Lessmann2021, title = {Automated assessment of CO-RADS and chest CT severity scores in patients with suspected COVID-19 using artificial intelligence}, author = {N. Lessmann, C.I. Sánchez, L. Beenen, L.H. Boulogne, M. Brink, E. Calli, J. Charbonnier, T. Dofferhoff, W.M. van Everdingen, P.K. Gerke, B. Geurts, H.A. Gietema, M. Groeneveld, L. van Harten, N. Hendrix, W. Hendrix, H.J. Huisman, I. Išgum, C. Jacobs, R. Kluge, M. Kok, J. Krdzalic, B. Lassen-Schmidt, K. van Leeuwen, J. Meakin, M. Overkamp, T. van Rees Vellinga, E.M. van Rikxoort, R. Samperna, C. Schaefer-Prokop, S. Schalekamp, E.T. Scholten, C. Sital, L. Stöger, J. Teuwen, K. Vaidhya Venkadesh, C. de Vente, M. Vermaat, W. Xie, B. de Wilde, M. Prokop, B. van Ginneken }, url = {https://pubs.rsna.org/doi/10.1148/radiol.2020202439}, doi = {10.1148/radiol.2020202439}, year = {2021}, date = {2021-01-01}, journal = {Radiology}, volume = {298}, number = {1}, pages = {E18-E28}, abstract = {Background The COVID-19 pandemic has spread across the globe with alarming speed, morbidity and mortality. Immediate triage of suspected patients with chest infections caused by COVID-19 using chest CT may be of assistance when results from definitive viral testing are delayed. Purpose To develop and validate an artificial intelligence (AI) system to score the likelihood and extent of pulmonary COVID-19 on chest CT scans using the CO-RADS and CT severity scoring systems. Materials and Methods CORADS-AI consists of three deep learning algorithms that automatically segment the five pulmonary lobes, assign a CO-RADS score for the suspicion of COVID-19 and assign a CT severity score for the degree of parenchymal involvement per lobe. This study retrospectively included patients who received an unenhanced chest CT scan due to clinical suspicion of COVID-19 at two medical centers. The system was trained, validated, and tested with data from one of the centers. Data from the second center served as an external test set. Diagnostic performance and agreement with scores assigned by eight independent observers were measured using receiver operating characteristic (ROC) analysis, linearly-weighted kappa and classification accuracy. Results 105 patients (62 ± 16 years, 61 men) and 262 patients (64 ± 16 years, 154 men) were evaluated in the internal and the external test set, respectively. The system discriminated between COVID-19 positive and negative patients with areas under the ROC curve of 0.95 (95% CI: 0.91-0.98) and 0.88 (95% CI: 0.84-0.93). Agreement with the eight human observers was moderate to substantial with a mean linearly-weighted kappa of 0.60 ± 0.01 for CO-RADS scores and 0.54 ± 0.01 for CT severity scores. Conclusion CORADS-AI correctly identified COVID-19 positive patients with high diagnostic performance from chest CT exams, assigned standardized CO-RADS and CT severity scores in good agreement with eight independent observers and generalized well to external data. Summary CORADS-AI is a freely accessible deep learning algorithm that automatically assigns CO-RADS and CT severity scores to non-contrast CT scans of patients suspected of COVID-19 with high diagnostic performance.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background The COVID-19 pandemic has spread across the globe with alarming speed, morbidity and mortality. Immediate triage of suspected patients with chest infections caused by COVID-19 using chest CT may be of assistance when results from definitive viral testing are delayed. Purpose To develop and validate an artificial intelligence (AI) system to score the likelihood and extent of pulmonary COVID-19 on chest CT scans using the CO-RADS and CT severity scoring systems. Materials and Methods CORADS-AI consists of three deep learning algorithms that automatically segment the five pulmonary lobes, assign a CO-RADS score for the suspicion of COVID-19 and assign a CT severity score for the degree of parenchymal involvement per lobe. This study retrospectively included patients who received an unenhanced chest CT scan due to clinical suspicion of COVID-19 at two medical centers. The system was trained, validated, and tested with data from one of the centers. Data from the second center served as an external test set. Diagnostic performance and agreement with scores assigned by eight independent observers were measured using receiver operating characteristic (ROC) analysis, linearly-weighted kappa and classification accuracy. Results 105 patients (62 ± 16 years, 61 men) and 262 patients (64 ± 16 years, 154 men) were evaluated in the internal and the external test set, respectively. The system discriminated between COVID-19 positive and negative patients with areas under the ROC curve of 0.95 (95% CI: 0.91-0.98) and 0.88 (95% CI: 0.84-0.93). Agreement with the eight human observers was moderate to substantial with a mean linearly-weighted kappa of 0.60 ± 0.01 for CO-RADS scores and 0.54 ± 0.01 for CT severity scores. Conclusion CORADS-AI correctly identified COVID-19 positive patients with high diagnostic performance from chest CT exams, assigned standardized CO-RADS and CT severity scores in good agreement with eight independent observers and generalized well to external data. Summary CORADS-AI is a freely accessible deep learning algorithm that automatically assigns CO-RADS and CT severity scores to non-contrast CT scans of patients suspected of COVID-19 with high diagnostic performance. |
| 2. | C. Celeng, R.A.P. Takx, N. Lessmann, P. Maurovich-Horvat, T. Leiner, I. Išgum, P.A. de Jong The association between marital status, coronary computed tomography imaging biomarkers, and mortality in a lung cancer screening population Journal Article Journal of Thoracic Imaging, 35 (3), pp. 204-209, 2020. @article{Celeng2019, title = {The association between marital status, coronary computed tomography imaging biomarkers, and mortality in a lung cancer screening population}, author = {C. Celeng, R.A.P. Takx, N. Lessmann, P. Maurovich-Horvat, T. Leiner, I. Išgum, P.A. de Jong}, url = {https://www.ncbi.nlm.nih.gov/pubmed/31651690}, doi = {10.1097/RTI.0000000000000457}, year = {2020}, date = {2020-05-01}, journal = {Journal of Thoracic Imaging}, volume = {35}, number = {3}, pages = {204-209}, abstract = {PURPOSE: The purpose of this study was to elucidate the impact of being unmarried on coronary computed tomography (CT) imaging biomarkers and mortality in a lung cancer screening population. MATERIALS AND METHODS: In this retrospective case-control study, 5707 subjects (3777 married; mean age: 61.9±5.1 y and 1930 unmarried; mean age: 61.9±5.3 y) underwent low-dose CT as part of the National Lung Screening Trial (NLST). The median follow-up time was 6.5 (Q1-Q3: 5.6 to 6.9) years. Being unmarried was defined as never married, widowed, separated, or divorced. Being married was defined as married or living as married. Our primary endpoint was cardiovascular disease (CVD)-related death; our secondary endpoint was all-cause mortality. Coronary CT imaging biomarkers (calcium score, density, and volume) on low-dose chest CT scan were calculated using dedicated automatic software. Weighted Cox proportional-hazards regression was performed to examine the association between marital status and death. Kaplan-Meier curves were generated to visualize subject survival. RESULTS: Being unmarried was significantly associated with an increased risk for CVD-related death (hazard ratio [HR]: 1.58; 95% confidence interval [CI]: 1.31-1.91) and all-cause mortality (HR: 1.39; 95% CI: 1.26-1.53), which remained significant even after adjusting for traditional cardiovascular risk factors (HR CVD death: 1.75; 1.44-2.12 and HR all-cause mortality: 1.58; 95% CI: 1.43-1.74) and coronary calcium score (HR CVD death: 1.58; 95% CI: 1.31-1.91 and HR all-cause mortality: 1.40; 95% CI: 1.27-1.54). CONCLUSIONS: Being unmarried is associated with an increased CVD-related death and all-cause mortality mainly due to cardiovascular etiology. On the basis of this, marital status might be taken into consideration when assessing individuals' health status.}, keywords = {}, pubstate = {published}, tppubtype = {article} } PURPOSE: The purpose of this study was to elucidate the impact of being unmarried on coronary computed tomography (CT) imaging biomarkers and mortality in a lung cancer screening population. MATERIALS AND METHODS: In this retrospective case-control study, 5707 subjects (3777 married; mean age: 61.9±5.1 y and 1930 unmarried; mean age: 61.9±5.3 y) underwent low-dose CT as part of the National Lung Screening Trial (NLST). The median follow-up time was 6.5 (Q1-Q3: 5.6 to 6.9) years. Being unmarried was defined as never married, widowed, separated, or divorced. Being married was defined as married or living as married. Our primary endpoint was cardiovascular disease (CVD)-related death; our secondary endpoint was all-cause mortality. Coronary CT imaging biomarkers (calcium score, density, and volume) on low-dose chest CT scan were calculated using dedicated automatic software. Weighted Cox proportional-hazards regression was performed to examine the association between marital status and death. Kaplan-Meier curves were generated to visualize subject survival. RESULTS: Being unmarried was significantly associated with an increased risk for CVD-related death (hazard ratio [HR]: 1.58; 95% confidence interval [CI]: 1.31-1.91) and all-cause mortality (HR: 1.39; 95% CI: 1.26-1.53), which remained significant even after adjusting for traditional cardiovascular risk factors (HR CVD death: 1.75; 1.44-2.12 and HR all-cause mortality: 1.58; 95% CI: 1.43-1.74) and coronary calcium score (HR CVD death: 1.58; 95% CI: 1.31-1.91 and HR all-cause mortality: 1.40; 95% CI: 1.27-1.54). CONCLUSIONS: Being unmarried is associated with an increased CVD-related death and all-cause mortality mainly due to cardiovascular etiology. On the basis of this, marital status might be taken into consideration when assessing individuals' health status. |
| 3. | C.C. van 't Klooster, H.M. Nathoe, J .Hjortnaes, M.L. Bots, I. Išgum, N. Lessmann, Y. van der Graaf, T. Leiner, F.L.J. Visseren, On behalf of the UCC-SMART-study group International Journal of Cardiology, Heart & Vasculature, 27 (100499), 2020. @article{Klooster2020, title = {Multifocal cardiovascular calcification in patients with established cardiovascular disease; prevalence, risk factors, and relation with recurrent cardiovascular disease}, author = {C.C. van 't Klooster, H.M. Nathoe, J .Hjortnaes, M.L. Bots, I. Išgum, N. Lessmann, Y. van der Graaf, T. Leiner, F.L.J. Visseren, On behalf of the UCC-SMART-study group}, doi = {10.1016/j.ijcha.2020.100499}, year = {2020}, date = {2020-04-20}, journal = {International Journal of Cardiology, Heart & Vasculature}, volume = {27}, number = {100499}, abstract = {Aims The aim is to investigate (multifocal) cardiovascular calcification in patients with established cardiovascular disease (CVD), regarding prevalence, risk factors, and relation with recurrent CVD or vascular interventions. Coronary artery calcification (CAC), thoracic aortic calcification (TAC) (including ascending aorta, aortic arch, descending aorta), mitral annular calcification (MAC), and aortic valve calcification (AVC) are studied. Methods The study concerned 568 patients with established CVD enrolled in the ORACLE cohort. All patients underwent computed tomography. Prevalence of site-specific and multifocal calcification was determined. Ordinal regression analyses were performed to quantify associations of risk factors with cardiovascular calcification, and Cox regression analyses to determine the relation between calcium scores and recurrent CVD or vascular interventions. Results Calcification was multifocal in 76% (N = 380) of patients with calcification. Age (per SD) was associated with calcification at all locations (lowest OR 2.17; 99%CI 1.54–3.11 for ascending aorta calcification). Diabetes mellitus and systolic blood pressure were associated with TAC, whereas male sex was a determinant of CAC. TAC and CAC were related to the combined endpoint CVD or vascular intervention (N = 68). In a model with all calcium scores combined, only CAC was related to the combined outcome (HR 1.39; 95%CI 1.15–1.68). Conclusion Cardiovascular calcification is generally multifocal in patients with established CVD. Differences in associations between risk factors and calcification at various anatomical locations stress the divergence in pathophysiological pathways. CAC is most strongly related to recurrent CVD or vascular interventions independent of traditional risk factors, and independent of heart valve and thoracic aorta calcification.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Aims The aim is to investigate (multifocal) cardiovascular calcification in patients with established cardiovascular disease (CVD), regarding prevalence, risk factors, and relation with recurrent CVD or vascular interventions. Coronary artery calcification (CAC), thoracic aortic calcification (TAC) (including ascending aorta, aortic arch, descending aorta), mitral annular calcification (MAC), and aortic valve calcification (AVC) are studied. Methods The study concerned 568 patients with established CVD enrolled in the ORACLE cohort. All patients underwent computed tomography. Prevalence of site-specific and multifocal calcification was determined. Ordinal regression analyses were performed to quantify associations of risk factors with cardiovascular calcification, and Cox regression analyses to determine the relation between calcium scores and recurrent CVD or vascular interventions. Results Calcification was multifocal in 76% (N = 380) of patients with calcification. Age (per SD) was associated with calcification at all locations (lowest OR 2.17; 99%CI 1.54–3.11 for ascending aorta calcification). Diabetes mellitus and systolic blood pressure were associated with TAC, whereas male sex was a determinant of CAC. TAC and CAC were related to the combined endpoint CVD or vascular intervention (N = 68). In a model with all calcium scores combined, only CAC was related to the combined outcome (HR 1.39; 95%CI 1.15–1.68). Conclusion Cardiovascular calcification is generally multifocal in patients with established CVD. Differences in associations between risk factors and calcification at various anatomical locations stress the divergence in pathophysiological pathways. CAC is most strongly related to recurrent CVD or vascular interventions independent of traditional risk factors, and independent of heart valve and thoracic aorta calcification. |
| 4. | S.G.M. van Velzen, N. Lessmann, B.K. Velthuis, I.E.M. Bank, D.H.J.G. van den Bongard, T. Leiner, P. A. de Jong, W. B. Veldhuis, A. Correa, J.G. Terry, J.J. Carr, M.A. Viergever, H.M. Verkooijen, I. Išgum Deep learning for automatic calcium scoring in CT: validation using multiple cardiac CT and chest CT protocols Journal Article Radiology, 295 (1), 2020. @article{vanVelzen2020, title = {Deep learning for automatic calcium scoring in CT: validation using multiple cardiac CT and chest CT protocols }, author = {S.G.M. van Velzen, N. Lessmann, B.K. Velthuis, I.E.M. Bank, D.H.J.G. van den Bongard, T. Leiner, P. A. de Jong, W. B. Veldhuis, A. Correa, J.G. Terry, J.J. Carr, M.A. Viergever, H.M. Verkooijen, I. Išgum}, doi = {https://doi.org/10.1148/radiol.2020191621}, year = {2020}, date = {2020-02-11}, journal = {Radiology}, volume = {295}, number = {1}, abstract = {Background Although several deep learning (DL) calcium scoring methods have achieved excellent performance for specific CT protocols, their performance in a range of CT examination types is unknown. Purpose To evaluate the performance of a DL method for automatic calcium scoring across a wide range of CT examination types and to investigate whether the method can adapt to different types of CT examinations when representative images are added to the existing training data set. Materials and Methods The study included 7240 participants who underwent various types of nonenhanced CT examinations that included the heart: coronary artery calcium (CAC) scoring CT, diagnostic CT of the chest, PET attenuation correction CT, radiation therapy treatment planning CT, CAC screening CT, and low-dose CT of the chest. CAC and thoracic aorta calcification (TAC) were quantified using a convolutional neural network trained with (a) 1181 low-dose chest CT examinations (baseline), (b) a small set of examinations of the respective type supplemented to the baseline (data specific), and (c) a combination of examinations of all available types (combined). Supplemental training sets contained 199–568 CT images depending on the calcium burden of each population. The DL algorithm performance was evaluated with intraclass correlation coefficients (ICCs) between DL and manual (Agatston) CAC and (volume) TAC scoring and with linearly weighted κ values for cardiovascular risk categories (Agatston score; cardiovascular disease risk categories: 0, 1–10, 11–100, 101–400, >400). Results At baseline, the DL algorithm yielded ICCs of 0.79–0.97 for CAC and 0.66–0.98 for TAC across the range of different types of CT examinations. ICCs improved to 0.84–0.99 (CAC) and 0.92–0.99 (TAC) for CT protocol–specific training and to 0.85–0.99 (CAC) and 0.96–0.99 (TAC) for combined training. For assignment of cardiovascular disease risk category, the κ value for all test CT scans was 0.90 (95% confidence interval [CI]: 0.89, 0.91) for the baseline training. It increased to 0.92 (95% CI: 0.91, 0.93) for both data-specific and combined training. Conclusion A deep learning calcium scoring algorithm for quantification of coronary and thoracic calcium was robust, despite substantial differences in CT protocol and variations in subject population. Augmenting the algorithm training with CT protocol–specific images further improved algorithm performance.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Background Although several deep learning (DL) calcium scoring methods have achieved excellent performance for specific CT protocols, their performance in a range of CT examination types is unknown. Purpose To evaluate the performance of a DL method for automatic calcium scoring across a wide range of CT examination types and to investigate whether the method can adapt to different types of CT examinations when representative images are added to the existing training data set. Materials and Methods The study included 7240 participants who underwent various types of nonenhanced CT examinations that included the heart: coronary artery calcium (CAC) scoring CT, diagnostic CT of the chest, PET attenuation correction CT, radiation therapy treatment planning CT, CAC screening CT, and low-dose CT of the chest. CAC and thoracic aorta calcification (TAC) were quantified using a convolutional neural network trained with (a) 1181 low-dose chest CT examinations (baseline), (b) a small set of examinations of the respective type supplemented to the baseline (data specific), and (c) a combination of examinations of all available types (combined). Supplemental training sets contained 199–568 CT images depending on the calcium burden of each population. The DL algorithm performance was evaluated with intraclass correlation coefficients (ICCs) between DL and manual (Agatston) CAC and (volume) TAC scoring and with linearly weighted κ values for cardiovascular risk categories (Agatston score; cardiovascular disease risk categories: 0, 1–10, 11–100, 101–400, >400). Results At baseline, the DL algorithm yielded ICCs of 0.79–0.97 for CAC and 0.66–0.98 for TAC across the range of different types of CT examinations. ICCs improved to 0.84–0.99 (CAC) and 0.92–0.99 (TAC) for CT protocol–specific training and to 0.85–0.99 (CAC) and 0.96–0.99 (TAC) for combined training. For assignment of cardiovascular disease risk category, the κ value for all test CT scans was 0.90 (95% confidence interval [CI]: 0.89, 0.91) for the baseline training. It increased to 0.92 (95% CI: 0.91, 0.93) for both data-specific and combined training. Conclusion A deep learning calcium scoring algorithm for quantification of coronary and thoracic calcium was robust, despite substantial differences in CT protocol and variations in subject population. Augmenting the algorithm training with CT protocol–specific images further improved algorithm performance. |
| 5. | M. Dekker, F. Waissi, I.E.M. Bank, N. Lessmann, I. Išgum, B.K. Velthuis, A.M. Scholtens, G.E. Leenders, G. Pasterkamp, D.P.V. de Kleijn, L. Timmers, A. Mosterd Automated calcium scores collected during myocardial perfusion imaging improve identification of obstructive coronary artery disease Journal Article International Journal of Cardiology, 26 (100434), 2019. @article{M2019b, title = {Automated calcium scores collected during myocardial perfusion imaging improve identification of obstructive coronary artery disease}, author = {M. Dekker, F. Waissi, I.E.M. Bank, N. Lessmann, I. Išgum, B.K. Velthuis, A.M. Scholtens, G.E. Leenders, G. Pasterkamp, D.P.V. de Kleijn, L. Timmers, A. Mosterd}, url = {https://www.ncbi.nlm.nih.gov/pubmed/31768415}, doi = {10.1016/j.ijcha.2019.100434}, year = {2019}, date = {2019-11-19}, journal = {International Journal of Cardiology}, volume = {26}, number = {100434}, abstract = {Myocardial perfusion imaging (MPI) is an accurate noninvasive test for patients with suspected obstructive coronary artery disease (CAD) and coronary artery calcium (CAC) score is known to be a powerful predictor of cardiovascular events. Collection of CAC scores simultaneously with MPI is unexplored. AIM: We aimed to investigate whether automatically derived CAC scores during myocardial perfusion imaging would further improve the diagnostic accuracy of MPI to detect obstructive CAD. METHODS: We analyzed 150 consecutive patients without a history of coronary revascularization with suspected obstructive CAD who were referred for 82Rb PET/CT and available coronary angiographic data. Myocardial perfusion was evaluated both semi quantitatively as well as quantitatively according to the European guidelines. CAC scores were automatically derived from the low-dose attenuation correction CT scans using previously developed software based on deep learning. Obstructive CAD was defined as stenosis >70% (or >50% in the left main coronary artery) and/or fractional flow reserve (FFR) ≤0.80. RESULTS: In total 58% of patients had obstructive CAD of which seventy-four percent were male. Addition of CAC scores to MPI and clinical predictors significantly improved the diagnostic accuracy of MPI to detect obstructive CAD. The area under the curve (AUC) increased from 0.87 to 0.91 (p: 0.025). Sensitivity and specificity analysis showed an incremental decrease in false negative tests with our MPI + CAC approach (n = 14 to n = 4), as a consequence an increase in false positive tests was seen (n = 11 to n = 28). CONCLUSION: CAC scores collected simultaneously with MPI improve the detection of obstructive coronary artery disease in patients without a history of coronary revascularization.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Myocardial perfusion imaging (MPI) is an accurate noninvasive test for patients with suspected obstructive coronary artery disease (CAD) and coronary artery calcium (CAC) score is known to be a powerful predictor of cardiovascular events. Collection of CAC scores simultaneously with MPI is unexplored. AIM: We aimed to investigate whether automatically derived CAC scores during myocardial perfusion imaging would further improve the diagnostic accuracy of MPI to detect obstructive CAD. METHODS: We analyzed 150 consecutive patients without a history of coronary revascularization with suspected obstructive CAD who were referred for 82Rb PET/CT and available coronary angiographic data. Myocardial perfusion was evaluated both semi quantitatively as well as quantitatively according to the European guidelines. CAC scores were automatically derived from the low-dose attenuation correction CT scans using previously developed software based on deep learning. Obstructive CAD was defined as stenosis >70% (or >50% in the left main coronary artery) and/or fractional flow reserve (FFR) ≤0.80. RESULTS: In total 58% of patients had obstructive CAD of which seventy-four percent were male. Addition of CAC scores to MPI and clinical predictors significantly improved the diagnostic accuracy of MPI to detect obstructive CAD. The area under the curve (AUC) increased from 0.87 to 0.91 (p: 0.025). Sensitivity and specificity analysis showed an incremental decrease in false negative tests with our MPI + CAC approach (n = 14 to n = 4), as a consequence an increase in false positive tests was seen (n = 11 to n = 28). CONCLUSION: CAC scores collected simultaneously with MPI improve the detection of obstructive coronary artery disease in patients without a history of coronary revascularization. |
| 6. | M.J. Emaus, I. Išgum, S.G.M. van Velzen, H.J.G.D. van den Bongard, S.A.M. Gernaat, N. Lessmann, M.G.A. Sattler, A.J. Teske, J. Penninkhof, H. Meijer, J.P. Pignol, H.M. Verkooijen; Bragatston study group BMJ Open, 9 (7), pp. e028752, 2019. @article{Emaus2019, title = {Bragatston study protocol: a multicentre cohort study on automated quantification of cardiovascular calcifications on radiotherapy planning CT scans for cardiovascular risk prediction in patients with breast cancer}, author = {M.J. Emaus, I. Išgum, S.G.M. van Velzen, H.J.G.D. van den Bongard, S.A.M. Gernaat, N. Lessmann, M.G.A. Sattler, A.J. Teske, J. Penninkhof, H. Meijer, J.P. Pignol, H.M. Verkooijen; Bragatston study group}, url = {https://doi.org/10.1136/bmjopen-2018-028752}, year = {2019}, date = {2019-07-27}, journal = {BMJ Open}, volume = {9}, number = {7}, pages = {e028752}, abstract = {NTRODUCTION: Cardiovascular disease (CVD) is an important cause of death in breast cancer survivors. Some breast cancer treatments including anthracyclines, trastuzumab and radiotherapy can increase the risk of CVD, especially for patients with pre-existing CVD risk factors. Early identification of patients at increased CVD risk may allow switching to less cardiotoxic treatments, active surveillance or treatment of CVD risk factors. One of the strongest independent CVD risk factors is the presence and extent of coronary artery calcifications (CAC). In clinical practice, CAC are generally quantified on ECG-triggered cardiac CT scans. Patients with breast cancer treated with radiotherapy routinely undergo radiotherapy planning CT scans of the chest, and those scans could provide the opportunity to routinely assess CAC before a potentially cardiotoxic treatment. The Bragatston study aims to investigate the association between calcifications in the coronary arteries, aorta and heart valves (hereinafter called \'cardiovascular calcifications\') measured automatically on planning CT scans of patients with breast cancer and CVD risk. METHODS AND ANALYSIS: In a first step, we will optimise and validate a deep learning algorithm for automated quantification of cardiovascular calcifications on planning CT scans of patients with breast cancer. Then, in a multicentre cohort study (University Medical Center Utrecht, Utrecht, Erasmus MC Cancer Institute, Rotterdam and Radboudumc, Nijmegen, The Netherlands), the association between cardiovascular calcifications measured on planning CT scans of patients with breast cancer (n≈16 000) and incident (non-)fatal CVD events will be evaluated. To assess the added predictive value of these calcifications over traditional CVD risk factors and treatment characteristics, a case-cohort analysis will be performed among all cohort members diagnosed with a CVD event during follow-up (n≈200) and a random sample of the baseline cohort (n≈600). ETHICS AND DISSEMINATION: The Institutional Review Boards of the participating hospitals decided that the Medical Research Involving Human Subjects Act does not apply. Findings will be published in peer-reviewed journals and presented at conferences.}, keywords = {}, pubstate = {published}, tppubtype = {article} } NTRODUCTION: Cardiovascular disease (CVD) is an important cause of death in breast cancer survivors. Some breast cancer treatments including anthracyclines, trastuzumab and radiotherapy can increase the risk of CVD, especially for patients with pre-existing CVD risk factors. Early identification of patients at increased CVD risk may allow switching to less cardiotoxic treatments, active surveillance or treatment of CVD risk factors. One of the strongest independent CVD risk factors is the presence and extent of coronary artery calcifications (CAC). In clinical practice, CAC are generally quantified on ECG-triggered cardiac CT scans. Patients with breast cancer treated with radiotherapy routinely undergo radiotherapy planning CT scans of the chest, and those scans could provide the opportunity to routinely assess CAC before a potentially cardiotoxic treatment. The Bragatston study aims to investigate the association between calcifications in the coronary arteries, aorta and heart valves (hereinafter called 'cardiovascular calcifications') measured automatically on planning CT scans of patients with breast cancer and CVD risk. METHODS AND ANALYSIS: In a first step, we will optimise and validate a deep learning algorithm for automated quantification of cardiovascular calcifications on planning CT scans of patients with breast cancer. Then, in a multicentre cohort study (University Medical Center Utrecht, Utrecht, Erasmus MC Cancer Institute, Rotterdam and Radboudumc, Nijmegen, The Netherlands), the association between cardiovascular calcifications measured on planning CT scans of patients with breast cancer (n≈16 000) and incident (non-)fatal CVD events will be evaluated. To assess the added predictive value of these calcifications over traditional CVD risk factors and treatment characteristics, a case-cohort analysis will be performed among all cohort members diagnosed with a CVD event during follow-up (n≈200) and a random sample of the baseline cohort (n≈600). ETHICS AND DISSEMINATION: The Institutional Review Boards of the participating hospitals decided that the Medical Research Involving Human Subjects Act does not apply. Findings will be published in peer-reviewed journals and presented at conferences. |
| 7. | N. Khalili, N. Lessmann, E. Turk, N. Claessens, R. de Heus, T. Kolk, M.A. Viergever, M.J.N.L. Benders, I. Išgum Automatic brain tissue segmentation in fetal MRI using convolutional neural networks Journal Article Magnetic Resonance Imaging, 64 , pp. 77-89, 2019. @article{Khalili2019b, title = {Automatic brain tissue segmentation in fetal MRI using convolutional neural networks}, author = {N. Khalili, N. Lessmann, E. Turk, N. Claessens, R. de Heus, T. Kolk, M.A. Viergever, M.J.N.L. Benders, I. Išgum}, url = {https://doi.org/10.1016/j.mri.2019.05.020 https://arxiv.org/abs/1906.04713}, year = {2019}, date = {2019-06-07}, journal = {Magnetic Resonance Imaging}, volume = {64}, pages = {77-89}, abstract = {MR images of fetuses allow clinicians to detect brain abnormalities in an early stage of development. The cornerstone of volumetric and morphologic analysis in fetal MRI is segmentation of the fetal brain into different tissue classes. Manual segmentation is cumbersome and time consuming, hence automatic segmentation could substantially simplify the procedure. However, automatic brain tissue segmentation in these scans is challenging owing to artifacts including intensity inhomogeneity, caused in particular by spontaneous fetal movements during the scan. Unlike methods that estimate the bias field to remove intensity inhomogeneity as a preprocessing step to segmentation, we propose to perform segmentation using a convolutional neural network that exploits images with synthetically introduced intensity inhomogeneity as data augmentation. The method first uses a CNN to extract the intracranial volume. Thereafter, another CNN with the same architecture is employed to segment the extracted volume into seven brain tissue classes: cerebellum, basal ganglia and thalami, ventricular cerebrospinal fluid, white matter, brain stem, cortical gray matter and extracerebral cerebrospinal fluid. To make the method applicable to slices showing intensity inhomogeneity artifacts, the training data was augmented by applying a combination of linear gradients with random offsets and orientations to image slices without artifacts. To evaluate the performance of the method, Dice coefficient (DC) and Mean surface distance (MSD) per tissue class were computed between automatic and manual expert annotations. When the training data was enriched by simulated intensity inhomogeneity artifacts, the average achieved DC over all tissue classes and images increased from 0.77 to 0.88, and MSD decreased from 0.78 mm to 0.37 mm. These results demonstrate that the proposed approach can potentially replace or complement preprocessing steps, such as bias field corrections, and thereby improve the segmentation performance.}, keywords = {}, pubstate = {published}, tppubtype = {article} } MR images of fetuses allow clinicians to detect brain abnormalities in an early stage of development. The cornerstone of volumetric and morphologic analysis in fetal MRI is segmentation of the fetal brain into different tissue classes. Manual segmentation is cumbersome and time consuming, hence automatic segmentation could substantially simplify the procedure. However, automatic brain tissue segmentation in these scans is challenging owing to artifacts including intensity inhomogeneity, caused in particular by spontaneous fetal movements during the scan. Unlike methods that estimate the bias field to remove intensity inhomogeneity as a preprocessing step to segmentation, we propose to perform segmentation using a convolutional neural network that exploits images with synthetically introduced intensity inhomogeneity as data augmentation. The method first uses a CNN to extract the intracranial volume. Thereafter, another CNN with the same architecture is employed to segment the extracted volume into seven brain tissue classes: cerebellum, basal ganglia and thalami, ventricular cerebrospinal fluid, white matter, brain stem, cortical gray matter and extracerebral cerebrospinal fluid. To make the method applicable to slices showing intensity inhomogeneity artifacts, the training data was augmented by applying a combination of linear gradients with random offsets and orientations to image slices without artifacts. To evaluate the performance of the method, Dice coefficient (DC) and Mean surface distance (MSD) per tissue class were computed between automatic and manual expert annotations. When the training data was enriched by simulated intensity inhomogeneity artifacts, the average achieved DC over all tissue classes and images increased from 0.77 to 0.88, and MSD decreased from 0.78 mm to 0.37 mm. These results demonstrate that the proposed approach can potentially replace or complement preprocessing steps, such as bias field corrections, and thereby improve the segmentation performance. |
| 8. | B.D. de Vos, J.M. Wolterink, T. Leiner, P.A. de Jong, N. Lessmann, I. Išgum Direct automatic coronary calcium scoring in cardiac and chest CT Journal Article IEEE Transactions on Medical Imaging, 34 , pp. 123-136, 2019. @article{deVos2019, title = {Direct automatic coronary calcium scoring in cardiac and chest CT}, author = {B.D. de Vos, J.M. Wolterink, T. Leiner, P.A. de Jong, N. Lessmann, I. Išgum}, url = {https://ieeexplore.ieee.org/abstract/document/8643342 https://arxiv.org/abs/1902.05408}, year = {2019}, date = {2019-02-21}, journal = {IEEE Transactions on Medical Imaging}, volume = {34}, pages = {123-136}, abstract = {Cardiovascular disease (CVD) is the global leading cause of death. A strong risk factor for CVD events is the amount of coronary artery calcium (CAC). To meet demands of the increasing interest in quantification of CAC, i.e. coronary calcium scoring, especially as an unrequested finding for screening and research, automatic methods have been proposed. Current automatic calcium scoring methods are relatively computationally expensive and only provide scores for one type of CT. To address this, we propose a computationally efficient method that employs two ConvNets: the first performs registration to align the fields of view of input CTs and the second performs direct regression of the calcium score, thereby circumventing time-consuming intermediate CAC segmentation. Optional decision feedback provides insight in the regions that contributed to the calcium score. Experiments were performed using 903 cardiac CT and 1,687 chest CT scans. The method predicted calcium scores in less than 0.3 s. Intra-class correlation coefficient between predicted and manual calcium scores was 0.98 for both cardiac and chest CT. The method showed almost perfect agreement between automatic and manual CVD risk categorization in both datasets, with a linearly weighted Cohen's kappa of 0.95 in cardiac CT and 0.93 in chest CT. Performance is similar to that of state-of-the-art methods, but the proposed method is hundreds of times faster. By providing visual feedback, insight is given in the decision process, making it readily implementable in clinical and research settings.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Cardiovascular disease (CVD) is the global leading cause of death. A strong risk factor for CVD events is the amount of coronary artery calcium (CAC). To meet demands of the increasing interest in quantification of CAC, i.e. coronary calcium scoring, especially as an unrequested finding for screening and research, automatic methods have been proposed. Current automatic calcium scoring methods are relatively computationally expensive and only provide scores for one type of CT. To address this, we propose a computationally efficient method that employs two ConvNets: the first performs registration to align the fields of view of input CTs and the second performs direct regression of the calcium score, thereby circumventing time-consuming intermediate CAC segmentation. Optional decision feedback provides insight in the regions that contributed to the calcium score. Experiments were performed using 903 cardiac CT and 1,687 chest CT scans. The method predicted calcium scores in less than 0.3 s. Intra-class correlation coefficient between predicted and manual calcium scores was 0.98 for both cardiac and chest CT. The method showed almost perfect agreement between automatic and manual CVD risk categorization in both datasets, with a linearly weighted Cohen's kappa of 0.95 in cardiac CT and 0.93 in chest CT. Performance is similar to that of state-of-the-art methods, but the proposed method is hundreds of times faster. By providing visual feedback, insight is given in the decision process, making it readily implementable in clinical and research settings. |
| 9. | N. Lessmann, B. van Ginneken, P.A. de Jong, I. Išgum Iterative fully convolutional neural networks for automatic vertebra segmentation and identification Journal Article Medical Image Analysis, 53 , pp. 142-155, 2019. @article{Lessmann2019, title = {Iterative fully convolutional neural networks for automatic vertebra segmentation and identification}, author = {N. Lessmann, B. van Ginneken, P.A. de Jong, I. Išgum}, url = {https://arxiv.org/abs/1804.04383}, year = {2019}, date = {2019-02-12}, journal = {Medical Image Analysis}, volume = {53}, pages = {142-155}, abstract = {Precise segmentation and anatomical identification of the vertebrae provides the basis for automatic analysis of the spine, such as detection of vertebral compression fractures or other abnormalities. Most dedicated spine CT and MR scans as well as scans of the chest, abdomen or neck cover only part of the spine. Segmentation and identification should therefore not rely on the visibility of certain vertebrae or a certain number of vertebrae. We propose an iterative instance segmentation approach that uses a fully convolutional neural network to segment and label vertebrae one after the other, independently of the number of visible vertebrae. This instance-by-instance segmentation is enabled by combining the network with a memory component that retains information about already segmented vertebrae. The network iteratively analyzes image patches, using information from both image and memory to search for the next vertebra. To efficiently traverse the image, we include the prior knowledge that the vertebrae are always located next to each other, which is used to follow the vertebral column. The network concurrently performs multiple tasks, which are segmentation of a vertebra, regression of its anatomical label and prediction whether the vertebra is completely visible in the image, which allows to exclude incompletely visible vertebrae from further analyses. The predicted anatomical labels of the individual vertebrae are additionally refined with a maximum likelihood approach, choosing the overall most likely labeling if all detected vertebrae are taken into account. This method was evaluated with five diverse datasets, including multiple modalities (CT and MR), various fields of view and coverages of different sections of the spine, and a particularly challenging set of low-dose chest CT scans. For vertebra segmentation, the average Dice score was 94.9 ± 2.1% with an average absolute symmetric surface distance of 0.2 ± 10.1mm. The anatomical identification had an accuracy of 93 %, corresponding to a single case with mislabeled vertebrae. Vertebrae were classified as completely or incompletely visible with an accuracy of 97 %. The proposed iterative segmentation method compares favorably with state-of-the-art methods and is fast, flexible and generalizable.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Precise segmentation and anatomical identification of the vertebrae provides the basis for automatic analysis of the spine, such as detection of vertebral compression fractures or other abnormalities. Most dedicated spine CT and MR scans as well as scans of the chest, abdomen or neck cover only part of the spine. Segmentation and identification should therefore not rely on the visibility of certain vertebrae or a certain number of vertebrae. We propose an iterative instance segmentation approach that uses a fully convolutional neural network to segment and label vertebrae one after the other, independently of the number of visible vertebrae. This instance-by-instance segmentation is enabled by combining the network with a memory component that retains information about already segmented vertebrae. The network iteratively analyzes image patches, using information from both image and memory to search for the next vertebra. To efficiently traverse the image, we include the prior knowledge that the vertebrae are always located next to each other, which is used to follow the vertebral column. The network concurrently performs multiple tasks, which are segmentation of a vertebra, regression of its anatomical label and prediction whether the vertebra is completely visible in the image, which allows to exclude incompletely visible vertebrae from further analyses. The predicted anatomical labels of the individual vertebrae are additionally refined with a maximum likelihood approach, choosing the overall most likely labeling if all detected vertebrae are taken into account. This method was evaluated with five diverse datasets, including multiple modalities (CT and MR), various fields of view and coverages of different sections of the spine, and a particularly challenging set of low-dose chest CT scans. For vertebra segmentation, the average Dice score was 94.9 ± 2.1% with an average absolute symmetric surface distance of 0.2 ± 10.1mm. The anatomical identification had an accuracy of 93 %, corresponding to a single case with mislabeled vertebrae. Vertebrae were classified as completely or incompletely visible with an accuracy of 97 %. The proposed iterative segmentation method compares favorably with state-of-the-art methods and is fast, flexible and generalizable. |
| 10. | N. Lessmann, P.A. de Jong, C. Celeng, R.A.P. Takx, M.A. Viergever, B. van Ginneken, I. Išgum Sex differences in coronary artery and thoracic aorta calcification and their association with cardiovascular mortality in heavy smokers Journal Article JACC: Cardiovascular Imaging, 12 (9), pp. 1808-1817, 2019. @article{Lessmann2019, title = {Sex differences in coronary artery and thoracic aorta calcification and their association with cardiovascular mortality in heavy smokers}, author = {N. Lessmann, P.A. de Jong, C. Celeng, R.A.P. Takx, M.A. Viergever, B. van Ginneken, I. Išgum}, url = {https://dx.doi.org/10.1016/j.jcmg.2018.10.026}, year = {2019}, date = {2019-01-16}, journal = {JACC: Cardiovascular Imaging}, volume = {12}, number = {9}, pages = {1808-1817}, abstract = {Objectives: The aim of this study was to investigate sex differences in the prevalence, extent, and association of coronary artery calcium (CAC) and thoracic aorta calcium (TAC) scores with cardiovascular mortality in a population eligible for lung screening. Background: CAC and TAC scores derived from chest computed tomography (CT) might be useful biomarkers for individualized cardiovascular disease prevention and could be especially relevant in high-risk populations such as heavy smokers. Therefore, it is important to know the prevalence of arterial calcifications in male and female heavy smokers, and if there are differences in the predictive value calcifications carry. Methods: We performed a nested case–control study with 5,718 participants of the CT arm of the NLST (National Lung Screening Trial). Prevalence and extent of CAC and TAC were resampled to the full cohort to provide unbiased estimates of the typical calcium burden of male and female heavy smokers. Weighted Cox proportional hazards regression was used to assess differences in the association of CAC and TAC scores with all-cause and cardiovascular mortality. Results: CAC was substantially more common and more severe in men (prevalence: 81% vs. 60%; median volume: 104 mm³ vs.12 mm³). Women had CAC comparable to that of men who were 10 years younger. TAC was equally common in men and women, with a tendency to be more pronounced in women (prevalence: 92% vs. 93%; median volume: 388 mm³ vs. 404 mm³). Both types of calcification were associated with increased cardiovascular and all-cause mortality. TAC scores improved the prediction of coronary heart disease mortality over CAC in men, but not in women. In both sexes, TAC, but not CAC, was associated with cardiovascular mortality other than coronary heart disease. Conclusions: CAC develops later in women, whereas TAC develops equally in both sexes. CAC is strongly associated with coronary heart disease, whereas TAC is especially associated with extracardiac vascular mortality in either sex.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Objectives: The aim of this study was to investigate sex differences in the prevalence, extent, and association of coronary artery calcium (CAC) and thoracic aorta calcium (TAC) scores with cardiovascular mortality in a population eligible for lung screening. Background: CAC and TAC scores derived from chest computed tomography (CT) might be useful biomarkers for individualized cardiovascular disease prevention and could be especially relevant in high-risk populations such as heavy smokers. Therefore, it is important to know the prevalence of arterial calcifications in male and female heavy smokers, and if there are differences in the predictive value calcifications carry. Methods: We performed a nested case–control study with 5,718 participants of the CT arm of the NLST (National Lung Screening Trial). Prevalence and extent of CAC and TAC were resampled to the full cohort to provide unbiased estimates of the typical calcium burden of male and female heavy smokers. Weighted Cox proportional hazards regression was used to assess differences in the association of CAC and TAC scores with all-cause and cardiovascular mortality. Results: CAC was substantially more common and more severe in men (prevalence: 81% vs. 60%; median volume: 104 mm³ vs.12 mm³). Women had CAC comparable to that of men who were 10 years younger. TAC was equally common in men and women, with a tendency to be more pronounced in women (prevalence: 92% vs. 93%; median volume: 388 mm³ vs. 404 mm³). Both types of calcification were associated with increased cardiovascular and all-cause mortality. TAC scores improved the prediction of coronary heart disease mortality over CAC in men, but not in women. In both sexes, TAC, but not CAC, was associated with cardiovascular mortality other than coronary heart disease. Conclusions: CAC develops later in women, whereas TAC develops equally in both sexes. CAC is strongly associated with coronary heart disease, whereas TAC is especially associated with extracardiac vascular mortality in either sex. |
| 11. | J. Šprem, B.D. de Vos, N. Lessmann, R.W. van Hamersvelt, M.J.W. Greuter, P.A. de Jong, T. Leiner, M.A. Viergever, I. Išgum Coronary calcium scoring with partial volume correction in anthropomorphic thorax phantom and screening chest CT images Journal Article PLoS One, 13 (12), pp. e0209318, 2018. @article{Šprem2018b, title = {Coronary calcium scoring with partial volume correction in anthropomorphic thorax phantom and screening chest CT images}, author = {J. Šprem, B.D. de Vos, N. Lessmann, R.W. van Hamersvelt, M.J.W. Greuter, P.A. de Jong, T. Leiner, M.A. Viergever, I. Išgum}, url = {https://doi.org/10.1371/journal.pone.0209318}, year = {2018}, date = {2018-12-20}, journal = {PLoS One}, volume = {13}, number = {12}, pages = {e0209318}, abstract = {Introduction: The amount of coronary artery calcium determined in CT scans is a well established predictor of cardiovascular events. However, high interscan variability of coronary calcium quantification may lead to incorrect cardiovascular risk assignment. Partial volume effect contributes to high interscan variability. Hence, we propose a method for coronary calcium quantification employing partial volume Methods: Two phantoms containing artificial coronary artery calcifications and 293 subject chest CT scans were used. The first and second phantom contained nine calcifications and the second phantom contained three artificial arteries with three calcifications of different volumes, shapes and densities. The first phantom was scanned five times with and without extension rings. The second phantom was scanned three times without and with simulated cardiac motion (10 and 30 mm/s). Chest CT scans were acquired without ECG-synchronization and reconstructed using sharp and soft kernels. Coronary calcifications were annotated employing the clinically used intensity value thresholding (130 HU). Thereafter, a threshold separating each calcification from its background was determined using an Expectation-Maximization algorithm. Finally, for each lesion the partial content of calcification in each voxel was determined depending on its intensity and the determined threshold. Results: Clinical calcium scoring resulted in overestimation of calcium volume for medium and high density calcifications in the first phantom, and overestimation of calcium volume for high density and underestimation for low density calcifications in the second phantom. With induced motion these effects were further emphasized. The proposed quantification resulted in better accuracy and substantially lower over- and underestimation of calcium volume even in presence of motion. In chest CT, the agreement between calcium scores from the two reconstructions improved when proposed method was Conclusion: Compared with clinical calcium scoring, proposed quantification provides a better estimate of the true calcium volume in phantoms and better agreement in calcium scores between different subject scan reconstructions.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Introduction: The amount of coronary artery calcium determined in CT scans is a well established predictor of cardiovascular events. However, high interscan variability of coronary calcium quantification may lead to incorrect cardiovascular risk assignment. Partial volume effect contributes to high interscan variability. Hence, we propose a method for coronary calcium quantification employing partial volume Methods: Two phantoms containing artificial coronary artery calcifications and 293 subject chest CT scans were used. The first and second phantom contained nine calcifications and the second phantom contained three artificial arteries with three calcifications of different volumes, shapes and densities. The first phantom was scanned five times with and without extension rings. The second phantom was scanned three times without and with simulated cardiac motion (10 and 30 mm/s). Chest CT scans were acquired without ECG-synchronization and reconstructed using sharp and soft kernels. Coronary calcifications were annotated employing the clinically used intensity value thresholding (130 HU). Thereafter, a threshold separating each calcification from its background was determined using an Expectation-Maximization algorithm. Finally, for each lesion the partial content of calcification in each voxel was determined depending on its intensity and the determined threshold. Results: Clinical calcium scoring resulted in overestimation of calcium volume for medium and high density calcifications in the first phantom, and overestimation of calcium volume for high density and underestimation for low density calcifications in the second phantom. With induced motion these effects were further emphasized. The proposed quantification resulted in better accuracy and substantially lower over- and underestimation of calcium volume even in presence of motion. In chest CT, the agreement between calcium scores from the two reconstructions improved when proposed method was Conclusion: Compared with clinical calcium scoring, proposed quantification provides a better estimate of the true calcium volume in phantoms and better agreement in calcium scores between different subject scan reconstructions. |
| 12. | J. Šprem; B.D. de Vos; N. Lessmann; P.A. de Jong; M.A. Viergever; I. Išgum Impact of automatically detected motion artifacts on coronary calcium scoring in chest CT Journal Article Journal of Medical Imaging, 5 (4), pp. 044007 , 2018. @article{Šprem2018, title = {Impact of automatically detected motion artifacts on coronary calcium scoring in chest CT}, author = {J. Šprem and B.D. de Vos and N. Lessmann and P.A. de Jong and M.A. Viergever and I. Išgum}, url = {https://doi.org/10.1117/1.JMI.5.4.044007}, year = {2018}, date = {2018-12-11}, journal = {Journal of Medical Imaging}, volume = {5}, number = {4}, pages = {044007 }, abstract = {The amount of coronary artery calcification (CAC) quantified in CT scans enables prediction of cardiovascular disease (CVD) risk. However, interscan variability of CAC quantification is high, especially in scans made without ECG synchronization. We propose a method for automatic detection of CACs that are severely affected by cardiac motion. Subsequently, we evaluate the impact of such CACs on CAC quantification and CVD risk determination. This study includes 1000 baseline and 585 one year follow-up low-dose chest CTs from the National Lung Screening Trial. 415 baseline scans are used to train and evaluate a convolutional neural network that identifies observer determined CACs affected by severe motion artifacts. Thereafter, 585 paired scans acquired at baseline and follow-up were used to evaluate the impact of severe motion artifacts on CAC quantification and risk categorization. Based on the CAC amount the scans were categorized into four standard CVD risk categories. The method identified CACs affected by severe motion artifacts with 85.2% accuracy. Moreover, reproducibility of CAC scores in scan pairs is higher in scans containing mostly CACs not affected by severe cardiac motion. Hence, the proposed method enables identification of scans affected by severe cardiac motion where CAC quantification may not be reproducible.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The amount of coronary artery calcification (CAC) quantified in CT scans enables prediction of cardiovascular disease (CVD) risk. However, interscan variability of CAC quantification is high, especially in scans made without ECG synchronization. We propose a method for automatic detection of CACs that are severely affected by cardiac motion. Subsequently, we evaluate the impact of such CACs on CAC quantification and CVD risk determination. This study includes 1000 baseline and 585 one year follow-up low-dose chest CTs from the National Lung Screening Trial. 415 baseline scans are used to train and evaluate a convolutional neural network that identifies observer determined CACs affected by severe motion artifacts. Thereafter, 585 paired scans acquired at baseline and follow-up were used to evaluate the impact of severe motion artifacts on CAC quantification and risk categorization. Based on the CAC amount the scans were categorized into four standard CVD risk categories. The method identified CACs affected by severe motion artifacts with 85.2% accuracy. Moreover, reproducibility of CAC scores in scan pairs is higher in scans containing mostly CACs not affected by severe cardiac motion. Hence, the proposed method enables identification of scans affected by severe cardiac motion where CAC quantification may not be reproducible. |
| 13. | S.A.M. Gernaat, S.G.M. van Velzen, V. Koh, M.J. Emaus, I. Išgum, N. Lessmann, S. Moes, A. Jacobson, P.W. Tan, D.E. Grobbee, D.H.J. van den Bongard, J.I. Tang, H.M. Verkooijen Radiotherapy and Oncology, 127 (3), pp. 487-492, 2018. @article{Velzen2018, title = {Automatic quantification of calcifications in the coronary arteries and thoracic aorta on radiotherapy planning CT scans of Western and Asian breast cancer patients}, author = {S.A.M. Gernaat, S.G.M. van Velzen, V. Koh, M.J. Emaus, I. Išgum, N. Lessmann, S. Moes, A. Jacobson, P.W. Tan, D.E. Grobbee, D.H.J. van den Bongard, J.I. Tang, H.M. Verkooijen}, url = {https://doi.org/10.1016/j.radonc.2018.04.011}, year = {2018}, date = {2018-04-24}, journal = {Radiotherapy and Oncology}, volume = {127}, number = {3}, pages = {487-492}, abstract = {Purpose This study automatically quantified calcifications in coronary arteries (CAC) and thoracic aorta (TAC) on breast planning computed tomography (CT) scans and assessed its reproducibility compared to manual scoring. Material and Methods Dutch (n=1,199) and Singaporean (n=1,090) breast cancer patients with radiotherapy planning CT scan were included. CAC and TAC were automatically scored using deep learning algorithm. CVD risk categories were based on Agatson CAC: 0, 1-10, 11-100, 101-400 and >400. Reliability between automatic and manual scoring was assessed in 120 randomly selected CT scans from each population, with linearly weighted kappa for CAC categories and intraclass correlation coefficient for TAC. Results Median age was higher in Dutch patients than Singaporean patients: 57 versus 52 years. CAC and TAC increased with age and were more present in Dutch patients than Singaporean patients: 24.2% versus 17.3% and 73.0% versus 62.2%, respectively. Reliability of CAC categories and TAC was excellent in the Netherlands (0.85 (95% confidence interval (CI)=0.77-0.93) and 0.98 (95% CI=0.96-0.98) respectively) and Singapore (0.90 (95% CI=0.84-0.96) and 0.99 (95% CI=0.98-0.99) respectively). Conclusions CAC and TAC prevalence was considerable and increased with age. Deep learning software is a reliable method to automatically measure CAC and TAC on radiotherapy breast CT scans.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Purpose This study automatically quantified calcifications in coronary arteries (CAC) and thoracic aorta (TAC) on breast planning computed tomography (CT) scans and assessed its reproducibility compared to manual scoring. Material and Methods Dutch (n=1,199) and Singaporean (n=1,090) breast cancer patients with radiotherapy planning CT scan were included. CAC and TAC were automatically scored using deep learning algorithm. CVD risk categories were based on Agatson CAC: 0, 1-10, 11-100, 101-400 and >400. Reliability between automatic and manual scoring was assessed in 120 randomly selected CT scans from each population, with linearly weighted kappa for CAC categories and intraclass correlation coefficient for TAC. Results Median age was higher in Dutch patients than Singaporean patients: 57 versus 52 years. CAC and TAC increased with age and were more present in Dutch patients than Singaporean patients: 24.2% versus 17.3% and 73.0% versus 62.2%, respectively. Reliability of CAC categories and TAC was excellent in the Netherlands (0.85 (95% confidence interval (CI)=0.77-0.93) and 0.98 (95% CI=0.96-0.98) respectively) and Singapore (0.90 (95% CI=0.84-0.96) and 0.99 (95% CI=0.98-0.99) respectively). Conclusions CAC and TAC prevalence was considerable and increased with age. Deep learning software is a reliable method to automatically measure CAC and TAC on radiotherapy breast CT scans. |
| 14. | N. Lessmann, B. van Ginneken, M. Zreik, P.A. de Jong, B.D. de Vos, M.A. Viergever, I. Išgum Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions Journal Article IEEE Transactions on Medical Imaging, 37 (2), pp. 615-625, 2018. @article{Lessmann2017, title = {Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions}, author = {N. Lessmann, B. van Ginneken, M. Zreik, P.A. de Jong, B.D. de Vos, M.A. Viergever, I. Išgum}, url = {https://arxiv.org/pdf/1711.00349.pdf}, year = {2018}, date = {2018-02-01}, journal = {IEEE Transactions on Medical Imaging}, volume = {37}, number = {2}, pages = {615-625}, abstract = {Heavy smokers undergoing screening with low-dose chest CT are affected by cardiovascular disease as much as by lung cancer. Low-dose chest CT scans acquired in screening enable quantification of atherosclerotic calcifications and thus enable identification of subjects at increased cardiovascular risk. This paper presents a method for automatic detection of coronary artery, thoracic aorta and cardiac valve calcifications in low-dose chest CT using two consecutive convolutional neural networks. The first network identifies and labels potential calcifications according to their anatomical location and the second network identifies true calcifications among the detected candidates. This method was trained and evaluated on a set of 1744 CT scans from the National Lung Screening Trial. To determine whether any reconstruction or only images reconstructed with soft tissue filters can be used for calcification detection, we evaluated the method on soft and medium/sharp filter reconstructions separately. On soft filter reconstructions, the method achieved F1 scores of 0.89, 0.89, 0.67, and 0.55 for coronary artery, thoracic aorta, aortic valve and mitral valve calcifications, respectively. On sharp filter reconstructions, the F1 scores were 0.84, 0.81, 0.64, and 0.66, respectively. Linearly weighted kappa coefficients for risk category assignment based on per subject coronary artery calcium were 0.91 and 0.90 for soft and sharp filter reconstructions, respectively. These results demonstrate that the presented method enables reliable automatic cardiovascular risk assessment in all low-dose chest CT scans acquired for lung cancer screening.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Heavy smokers undergoing screening with low-dose chest CT are affected by cardiovascular disease as much as by lung cancer. Low-dose chest CT scans acquired in screening enable quantification of atherosclerotic calcifications and thus enable identification of subjects at increased cardiovascular risk. This paper presents a method for automatic detection of coronary artery, thoracic aorta and cardiac valve calcifications in low-dose chest CT using two consecutive convolutional neural networks. The first network identifies and labels potential calcifications according to their anatomical location and the second network identifies true calcifications among the detected candidates. This method was trained and evaluated on a set of 1744 CT scans from the National Lung Screening Trial. To determine whether any reconstruction or only images reconstructed with soft tissue filters can be used for calcification detection, we evaluated the method on soft and medium/sharp filter reconstructions separately. On soft filter reconstructions, the method achieved F1 scores of 0.89, 0.89, 0.67, and 0.55 for coronary artery, thoracic aorta, aortic valve and mitral valve calcifications, respectively. On sharp filter reconstructions, the F1 scores were 0.84, 0.81, 0.64, and 0.66, respectively. Linearly weighted kappa coefficients for risk category assignment based on per subject coronary artery calcium were 0.91 and 0.90 for soft and sharp filter reconstructions, respectively. These results demonstrate that the presented method enables reliable automatic cardiovascular risk assessment in all low-dose chest CT scans acquired for lung cancer screening. |
| 15. | M. Zreik, N. Lessmann, R.W. van Hamersvelt, J.M. Wolterink, M. Voskuil, M.A. Viergever, T. Leiner, I. Išgum Medical Image Analysis, 44 , pp. 72-85, 2018. @article{Zreik2017b, title = {Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis}, author = {M. Zreik, N. Lessmann, R.W. van Hamersvelt, J.M. Wolterink, M. Voskuil, M.A. Viergever, T. Leiner, I. Išgum}, url = {https://arxiv.org/abs/1711.08917}, year = {2018}, date = {2018-02-01}, journal = {Medical Image Analysis}, volume = {44}, pages = {72-85}, abstract = {In patients with coronary artery stenoses of intermediate severity, the functional signi cance needs to be determined. Fractional flow reserve (FFR) measurement, performed during invasive coronary angiography (ICA), is most often used in clinical practice. To reduce the number of ICA procedures, we present a method for automatic identi cation of patients with functionally signi cant coronary artery stenoses, employing deep learning analysis of the left ventricle (LV) myocardium in rest coronary CT angiography (CCTA). The study includes consecutively acquired CCTA scans of 166 patients who underwent invasive FFR measurements. To identify patients with a functionally signi cant coronary artery stenosis, analysis is performed in several stages. First, the LV myocardium is segmented using a multiscale convolutional neural network (CNN). To characterize the segmented LV myocardium, it is subsequently encoded using unsupervised convolutional autoencoder (CAE). As ischemic changes are expected to appear locally, the LV myocardium is divided into a number of spatially connected clusters, and statistics of the encodings are computed as features. Thereafter, patients are classi ed according to the presence of functionally signi cant stenosis using an SVM classi er based on the extracted features. Quantitative evaluation of LV myocardium segmentation in 20 images resulted in an average Dice coecient of 0:91 and an average mean absolute distance between the segmented and reference LV boundaries of 0:7 mm. Twenty CCTA images were used to train the LV myocardium encoder. Classi cation of patients was evaluated in the remaining 126 CCTA scans in 50 10-fold cross-validation experiments and resulted in an area under the receiver operating characteristic curve of 0.74 0.02. At sensitivity levels 0.60, 0.70 and 0.80, the corresponding speci city was 0.77, 0.71 and 0.59, respectively. The results demonstrate that automatic analysis of the LV myocardium in a single CCTA scan acquired at rest, without assessment of the anatomy of the coronary arteries, can be used to identify patients with functionally signi cant coronary artery stenosis. This might reduce the number of patients undergoing unnecessary invasive FFR measurements.}, keywords = {}, pubstate = {published}, tppubtype = {article} } In patients with coronary artery stenoses of intermediate severity, the functional signi cance needs to be determined. Fractional flow reserve (FFR) measurement, performed during invasive coronary angiography (ICA), is most often used in clinical practice. To reduce the number of ICA procedures, we present a method for automatic identi cation of patients with functionally signi cant coronary artery stenoses, employing deep learning analysis of the left ventricle (LV) myocardium in rest coronary CT angiography (CCTA). The study includes consecutively acquired CCTA scans of 166 patients who underwent invasive FFR measurements. To identify patients with a functionally signi cant coronary artery stenosis, analysis is performed in several stages. First, the LV myocardium is segmented using a multiscale convolutional neural network (CNN). To characterize the segmented LV myocardium, it is subsequently encoded using unsupervised convolutional autoencoder (CAE). As ischemic changes are expected to appear locally, the LV myocardium is divided into a number of spatially connected clusters, and statistics of the encodings are computed as features. Thereafter, patients are classi ed according to the presence of functionally signi cant stenosis using an SVM classi er based on the extracted features. Quantitative evaluation of LV myocardium segmentation in 20 images resulted in an average Dice coecient of 0:91 and an average mean absolute distance between the segmented and reference LV boundaries of 0:7 mm. Twenty CCTA images were used to train the LV myocardium encoder. Classi cation of patients was evaluated in the remaining 126 CCTA scans in 50 10-fold cross-validation experiments and resulted in an area under the receiver operating characteristic curve of 0.74 0.02. At sensitivity levels 0.60, 0.70 and 0.80, the corresponding speci city was 0.77, 0.71 and 0.59, respectively. The results demonstrate that automatic analysis of the LV myocardium in a single CCTA scan acquired at rest, without assessment of the anatomy of the coronary arteries, can be used to identify patients with functionally signi cant coronary artery stenosis. This might reduce the number of patients undergoing unnecessary invasive FFR measurements. |
| 16. | E. Pompe, P.A. de Jong, D.A. Lynch, N. Lessmann, I. Isgum, B. van Ginneken, J.-W.J. Lammers, F.A.A. Mohamed Hoesein Computed tomographic findings in subjects who died from respiratory disease in the National Lung Screening Trial Journal Article European Respiratory Journal, 49 , pp. 1601814, 2017. @article{pompe:2017-3151, title = {Computed tomographic findings in subjects who died from respiratory disease in the National Lung Screening Trial}, author = {E. Pompe, P.A. de Jong, D.A. Lynch, N. Lessmann, I. Isgum, B. van Ginneken, J.-W.J. Lammers, F.A.A. Mohamed Hoesein}, url = {https://doi.org/10.1183/13993003.01814-2016}, year = {2017}, date = {2017-04-19}, journal = {European Respiratory Journal}, volume = {49}, pages = {1601814}, abstract = {We evaluated the prevalence of significant lung abnormalities on computed tomography (CT) in patients who died from a respiratory illness other than lung cancer in the National Lung Screening Trial (NLST). In this retrospective case–control study, NLST participants in the CT arm who died of respiratory illness other than lung cancer were matched for age, sex, pack-years and smoking status to a surviving control. A chest radiologist and a radiology resident blinded to the outcome independently scored baseline CT scans visually and qualitatively for the presence of emphysema, airway wall thickening and fibrotic lung disease. The prevalence of CT abnormalities was compared between cases and controls by using chi-squared tests. In total, 167 participants died from a respiratory cause other than lung cancer. The prevalence of severe emphysema, airway wall thickening and fibrotic lung disease were 28.7% versus 4.8%, 26.9% versus 13.2% and 18.6% versus 0.5% in cases and controls, respectively. Radiological findings were significantly more prevalent in deaths compared with controls (all p<0.001). CT-diagnosed severe emphysema, airway wall thickening and fibrosis were much more common in NLST participants who died from respiratory disease, and CT may provide an additional means of identifying these diseases.}, keywords = {}, pubstate = {published}, tppubtype = {article} } We evaluated the prevalence of significant lung abnormalities on computed tomography (CT) in patients who died from a respiratory illness other than lung cancer in the National Lung Screening Trial (NLST). In this retrospective case–control study, NLST participants in the CT arm who died of respiratory illness other than lung cancer were matched for age, sex, pack-years and smoking status to a surviving control. A chest radiologist and a radiology resident blinded to the outcome independently scored baseline CT scans visually and qualitatively for the presence of emphysema, airway wall thickening and fibrotic lung disease. The prevalence of CT abnormalities was compared between cases and controls by using chi-squared tests. In total, 167 participants died from a respiratory cause other than lung cancer. The prevalence of severe emphysema, airway wall thickening and fibrotic lung disease were 28.7% versus 4.8%, 26.9% versus 13.2% and 18.6% versus 0.5% in cases and controls, respectively. Radiological findings were significantly more prevalent in deaths compared with controls (all p<0.001). CT-diagnosed severe emphysema, airway wall thickening and fibrosis were much more common in NLST participants who died from respiratory disease, and CT may provide an additional means of identifying these diseases. |
Inproceedings |
|
| 1. | S.G.M. van Velzen, M. Zreik, N. Lessmann, M.A. Viergever, P.A. de Jong, H.M. Verkooijen, I. Išgum Direct prediction of cardiovascular mortality from low-dose chest CT using deep learning Inproceedings In: SPIE Medical Imaging, pp. 109490X, 2019. @inproceedings{Velzen2019, title = {Direct prediction of cardiovascular mortality from low-dose chest CT using deep learning}, author = {S.G.M. van Velzen, M. Zreik, N. Lessmann, M.A. Viergever, P.A. de Jong, H.M. Verkooijen, I. Išgum}, url = {https://arxiv.org/abs/1810.02277}, doi = {10.1117/12.2512400}, year = {2019}, date = {2019-02-17}, booktitle = {SPIE Medical Imaging}, volume = {10949}, pages = {109490X}, abstract = {Cardiovascular disease (CVD) is a leading cause of death in the lung cancer screening population. Chest CT scans made in lung cancer screening are suitable for identification of participants at risk of CVD. Existing methods analyzing CT images from lung cancer screening for prediction of CVD events or mortality use engineered features extracted from the images combined with patient information. In this work we propose a method that automatically predicts 5-year cardiovascular mortality directly from chest CT scans without the need for hand-crafting image features. A set of 1,583 participants of the National Lung Screening Trial was included (1,188 survivors, 395 non-survivors). Low-dose chest CT images acquired at baseline were analyzed and the follow-up time was 5 years. To limit the analysis to the heart region, the heart was first localized by our previously developed algorithm for organ localization exploiting convolutional neural networks. Thereafter, a convolutional autoencoder was used to encode the identified heart region. Finally, based on the extracted encodings subjects were classified into survivors or non-survivors using a support vector machine classifier. The performance of the method was assessed in eight cross-validation experiments with 1,433 images used for training, 50 for validation and 100 for testing. The method achieved a performance with an area under the ROC curve of 0.72. The results demonstrate that prediction of cardiovascular mortality directly from low-dose screening chest CT scans, without hand-crafted features, is feasible, allowing identification of subjects at risk of fatal CVD events.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Cardiovascular disease (CVD) is a leading cause of death in the lung cancer screening population. Chest CT scans made in lung cancer screening are suitable for identification of participants at risk of CVD. Existing methods analyzing CT images from lung cancer screening for prediction of CVD events or mortality use engineered features extracted from the images combined with patient information. In this work we propose a method that automatically predicts 5-year cardiovascular mortality directly from chest CT scans without the need for hand-crafting image features. A set of 1,583 participants of the National Lung Screening Trial was included (1,188 survivors, 395 non-survivors). Low-dose chest CT images acquired at baseline were analyzed and the follow-up time was 5 years. To limit the analysis to the heart region, the heart was first localized by our previously developed algorithm for organ localization exploiting convolutional neural networks. Thereafter, a convolutional autoencoder was used to encode the identified heart region. Finally, based on the extracted encodings subjects were classified into survivors or non-survivors using a support vector machine classifier. The performance of the method was assessed in eight cross-validation experiments with 1,433 images used for training, 50 for validation and 100 for testing. The method achieved a performance with an area under the ROC curve of 0.72. The results demonstrate that prediction of cardiovascular mortality directly from low-dose screening chest CT scans, without hand-crafted features, is feasible, allowing identification of subjects at risk of fatal CVD events. |
| 2. | N. Lessmann, B. van Ginneken, P.A. de Jong, I. Išgum Iterative fully convolutional neural networks for automatic vertebra segmentation Inproceedings In: Medical Imaging with Deep Learning (MIDL 2018), 2018. @inproceedings{Lessmann2018, title = {Iterative fully convolutional neural networks for automatic vertebra segmentation}, author = {N. Lessmann, B. van Ginneken, P.A. de Jong, I. Išgum}, url = {https://openreview.net/pdf?id=S1NnlZnjG}, year = {2018}, date = {2018-05-22}, booktitle = {Medical Imaging with Deep Learning (MIDL 2018)}, abstract = {Precise segmentation of the vertebrae is often required for automatic detection of vertebral abnormalities. This especially enables incidental detection of abnormalities such as compression fractures in images that were acquired for other diagnostic purposes. While many CT and MR scans of the chest and abdomen cover a section of the spine, they often do not cover the entire spine. Additionally, the first and last visible vertebrae are likely only partially included in such scans. In this paper, we therefore approach vertebra segmentation as an instance segmentation problem. A fully convolutional neural network is combined with an instance memory that retains information about already segmented vertebrae. This network iteratively analyzes image patches, using the instance memory to search for and segment the first not yet segmented vertebra. At the same time, each vertebra is classified as completely or partially visible, so that partially visible vertebrae can be excluded from further analyses. We evaluated this method on spine CT scans from a vertebra segmentation challenge and on low-dose chest CT scans. The method achieved an average Dice score of 95.8% and 92.1%, respectively, and a mean absolute surface distance of 0.194 mm and 0.344 mm.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Precise segmentation of the vertebrae is often required for automatic detection of vertebral abnormalities. This especially enables incidental detection of abnormalities such as compression fractures in images that were acquired for other diagnostic purposes. While many CT and MR scans of the chest and abdomen cover a section of the spine, they often do not cover the entire spine. Additionally, the first and last visible vertebrae are likely only partially included in such scans. In this paper, we therefore approach vertebra segmentation as an instance segmentation problem. A fully convolutional neural network is combined with an instance memory that retains information about already segmented vertebrae. This network iteratively analyzes image patches, using the instance memory to search for and segment the first not yet segmented vertebra. At the same time, each vertebra is classified as completely or partially visible, so that partially visible vertebrae can be excluded from further analyses. We evaluated this method on spine CT scans from a vertebra segmentation challenge and on low-dose chest CT scans. The method achieved an average Dice score of 95.8% and 92.1%, respectively, and a mean absolute surface distance of 0.194 mm and 0.344 mm. |
| 3. | N. Lessmann, B. van Ginneken, I. Išgum Iterative convolutional neural networks for automatic vertebra identification and segmentation in CT images Inproceedings In: SPIE Medical Imaging, pp. 1057408, 2018. @inproceedings{less18, title = {Iterative convolutional neural networks for automatic vertebra identification and segmentation in CT images}, author = {N. Lessmann, B. van Ginneken, I. Išgum}, url = {https://doi.org/10.1117/12.2292731}, year = {2018}, date = {2018-02-11}, booktitle = {SPIE Medical Imaging}, pages = {1057408}, abstract = {Segmentation and identification of the vertebrae in CT images are important initial steps for automatic analysis of the spine. This paper presents an automatic method based on iteratively applied convolutional neural networks. This approach utilizes the inherent order of the vertebral column to simplify the detection problem, so that a deep neural network can be trained with a low number of manual reference segmentations. Vertebrae are identified and segmented individually in sequential order relative to a reference vertebra. Additionally, a coarse-to-fine segmentation scheme is employed: The localization and identification of the vertebrae is first performed in low-resolution images that enable the analysis of context information. The fine segmentation is performed afterwards in the original high-resolution images. In contrast to most previous methods for vertebra segmentation, this approach is not focused on modeling shape information. The method was trained and evaluated with 15 spine CT scans from the MICCAI CSI 2014 workshop challenge. These scans cover the whole thoracic and lumbar part of the spine of healthy young adults. In contrast to a non-iterative convolutional neural network, the proposed method correctly identified all vertebrae. The method achieved a mean Dice coefficient of 0.948 and a mean surface distance of 0.29 mm and thus outperforms the best method that participated in the original challenge.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Segmentation and identification of the vertebrae in CT images are important initial steps for automatic analysis of the spine. This paper presents an automatic method based on iteratively applied convolutional neural networks. This approach utilizes the inherent order of the vertebral column to simplify the detection problem, so that a deep neural network can be trained with a low number of manual reference segmentations. Vertebrae are identified and segmented individually in sequential order relative to a reference vertebra. Additionally, a coarse-to-fine segmentation scheme is employed: The localization and identification of the vertebrae is first performed in low-resolution images that enable the analysis of context information. The fine segmentation is performed afterwards in the original high-resolution images. In contrast to most previous methods for vertebra segmentation, this approach is not focused on modeling shape information. The method was trained and evaluated with 15 spine CT scans from the MICCAI CSI 2014 workshop challenge. These scans cover the whole thoracic and lumbar part of the spine of healthy young adults. In contrast to a non-iterative convolutional neural network, the proposed method correctly identified all vertebrae. The method achieved a mean Dice coefficient of 0.948 and a mean surface distance of 0.29 mm and thus outperforms the best method that participated in the original challenge. |
| 4. | N. Lessmann, I. Isgum, A.A.A. Setio, B.D. de Vos, F. Ciompi, P.A. de Jong, M. Oudkerk, W.P.Th.M. Mali, M.A. Viergever, B. van Ginneken Deep convolutional neural networks for automatic coronary calcium scoring in a screening study with low-dose chest CT Inproceedings In: SPIE Medical Imaging, pp. 978511, 2016, (Bla). @inproceedings{less16, title = {Deep convolutional neural networks for automatic coronary calcium scoring in a screening study with low-dose chest CT}, author = {N. Lessmann, I. Isgum, A.A.A. Setio, B.D. de Vos, F. Ciompi, P.A. de Jong, M. Oudkerk, W.P.Th.M. Mali, M.A. Viergever, B. van Ginneken}, url = {https://doi.org/10.1117/12.2216978 http://188.166.76.74/papers/Lessmann2016_CalciumScoringChestCT_DeepLearning_SPIE.pdf}, year = {2016}, date = {2016-03-01}, booktitle = {SPIE Medical Imaging}, volume = {9785}, pages = {978511}, abstract = {Coronary artery calcium (CAC) scoring can identify subjects at risk of cardiovascular events in screening programs with low-dose chest CT. We present an automatic method for CAC scoring based on deep convolutional neural networks. Candidates are extracted by intensity-based thresholding and subsequently classified by three concurrent networks that analyze three orthogonal 2D image patches per voxel. The networks consist of three convolutional steps and one fully-connected layer. In 231 subjects, this method detected on average 194.3 / 199.8mm3 CAC (sensitivity 97.2%), with 10.3mm3 false-positive volume per scan. Accuracy of cardiovascular risk category assignment was 84.4% (linearly weighted kappa 0.89).}, note = {Bla}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Coronary artery calcium (CAC) scoring can identify subjects at risk of cardiovascular events in screening programs with low-dose chest CT. We present an automatic method for CAC scoring based on deep convolutional neural networks. Candidates are extracted by intensity-based thresholding and subsequently classified by three concurrent networks that analyze three orthogonal 2D image patches per voxel. The networks consist of three convolutional steps and one fully-connected layer. In 231 subjects, this method detected on average 194.3 / 199.8mm3 CAC (sensitivity 97.2%), with 10.3mm3 false-positive volume per scan. Accuracy of cardiovascular risk category assignment was 84.4% (linearly weighted kappa 0.89). |
Abstracts |
|
| 1. | R. Gal, S.G. van Velzen, M.J. Emaus, D.H. van den Bongard, M.L. Gregorowitsch, E.L. Blezer, G. Sofie, N. Lessmann, M.G. Sattler, M.J. Hooning, A.J. Teske, J.J. Penninkhof, H. Meijer, J.P. Pignol, J. Verloop, I. Išgum, H.M. Verkooijen, Bragatston Study Group In: European Journal of Cancer, 138, pp. S6, 2020. @booklet{Gal2020, title = {The risk of cardiovascular disease in irradiated breast cancer patients: The role of cardiac calcifications and adjuvant treatment}, author = {R. Gal, S.G. van Velzen, M.J. Emaus, D.H. van den Bongard, M.L. Gregorowitsch, E.L. Blezer, G. Sofie, N. Lessmann, M.G. Sattler, M.J. Hooning, A.J. Teske, J.J. Penninkhof, H. Meijer, J.P. Pignol, J. Verloop, I. Išgum, H.M. Verkooijen, Bragatston Study Group }, url = {https://www.sciencedirect.com/science/article/pii/S0959804920305438?via%3Dihub}, doi = {10.1016/S0959-8049(20)30543-8}, year = {2020}, date = {2020-10-10}, journal = {European Journal of Cancer}, volume = {138}, pages = {S6}, abstract = {Background: (Neo) adjuvant treatments including anthracyclines, trastuzumab and (left-sided) radiotherapy (RT) are associated with an increased risk of cardiovascular disease (CVD). Breast cancer patients with pre-existing CVD risk factors have the highest risk of treatment induced cardiotoxicity. Coronary artery calcium (CAC) is a strong independent CVD risk factor and can be quantified on dedicated radiotherapy planning CT scans of the chest. Automated assessment of CAC scores in breast cancer patients planned for RT may be helpful in detecting patients at increased CVD risk. In the Bragatston study, we evaluate the association between automated CAC measurement on RT planning CT scans and the risk of CVD in breast cancer patients treated with RT. Methods: In this multicenter retrospective cohort study, CAC scores of breast cancer patients receiving RT between 2005 and 2016 were automatically calculated in planning CT scans using an deep learning algorithm and classified into Agatston categories (0, 1–10, 11–100, 101–399, >400 units). Tumor and treatment characteristics were obtained from the Netherlands Cancer Registry. Data on CVD occurrence were obtained from Dutch Hospital Data and the National Cause of Death Register. Cox proportional hazard regression models were used to evaluate the association between CAC scores and CVD risk. Stratification for left- vs right-sided RT and treatment with vs without anthracyclines was performed. Results: Data from 14,002 patients with a mean age of 58 years (SD = 11) were included. Twenty-nine percent of the patients had a CAC score of >0 (Table). At a median follow-up of 52 months (IQR: 27–82), 8% of the patients (n = 1138) were admitted to the hospital for CVD and 93 patients (1%) died from CVD. After adjustment for age and calendar year at planning CT, the risk of CVD increased with higher CAC, from 5% for patients without CAC to 28% of patients with a CAC score >400. The association between a high CAC score and CVD was strongest in patients treated with anthracyclines (HRCAC >400 = 5.4, 95%CI = 2.6–11.3). Conclusion: CAC detected on the RT planning CT is strongly associated with CVD risk. This finding is relevant for breast cancer patients since early identification of high risk patients enables switching to less cardiotoxic breast cancer treatment (e.g. adaptation of RT target volumes or technique, chemotherapy dose reduction). Also, patients can adopt targeted cardiopreventive interventions (e.g. lifestyle changes, pharmaco-prevention, close monitoring for early detection).}, howpublished = {European Journal of Cancer, 138, pp. S6}, month = {10}, keywords = {}, pubstate = {published}, tppubtype = {booklet} } Background: (Neo) adjuvant treatments including anthracyclines, trastuzumab and (left-sided) radiotherapy (RT) are associated with an increased risk of cardiovascular disease (CVD). Breast cancer patients with pre-existing CVD risk factors have the highest risk of treatment induced cardiotoxicity. Coronary artery calcium (CAC) is a strong independent CVD risk factor and can be quantified on dedicated radiotherapy planning CT scans of the chest. Automated assessment of CAC scores in breast cancer patients planned for RT may be helpful in detecting patients at increased CVD risk. In the Bragatston study, we evaluate the association between automated CAC measurement on RT planning CT scans and the risk of CVD in breast cancer patients treated with RT. Methods: In this multicenter retrospective cohort study, CAC scores of breast cancer patients receiving RT between 2005 and 2016 were automatically calculated in planning CT scans using an deep learning algorithm and classified into Agatston categories (0, 1–10, 11–100, 101–399, >400 units). Tumor and treatment characteristics were obtained from the Netherlands Cancer Registry. Data on CVD occurrence were obtained from Dutch Hospital Data and the National Cause of Death Register. Cox proportional hazard regression models were used to evaluate the association between CAC scores and CVD risk. Stratification for left- vs right-sided RT and treatment with vs without anthracyclines was performed. Results: Data from 14,002 patients with a mean age of 58 years (SD = 11) were included. Twenty-nine percent of the patients had a CAC score of >0 (Table). At a median follow-up of 52 months (IQR: 27–82), 8% of the patients (n = 1138) were admitted to the hospital for CVD and 93 patients (1%) died from CVD. After adjustment for age and calendar year at planning CT, the risk of CVD increased with higher CAC, from 5% for patients without CAC to 28% of patients with a CAC score >400. The association between a high CAC score and CVD was strongest in patients treated with anthracyclines (HRCAC >400 = 5.4, 95%CI = 2.6–11.3). Conclusion: CAC detected on the RT planning CT is strongly associated with CVD risk. This finding is relevant for breast cancer patients since early identification of high risk patients enables switching to less cardiotoxic breast cancer treatment (e.g. adaptation of RT target volumes or technique, chemotherapy dose reduction). Also, patients can adopt targeted cardiopreventive interventions (e.g. lifestyle changes, pharmaco-prevention, close monitoring for early detection). |
| 2. | S.G.M. van Velzen, J.G. Terry, B.D. de Vos, N Lessmann, S. Nair, A. Correa, H.M. Verkooijen J.J. Carr, I. Išgum In: Radiological Society of North America, 105th Annual Meeting, 2019. @booklet{vanVelzen2020c, title = {Automatic prediction of coronary heart disease events using coronary and thoracic aorta calcium among African Americans in the Jackson Heart study}, author = {S.G.M. van Velzen, J.G. Terry, B.D. de Vos, N Lessmann, S. Nair, A. Correa, H.M. Verkooijen J.J. Carr, I. Išgum}, url = {http://archive.rsna.org/2019/19006976.html}, year = {2019}, date = {2019-12-01}, booktitle = {Radiological Society of North America, 105th Annual Meeting}, abstract = {PURPOSE Coronary artery calcium (CAC) and thoracic aorta calcium (TAC) are predictors of CHD events. Given that CAC and TAC identification is time-consuming, methods for automatic quantification in CT have been developed. Hence, we investigate whether subjects who will experience a CHD event within 5 years from acquisition of cardiac CT can be identified using automatically extracted calcium scores. METHOD AND MATERIALS We included 2532 participants (age 59±11, 31% male) of the Jackson Heart Study without CHD history: 111 participants had a CHD event within 5 years from CT acquisition, defined by death certificates and medical records. For each subject a cardiac CT scan(GE Healthcare Lightspeed 16Pro, 2.5mm slice thickness, 2.5mm increment, 120kVP, 400mAs, ECG-triggered, no contrast) was available. Per-artery Agatston CAC scores (left anterior descending, left circumflex, right coronary artery) and TAC volume were automatically extracted with a previously developed AI algorithm. Scores were log transformed, combined with age and sex and all continuous variables were normalized to zero-mean and unit variance. We evaluated 3 models with 3-fold cross-validation where subjects were classified according to occurrence of CHD event using LASSO regression with 1) age, sex and CAC scores, 2) age, sex and TAC scores, and 3) all variables. Performance was evaluated with the area under the ROC curve (AUC). RESULTS In 1468 (58%) subjects no CAC and in 1240 (49%) no TAC was found. In remaining scans, median (range) CAC score was 78.7(1.6-5562.1): 49.5(0.0-4569.4), 0.0(0.0-2735.3), 3.9(0.0-3242.7) in the LDA, LCX and RCA, respectively. Median TAC volume was 116.8(4.7-7275.9). Prediction of CHD events using Model 1, 2 and 3 resulted in an AUC (95% CI) of 0.721(0.672-0.771), 0.735(0.686-0.785) and 0.727(0.678-0.776). Differences between the ROC curves were not significant (Model 1 and 2: p=0.80; 1 and 3: p=0.29; 2 and 3: p=0.76). CONCLUSION Identification of subjects at risk of a CHD event can be performed using automatically extracted CAC or TAC scores from cardiac CT. CLINICAL RELEVANCE/APPLICATION Prediction of CHD events from cardiac CT using TAC instead of CAC is feasible and may be advantageous in scans acquired without ECG-triggering or low image resolution.}, howpublished = {Radiological Society of North America, 105th Annual Meeting}, month = {12}, keywords = {}, pubstate = {published}, tppubtype = {booklet} } PURPOSE Coronary artery calcium (CAC) and thoracic aorta calcium (TAC) are predictors of CHD events. Given that CAC and TAC identification is time-consuming, methods for automatic quantification in CT have been developed. Hence, we investigate whether subjects who will experience a CHD event within 5 years from acquisition of cardiac CT can be identified using automatically extracted calcium scores. METHOD AND MATERIALS We included 2532 participants (age 59±11, 31% male) of the Jackson Heart Study without CHD history: 111 participants had a CHD event within 5 years from CT acquisition, defined by death certificates and medical records. For each subject a cardiac CT scan(GE Healthcare Lightspeed 16Pro, 2.5mm slice thickness, 2.5mm increment, 120kVP, 400mAs, ECG-triggered, no contrast) was available. Per-artery Agatston CAC scores (left anterior descending, left circumflex, right coronary artery) and TAC volume were automatically extracted with a previously developed AI algorithm. Scores were log transformed, combined with age and sex and all continuous variables were normalized to zero-mean and unit variance. We evaluated 3 models with 3-fold cross-validation where subjects were classified according to occurrence of CHD event using LASSO regression with 1) age, sex and CAC scores, 2) age, sex and TAC scores, and 3) all variables. Performance was evaluated with the area under the ROC curve (AUC). RESULTS In 1468 (58%) subjects no CAC and in 1240 (49%) no TAC was found. In remaining scans, median (range) CAC score was 78.7(1.6-5562.1): 49.5(0.0-4569.4), 0.0(0.0-2735.3), 3.9(0.0-3242.7) in the LDA, LCX and RCA, respectively. Median TAC volume was 116.8(4.7-7275.9). Prediction of CHD events using Model 1, 2 and 3 resulted in an AUC (95% CI) of 0.721(0.672-0.771), 0.735(0.686-0.785) and 0.727(0.678-0.776). Differences between the ROC curves were not significant (Model 1 and 2: p=0.80; 1 and 3: p=0.29; 2 and 3: p=0.76). CONCLUSION Identification of subjects at risk of a CHD event can be performed using automatically extracted CAC or TAC scores from cardiac CT. CLINICAL RELEVANCE/APPLICATION Prediction of CHD events from cardiac CT using TAC instead of CAC is feasible and may be advantageous in scans acquired without ECG-triggering or low image resolution. |
| 3. | S.G.M. van Velzen, N. Lessmann, M.J. Emaus, H. van den Bongard, H.M. Verkooijen, I. Išgum In: Radiological Society of North America, 105th Annual Meeting, 2019. @booklet{vanVelzen2019, title = {Deep learning for calcium scoring in radiotherapy treatment planning CT scans in breast cancer patients}, author = {S.G.M. van Velzen, N. Lessmann, M.J. Emaus, H. van den Bongard, H.M. Verkooijen, I. Išgum}, url = {http://archive.rsna.org/2019/19002536.html}, year = {2019}, date = {2019-12-01}, booktitle = {Radiological Society of North America, 105th Annual Meeting}, abstract = {PURPOSE Cardiovascular disease (CVD) is an important cause of mortality in breast cancer patients. Coronary artery calcification (CAC) and thoracic aorta calcification (TAC) are strong and independent risk factors for CVD and can be detected and quantified in radiotherapy treatment planning (RTTP) CT. Manual quantification of CAC and TAC is a tedious and time-consuming task. Therefore, we evaluated the performance of an AI system, developed for automatic calcium scoring in low-dose chest CT, in RTTP CT. METHOD AND MATERIALS We included 1409 breast cancer patients (age 56±7 years), who participated in the UMBRELLA cohort and underwent a RTTP CT (Philips Brilliance Big Bore CT, 120kVp, no ECG-triggering, no contrast, 3.0mm slice thickness). In a first step, CAC and TAC were manually annotated in these scans. In a second step, a deep learning algorithm was applied for automated detection of CAC and TAC. A baseline system was trained with 1181 low-dose chest CTs (all major CT vendors, 120/140kVp, no ECG-triggering, no contrast, 1.0-3.0mm slice thickness) from the National Lung Screening Trail (NLST). A RTTP-specific system was trained with the NLST scans and additionally 568 RTTP scans. The remaining 841 RTTP scans were used for evaluation. CAC was quantified as Agatston and volume scores; TAC as volume scores only. Agatston score was stratified into five risk categories: 0, 1-10, 11-100, 101-400, >400. Reproducibility between manual and automatic scores was evaluated with linearly weighted κ (categories) and Intraclass Correlation Coefficient (ICC, volume scores). RESULTS For the baseline system, ICCs were 0.85 (95% CI 0.83-0.87) and 0.98 (0.97-0.98) for CAC and TAC volumes, respectively. ICCs for the RRTP-specific system improved to 0.92 (0.91-0.93) and 0.99 (0.98-0.99) for CAC and TAC volumes, respectively. The baseline and RTTP-specific systems achieved a κ of 0.85 (0.80-0.90) and 0.89 (0.85-0.93). CONCLUSION An AI system trained on low-dose chest CTs allows accurate automatic CAC and TAC scoring in RTTP CT, which improves further upon RTTP-specific training. CLINICAL RELEVANCE/APPLICATION Accurate, fully automatic CVD risk assessment in breast cancer patients from readily available RTTP scans allows cost-effective identification of patients who may benefit from preventive treatment. }, howpublished = {Radiological Society of North America, 105th Annual Meeting}, month = {12}, keywords = {}, pubstate = {published}, tppubtype = {booklet} } PURPOSE Cardiovascular disease (CVD) is an important cause of mortality in breast cancer patients. Coronary artery calcification (CAC) and thoracic aorta calcification (TAC) are strong and independent risk factors for CVD and can be detected and quantified in radiotherapy treatment planning (RTTP) CT. Manual quantification of CAC and TAC is a tedious and time-consuming task. Therefore, we evaluated the performance of an AI system, developed for automatic calcium scoring in low-dose chest CT, in RTTP CT. METHOD AND MATERIALS We included 1409 breast cancer patients (age 56±7 years), who participated in the UMBRELLA cohort and underwent a RTTP CT (Philips Brilliance Big Bore CT, 120kVp, no ECG-triggering, no contrast, 3.0mm slice thickness). In a first step, CAC and TAC were manually annotated in these scans. In a second step, a deep learning algorithm was applied for automated detection of CAC and TAC. A baseline system was trained with 1181 low-dose chest CTs (all major CT vendors, 120/140kVp, no ECG-triggering, no contrast, 1.0-3.0mm slice thickness) from the National Lung Screening Trail (NLST). A RTTP-specific system was trained with the NLST scans and additionally 568 RTTP scans. The remaining 841 RTTP scans were used for evaluation. CAC was quantified as Agatston and volume scores; TAC as volume scores only. Agatston score was stratified into five risk categories: 0, 1-10, 11-100, 101-400, >400. Reproducibility between manual and automatic scores was evaluated with linearly weighted κ (categories) and Intraclass Correlation Coefficient (ICC, volume scores). RESULTS For the baseline system, ICCs were 0.85 (95% CI 0.83-0.87) and 0.98 (0.97-0.98) for CAC and TAC volumes, respectively. ICCs for the RRTP-specific system improved to 0.92 (0.91-0.93) and 0.99 (0.98-0.99) for CAC and TAC volumes, respectively. The baseline and RTTP-specific systems achieved a κ of 0.85 (0.80-0.90) and 0.89 (0.85-0.93). CONCLUSION An AI system trained on low-dose chest CTs allows accurate automatic CAC and TAC scoring in RTTP CT, which improves further upon RTTP-specific training. CLINICAL RELEVANCE/APPLICATION Accurate, fully automatic CVD risk assessment in breast cancer patients from readily available RTTP scans allows cost-effective identification of patients who may benefit from preventive treatment. |
| 4. | N. Khalili, N. Lessmann, E. Turk, M.A. Viergever, M.J.N.L. Benders, I. Išgum Brain tissue segmentation in fetal MRI using convolutional neural networks with simulated intensity inhomogeneities Abstract In: International Society for Magnetic Resonance in Medicine, 27th Annual Meeting & Exhibition, 2019. @booklet{Khalili2019, title = {Brain tissue segmentation in fetal MRI using convolutional neural networks with simulated intensity inhomogeneities }, author = {N. Khalili, N. Lessmann, E. Turk, M.A. Viergever, M.J.N.L. Benders, I. Išgum}, year = {2019}, date = {2019-05-10}, booktitle = {International Society for Magnetic Resonance in Medicine, 27th Annual Meeting & Exhibition}, abstract = {Automatic brain tissue segmentation in fetal MRI is a challenging task due to artifacts such as intensity inhomogeneity, caused in particular by spontaneous fetal movements during the scan. Unlike methods that estimate the bias field to remove intensity inhomogeneity as a preprocessing step in segmentation process, we aim at improving the robustness of the segmentation method by introducing an intensity inhomogeneity augmentation (IIA). The IIA simulates various patterns of intensity inhomogeneity during the training of the segmentation network. The segmentation results demonstrate an improvement in segmentation performance when the training data is augmented with IIA.}, howpublished = {International Society for Magnetic Resonance in Medicine, 27th Annual Meeting & Exhibition}, month = {05}, keywords = {}, pubstate = {published}, tppubtype = {booklet} } Automatic brain tissue segmentation in fetal MRI is a challenging task due to artifacts such as intensity inhomogeneity, caused in particular by spontaneous fetal movements during the scan. Unlike methods that estimate the bias field to remove intensity inhomogeneity as a preprocessing step in segmentation process, we aim at improving the robustness of the segmentation method by introducing an intensity inhomogeneity augmentation (IIA). The IIA simulates various patterns of intensity inhomogeneity during the training of the segmentation network. The segmentation results demonstrate an improvement in segmentation performance when the training data is augmented with IIA. |
| 5. | A. Schreuder; C. Jacobs; N. Lessmann; E.T. Scholten; I. Išgum; M. Prokop; C.M. Schaefer-Prokop; B. van Ginneken Improved lung cancer and mortality prediction accuracy using survival models based on semi-automatic CT image measurements Abstract In: 2018. @booklet{Schreuder2018, title = {Improved lung cancer and mortality prediction accuracy using survival models based on semi-automatic CT image measurements}, author = {A. Schreuder and C. Jacobs and N. Lessmann and E.T. Scholten and I. Išgum and M. Prokop and C.M. Schaefer-Prokop and B. van Ginneken}, year = {2018}, date = {2018-06-16}, booktitle = {World Conference on Lung Cancer}, month = {06}, keywords = {}, pubstate = {published}, tppubtype = {booklet} } |
| 6. | R. van Hamersvelt, M. Zreik, N. Lessmann, J. Wolterink, M. Voskuil, M.A Viergever, T. Leiner, I. Isgum Improving Specificity of Coronary CT Angiography for the Detection of Functionally Significant Coronary Artery Disease: A Deep Learning Approach Abstract In: 2017. @booklet{vanHamersvelt2017, title = {Improving Specificity of Coronary CT Angiography for the Detection of Functionally Significant Coronary Artery Disease: A Deep Learning Approach}, author = {R. van Hamersvelt, M. Zreik, N. Lessmann, J. Wolterink, M. Voskuil, M.A Viergever, T. Leiner, I. Isgum}, year = {2017}, date = {2017-11-30}, booktitle = {Radiological Society of North America, 103rd Annual Meeting}, abstract = {PURPOSE Coronary computed tomography angiography (CCTA) is an increasingly important diagnostic tool for the detection of coronary artery disease (CAD). However, due to calcium blooming and beam hardening, specificity for diagnosing functionally significant CAD is limited. The purpose of this study was to evaluate to what extent the specificity of CCTA for detection of functionally significant CAD could be improved by combining simple stenosis grading with deep-learning based analysis of left ventricular myocardium (LVM). METHOD AND MATERIALS We retrospectively included 126 patients (77% male, 58.7±9.5 years) who underwent CCTA prior to invasive fractional flow reserve (FFR). Functionally significant CAD was defined as an invasively measured FFR value below 0.78. First, the presence and degree of coronary artery stenosis was analyzed using the CAD-RADS system. Patients without a significant stenosis reported on CCTA scans were scored as functionally non-significant. For the remaining patients, fully automatic deep learning analysis of the LVM was used to identify presence of functionally significant CAD. LVM was first segmented using a convolutional neural network and then characterized by a convolutional auto-encoder (CAE). Based on the encodings generated by the CAE a support vector machine classifier identified patients with functionally significant stenosis. Diagnostic performance of this combined analysis was evaluated and compared with patient identification based only on ≥50% stenosis degree as measured in CCTA. RESULTS FFR was significant in 64 (51%) of the patients. Sensitivity and specificity of stenosis degree reported on CCTA alone were 91% and 18%, respectively. Adding deep-learning based analysis of LVM to stenosis detection resulted in improved specificity with a slight decline in sensitivity. The combined evaluation resulted in a sensitivity of 83% and a specificity of 73%. CONCLUSION Our results show that, at the expense of only a mild sensitivity decrease, a combination of clinical stenosis evaluation and automatic LVM analysis in CCTA led to substantial increase of the specificity. CLINICAL RELEVANCE/APPLICATION Adding deep learning analysis of LVM to stenosis assessment holds the potential to substantially increase specificity of CCTA and to decrease number of patients unnecessarily referred to invasive FFR.}, month = {11}, keywords = {}, pubstate = {published}, tppubtype = {booklet} } PURPOSE Coronary computed tomography angiography (CCTA) is an increasingly important diagnostic tool for the detection of coronary artery disease (CAD). However, due to calcium blooming and beam hardening, specificity for diagnosing functionally significant CAD is limited. The purpose of this study was to evaluate to what extent the specificity of CCTA for detection of functionally significant CAD could be improved by combining simple stenosis grading with deep-learning based analysis of left ventricular myocardium (LVM). METHOD AND MATERIALS We retrospectively included 126 patients (77% male, 58.7±9.5 years) who underwent CCTA prior to invasive fractional flow reserve (FFR). Functionally significant CAD was defined as an invasively measured FFR value below 0.78. First, the presence and degree of coronary artery stenosis was analyzed using the CAD-RADS system. Patients without a significant stenosis reported on CCTA scans were scored as functionally non-significant. For the remaining patients, fully automatic deep learning analysis of the LVM was used to identify presence of functionally significant CAD. LVM was first segmented using a convolutional neural network and then characterized by a convolutional auto-encoder (CAE). Based on the encodings generated by the CAE a support vector machine classifier identified patients with functionally significant stenosis. Diagnostic performance of this combined analysis was evaluated and compared with patient identification based only on ≥50% stenosis degree as measured in CCTA. RESULTS FFR was significant in 64 (51%) of the patients. Sensitivity and specificity of stenosis degree reported on CCTA alone were 91% and 18%, respectively. Adding deep-learning based analysis of LVM to stenosis detection resulted in improved specificity with a slight decline in sensitivity. The combined evaluation resulted in a sensitivity of 83% and a specificity of 73%. CONCLUSION Our results show that, at the expense of only a mild sensitivity decrease, a combination of clinical stenosis evaluation and automatic LVM analysis in CCTA led to substantial increase of the specificity. CLINICAL RELEVANCE/APPLICATION Adding deep learning analysis of LVM to stenosis assessment holds the potential to substantially increase specificity of CCTA and to decrease number of patients unnecessarily referred to invasive FFR. |
| 7. | N. Lessmann, B. van Ginneken, P.A. de Jong, W.B. Veldhuis, M.A. Viergever, I. Isgum Deep learning analysis for automatic calcium scoring in routine chest CT Abstract In: 2017. @booklet{less2017, title = {Deep learning analysis for automatic calcium scoring in routine chest CT}, author = {N. Lessmann, B. van Ginneken, P.A. de Jong, W.B. Veldhuis, M.A. Viergever, I. Isgum}, year = {2017}, date = {2017-11-28}, booktitle = {Radiological Society of North America, 103rd Annual Meeting}, abstract = {INTRODUCTION Coronary artery calcium (CAC) is a robust predictor of cardiovascular events (CVE) in asymptomatic individuals. Several guidelines recommend reporting of CAC scores in ungated chest CT exams. In addition, chest CT can be used to quantify thoracic aorta calcification (TAC) and cardiac valve calcification (CVC), which may further improve prediction of CVE. This study evaluates the performance of an automatic method for scoring of CAC, TAC and CVC on routine chest CT exams. METHOD AND MATERIALS The study includes 290 retrospectively collected chest CTs (16/64/256 slice scanners, 0.9/1.0mm slice thickness, 0.7mm increment, 100/120kvP, 60mAs, ungated non-contrast). For calcium scoring, the scans were resampled to 3mm thick slices with 1.5mm increment. Calcifications were manually identified and labeled to define a reference standard. A deep-learning-based method employing two convolutional neural networks was used to identify and label calcifications automatically. This automatic method was trained on 1012 low-dose chest CTs from the National Lung Screening Trial. Calcifications were quantified using volume and Agatston scores. Correlation of automatic and reference scores was assessed using two-way-mixed ICC. Additionally, patients were assigned to a cardiovascular risk category based on their total CAC Agatston score (0, 1-100, 101-1000, >1000). Risk category assignment was evaluated using proportion of agreement and linearly weighted к. RESULTS 16 scans (5.5%) were excluded due to insufficient image quality for manual scoring. 38.7% of the remaining patients had no CAC, 18.6% had a score 1-100, 16.4% a score 101-1000, and 26.3% a score > 1000. There was excellent correlation between automatic and manual volume scores for CAC (ICC=0.925, 95% CI: 0.904-0.941), TAC (ICC=0.991, 95% CI: 0.987-0.994), aortic valve calcifications (ICC=0.791, 95% CI: 0.734-0.836) and mitral valve calcifications (ICC=0.935, 95% CI: 0.918-0.949). Automatic and manual risk categorization agreed in 81.8% and differed by one category in 15.0% of the patients with excellent reliability (к=0.82). CONCLUSIONS Fully automatic scoring of coronary, aortic and cardiac valve calcifications highly correlates with manual scoring, even in ungated routine chest CT.}, month = {11}, keywords = {}, pubstate = {published}, tppubtype = {booklet} } INTRODUCTION Coronary artery calcium (CAC) is a robust predictor of cardiovascular events (CVE) in asymptomatic individuals. Several guidelines recommend reporting of CAC scores in ungated chest CT exams. In addition, chest CT can be used to quantify thoracic aorta calcification (TAC) and cardiac valve calcification (CVC), which may further improve prediction of CVE. This study evaluates the performance of an automatic method for scoring of CAC, TAC and CVC on routine chest CT exams. METHOD AND MATERIALS The study includes 290 retrospectively collected chest CTs (16/64/256 slice scanners, 0.9/1.0mm slice thickness, 0.7mm increment, 100/120kvP, 60mAs, ungated non-contrast). For calcium scoring, the scans were resampled to 3mm thick slices with 1.5mm increment. Calcifications were manually identified and labeled to define a reference standard. A deep-learning-based method employing two convolutional neural networks was used to identify and label calcifications automatically. This automatic method was trained on 1012 low-dose chest CTs from the National Lung Screening Trial. Calcifications were quantified using volume and Agatston scores. Correlation of automatic and reference scores was assessed using two-way-mixed ICC. Additionally, patients were assigned to a cardiovascular risk category based on their total CAC Agatston score (0, 1-100, 101-1000, >1000). Risk category assignment was evaluated using proportion of agreement and linearly weighted к. RESULTS 16 scans (5.5%) were excluded due to insufficient image quality for manual scoring. 38.7% of the remaining patients had no CAC, 18.6% had a score 1-100, 16.4% a score 101-1000, and 26.3% a score > 1000. There was excellent correlation between automatic and manual volume scores for CAC (ICC=0.925, 95% CI: 0.904-0.941), TAC (ICC=0.991, 95% CI: 0.987-0.994), aortic valve calcifications (ICC=0.791, 95% CI: 0.734-0.836) and mitral valve calcifications (ICC=0.935, 95% CI: 0.918-0.949). Automatic and manual risk categorization agreed in 81.8% and differed by one category in 15.0% of the patients with excellent reliability (к=0.82). CONCLUSIONS Fully automatic scoring of coronary, aortic and cardiac valve calcifications highly correlates with manual scoring, even in ungated routine chest CT. |
| 8. | B.D. de Vos, N. Lessmann, P.A. de Jong, M.A. Viergever, I. Isgum Direct coronary artery calcium scoring in low-dose chest CT using deep learning analysis Abstract In: 2017. @booklet{deVos2017b, title = {Direct coronary artery calcium scoring in low-dose chest CT using deep learning analysis}, author = {B.D. de Vos, N. Lessmann, P.A. de Jong, M.A. Viergever, I. Isgum}, year = {2017}, date = {2017-11-28}, booktitle = {Radiological Society of North America, 103rd Annual Meeting}, abstract = {PURPOSE Coronary artery calcium (CAC) score determined in screening with low-dose chest CT is a strong and independent predictor of cardiovascular events (CVE). However, manual CAC scoring in these images is cumbersome. Existing automatic methods detect CAC lesions and thereafter quantify them. However, precise localization of lesions may not be needed to facilitate identification of subjects at risk of CVE. Hence, we have developed a deep learning system for fully automatic, real-time and direct calcium scoring circumventing the need for intermediate detection of CAC lesions. METHOD AND MATERIALS The study included a set of 1,546 baseline CT scans from the National Lung Screening Trial. Three experts defined the reference standard by manually identifying CAC lesions that were subsequently quantified using the Agatston score. The designed convolutional neural network analyzed axial slices and predicted the corresponding Agatston score. Per-subject Agatston scores were determined as the sum of per-slice scores. Each subject was assigned to one of five cardiovascular risk categories (Agatston score: 0, 1-10, 10-100, 100-400, >400). The system was trained with 75% of the scans and tested with the remaining 25%. Correlation between manual and automatic CAC scores was determined using the intra class correlation coefficient (ICC). Agreement of CVD risk categorization was evaluated using accuracy and Cohen’s linearly weighted κ. RESULTS In the 386 test subjects, the median (Q1-Q3) reference Agatston score was 54 (1-321). By the reference, 95, 37, 86, 94 and 75 subjects were assigned to 0, 1-10, 10-100, 100-400, >400 risk categories, respectively. The ICC between the automatic and reference scores was 0.95. The method assigned 85% of subjects to the correct risk category with a κ of 0.90. The score was determined in <2 seconds per CT. CONCLUSION Unlike previous automatic CAC scoring methods, the proposed method allows for quantification of coronary calcium burden without the need for intermediate identification or segmentation of separate CAC lesions. The system is robust and performs analysis in real-time. CLINICAL RELEVANCE/APPLICATION The proposed method may allow real-time identification of subjects at risk of a CVE undergoing CT-based lung cancer screening without the need for intermediate segmentation of coronary calcifications.}, month = {11}, keywords = {}, pubstate = {published}, tppubtype = {booklet} } PURPOSE Coronary artery calcium (CAC) score determined in screening with low-dose chest CT is a strong and independent predictor of cardiovascular events (CVE). However, manual CAC scoring in these images is cumbersome. Existing automatic methods detect CAC lesions and thereafter quantify them. However, precise localization of lesions may not be needed to facilitate identification of subjects at risk of CVE. Hence, we have developed a deep learning system for fully automatic, real-time and direct calcium scoring circumventing the need for intermediate detection of CAC lesions. METHOD AND MATERIALS The study included a set of 1,546 baseline CT scans from the National Lung Screening Trial. Three experts defined the reference standard by manually identifying CAC lesions that were subsequently quantified using the Agatston score. The designed convolutional neural network analyzed axial slices and predicted the corresponding Agatston score. Per-subject Agatston scores were determined as the sum of per-slice scores. Each subject was assigned to one of five cardiovascular risk categories (Agatston score: 0, 1-10, 10-100, 100-400, >400). The system was trained with 75% of the scans and tested with the remaining 25%. Correlation between manual and automatic CAC scores was determined using the intra class correlation coefficient (ICC). Agreement of CVD risk categorization was evaluated using accuracy and Cohen’s linearly weighted κ. RESULTS In the 386 test subjects, the median (Q1-Q3) reference Agatston score was 54 (1-321). By the reference, 95, 37, 86, 94 and 75 subjects were assigned to 0, 1-10, 10-100, 100-400, >400 risk categories, respectively. The ICC between the automatic and reference scores was 0.95. The method assigned 85% of subjects to the correct risk category with a κ of 0.90. The score was determined in <2 seconds per CT. CONCLUSION Unlike previous automatic CAC scoring methods, the proposed method allows for quantification of coronary calcium burden without the need for intermediate identification or segmentation of separate CAC lesions. The system is robust and performs analysis in real-time. CLINICAL RELEVANCE/APPLICATION The proposed method may allow real-time identification of subjects at risk of a CVE undergoing CT-based lung cancer screening without the need for intermediate segmentation of coronary calcifications. |
| 9. | M. Zreik, N. Lessmann, R. van Hamersvelt, J. Wolterink, M. Voskuil, M.A Viergever, T. Leiner, I. Isgum Deep learning analysis of the left ventricular myocardium in cardiac CT images enables detection of functionally significant coronary artery stenosis regardless of coronary anatomy Abstract In: 2017. @booklet{Zreik2017, title = {Deep learning analysis of the left ventricular myocardium in cardiac CT images enables detection of functionally significant coronary artery stenosis regardless of coronary anatomy}, author = {M. Zreik, N. Lessmann, R. van Hamersvelt, J. Wolterink, M. Voskuil, M.A Viergever, T. Leiner, I. Isgum}, year = {2017}, date = {2017-08-23}, booktitle = {Radiological Society of North America, 103rd Annual Meeting}, abstract = {PURPOSE Fractional flow reserve (FFR), performed during invasive coronary angiography (ICA), is the current reference standard to determine the functional significance of a coronary stenosis. Coronary Computed Tomography Angiography (CCTA) derived virtual FFR is a promising but time and computationally expensive non-invasive alternative that can reduce the number of unnecessary ICA procedures by modeling coronary artery flow dynamics. We propose a method for fully automatic identification of patients with significant coronary artery stenosis based on deep learning analysis of only the left ventricle (LV) myocardium in CCTA. METHOD AND MATERIALS The study included resting CCTA scans (Philips Brilliance iCT, 120kVp, 210-300mAs) of 166 consecutive patients (59.2 ± 9.5 years, 128 males) who underwent invasive FFR (0.79 ± 0.10). FFR provided the reference for presence of a functionally significant stenosis (cut-off 0.78) . Automatic analysis first segmented the LV myocardium using a multiscale convolutional neural network (CNN). Next, the segmented myocardium was represented with a number of encodings generated by a convolutional auto-encoder (CAE). To detect local ischemic changes, the LV myocardium was divided into a number of spatially connected clusters. Per-cluster statistics of the encodings were subsequently used by a support vector machine classifier to identify patients with functionally significant stenosis. CCTA scans of 20 patients were used to train the CNN, and an additional 20 scans were used to train the CAE. Accuracy of patient classification was evaluated using the remaining 126 CCTA scans in 50 ten-fold cross-validation experiments. In each experiment, patients were randomly assigned to training and test sets. RESULTS Classification of patients resulted in an area under the receiver operating characteristic curve of 0.74 ± 0.02. At sensitivity levels 0.60, 0.70 and 0.80, the corresponding specificity was 0.77, 0.71 and 0.59, respectively. CONCLUSION The results demonstrate that fully automatic analysis of only the LV myocardium in resting CCTA scans, without assessment of the anatomy of the coronary arteries, can be used to identify patients with functionally significant coronary artery stenosis. CLINICAL RELEVANCE/APPLICATION Deep learning analysis of the LV myocardium could increase the specificity of the clinically used visual stenosis assessment in CCTA and reduce the number of patients undergoing unnecessary ICA.}, month = {08}, keywords = {}, pubstate = {published}, tppubtype = {booklet} } PURPOSE Fractional flow reserve (FFR), performed during invasive coronary angiography (ICA), is the current reference standard to determine the functional significance of a coronary stenosis. Coronary Computed Tomography Angiography (CCTA) derived virtual FFR is a promising but time and computationally expensive non-invasive alternative that can reduce the number of unnecessary ICA procedures by modeling coronary artery flow dynamics. We propose a method for fully automatic identification of patients with significant coronary artery stenosis based on deep learning analysis of only the left ventricle (LV) myocardium in CCTA. METHOD AND MATERIALS The study included resting CCTA scans (Philips Brilliance iCT, 120kVp, 210-300mAs) of 166 consecutive patients (59.2 ± 9.5 years, 128 males) who underwent invasive FFR (0.79 ± 0.10). FFR provided the reference for presence of a functionally significant stenosis (cut-off 0.78) . Automatic analysis first segmented the LV myocardium using a multiscale convolutional neural network (CNN). Next, the segmented myocardium was represented with a number of encodings generated by a convolutional auto-encoder (CAE). To detect local ischemic changes, the LV myocardium was divided into a number of spatially connected clusters. Per-cluster statistics of the encodings were subsequently used by a support vector machine classifier to identify patients with functionally significant stenosis. CCTA scans of 20 patients were used to train the CNN, and an additional 20 scans were used to train the CAE. Accuracy of patient classification was evaluated using the remaining 126 CCTA scans in 50 ten-fold cross-validation experiments. In each experiment, patients were randomly assigned to training and test sets. RESULTS Classification of patients resulted in an area under the receiver operating characteristic curve of 0.74 ± 0.02. At sensitivity levels 0.60, 0.70 and 0.80, the corresponding specificity was 0.77, 0.71 and 0.59, respectively. CONCLUSION The results demonstrate that fully automatic analysis of only the LV myocardium in resting CCTA scans, without assessment of the anatomy of the coronary arteries, can be used to identify patients with functionally significant coronary artery stenosis. CLINICAL RELEVANCE/APPLICATION Deep learning analysis of the LV myocardium could increase the specificity of the clinically used visual stenosis assessment in CCTA and reduce the number of patients undergoing unnecessary ICA. |
| 10. | F. Mohamed Hoesein, E. Pompe, D.A. Lynch, N. Lessmann, J.W.J. Lammers, I. Isgum, P.A. de Jong Computed tomographic findings are associated with respiratory mortality in the National Lung Screening Trial Abstract In: 2016. @booklet{moha16, title = {Computed tomographic findings are associated with respiratory mortality in the National Lung Screening Trial}, author = {F. Mohamed Hoesein, E. Pompe, D.A. Lynch, N. Lessmann, J.W.J. Lammers, I. Isgum, P.A. de Jong}, year = {2016}, date = {2016-11-27}, booktitle = {Radiological Society of North America, 102nd Annual Meeting}, abstract = {PURPOSE Almost 10% of all deaths in the computed tomography (CT) arm of the National Lung Cancer Screening Trial (NLST) were due to respiratory illnesses other than lung cancer. We evaluated the importance of lung abnormalities on screening CT for survival in NLST participants. METHOD AND MATERIALS Subjects were derived from the CT-arm of the NLST that died of a respiratory illness other than lung cancer, as defined on the death certificate, matched with an equal number of control subjects, based on age, sex, pack-years, and smoking status. A chest radiologist and senior radiology resident independently and blindly scored baseline CTs for the presence of emphysema, airway wall thickening, or fibrotic lung disease. Associations between CT abnormalities and death was evaluated with a logistic regression model. RESULTS 172 died from a respiratory cause other than lung cancer. Radiologic diseases were significantly associated with higher mortality; severe emphysema OR (95%CI) 9.7 (4.6–20.4), airway wall disease OR (95%CI) 2.3 (1.3–3.9) or fibrotic lung disease OR (95%CI) 39.1 (5.1–289.6). 81 subjects were evaluated by the EVP and confirmed the diagnosis in 55 subjects. In this group, the presence of severe emphysema was significantly associated with mortality (OR=17.2, p<0.001), as well as airway remodeling (OR=3.2}, month = {11}, keywords = {}, pubstate = {published}, tppubtype = {booklet} } PURPOSE Almost 10% of all deaths in the computed tomography (CT) arm of the National Lung Cancer Screening Trial (NLST) were due to respiratory illnesses other than lung cancer. We evaluated the importance of lung abnormalities on screening CT for survival in NLST participants. METHOD AND MATERIALS Subjects were derived from the CT-arm of the NLST that died of a respiratory illness other than lung cancer, as defined on the death certificate, matched with an equal number of control subjects, based on age, sex, pack-years, and smoking status. A chest radiologist and senior radiology resident independently and blindly scored baseline CTs for the presence of emphysema, airway wall thickening, or fibrotic lung disease. Associations between CT abnormalities and death was evaluated with a logistic regression model. RESULTS 172 died from a respiratory cause other than lung cancer. Radiologic diseases were significantly associated with higher mortality; severe emphysema OR (95%CI) 9.7 (4.6–20.4), airway wall disease OR (95%CI) 2.3 (1.3–3.9) or fibrotic lung disease OR (95%CI) 39.1 (5.1–289.6). 81 subjects were evaluated by the EVP and confirmed the diagnosis in 55 subjects. In this group, the presence of severe emphysema was significantly associated with mortality (OR=17.2, p<0.001), as well as airway remodeling (OR=3.2 |
| 11. | N. Lessmann, I. Isgum, S. Lam, J. Mayo, P.A. de Jong, M.A. Viergever, B. van Ginneken Automatic coronary calcium scoring and cardiovascular risk estimation in the Pan-Canadian lung cancer screening trial Abstract In: 2015. @booklet{less15, title = {Automatic coronary calcium scoring and cardiovascular risk estimation in the Pan-Canadian lung cancer screening trial}, author = {N. Lessmann, I. Isgum, S. Lam, J. Mayo, P.A. de Jong, M.A. Viergever, B. van Ginneken}, year = {2015}, date = {2015-11-29}, booktitle = {Radiological Society of North America, 101th Annual Meeting}, abstract = {PURPOSE Coronary artery calcium (CAC) scores determined in low-dose ungated chest CT as acquired for lung cancer screening are a strong and independent predictor of cardiovascular events (CVE). Automatic CAC scoring can complement lung cancer screening by identifying subjects at risk of a CVE. We investigated agreement and reliability of an automatic CAC scoring method previously developed for CAC scoring in the Dutch-Belgian lung cancer screening trial (NELSON) in the Pan-Canadian Early Detection of Lung Cancer Study (PanCan). METHOD AND MATERIALS Our study included 149 low-dose chest CT scans from the PanCan (16x or 64x 1.0 or 1.25 mm, 120 kvP, 40-50 mAs, no IV contrast, no ECG synchronization). Prior to scoring, the scans were reconstructed to 3.1 mm slice thickness at 1.4 mm increment. In each scan, the reference standard was set by manual annotation of CAC by one observer. Only voxels with intensities above 130 HU and lesions with a minimum volume of 1.5 mm³ were considered. Subsequently, automatic CAC scoring was performed using a supervised pattern recognition method previously developed for CAC scoring in the NELSON trial. The algorithm was trained with 100 NELSON scans. Volume and Agatston scores were computed for manual and automatic scores. Subjects were assigned to a cardiovascular risk category based on the Agatston score (0-10, 11-100, 101-400, >400). Agreement was determined as proportion of agreement in risk category assignment. Reliability was determined using linearly weighted к for risk category assignment and two-way-mixed intraclass correlation coefficient (ICC) for volume scores. RESULTS Three (2.0%) scans were excluded due to metal artifacts. In the remaining scans, the reference median CAC volume was 52.3 mm3 (P25-P75: 0-287.3 mm3). 83.6% of these scans were automatically assigned to the correct risk category. Reliability of the automatic scoring was very good for both risk category assignment (к=0.83) and volume scores (ICC=0.80). CONCLUSION Automatic coronary calcium scoring in lung cancer screening CT scans is feasible. To achieve good agreement with manual scores representative training data was not necessary.}, month = {11}, keywords = {}, pubstate = {published}, tppubtype = {booklet} } PURPOSE Coronary artery calcium (CAC) scores determined in low-dose ungated chest CT as acquired for lung cancer screening are a strong and independent predictor of cardiovascular events (CVE). Automatic CAC scoring can complement lung cancer screening by identifying subjects at risk of a CVE. We investigated agreement and reliability of an automatic CAC scoring method previously developed for CAC scoring in the Dutch-Belgian lung cancer screening trial (NELSON) in the Pan-Canadian Early Detection of Lung Cancer Study (PanCan). METHOD AND MATERIALS Our study included 149 low-dose chest CT scans from the PanCan (16x or 64x 1.0 or 1.25 mm, 120 kvP, 40-50 mAs, no IV contrast, no ECG synchronization). Prior to scoring, the scans were reconstructed to 3.1 mm slice thickness at 1.4 mm increment. In each scan, the reference standard was set by manual annotation of CAC by one observer. Only voxels with intensities above 130 HU and lesions with a minimum volume of 1.5 mm³ were considered. Subsequently, automatic CAC scoring was performed using a supervised pattern recognition method previously developed for CAC scoring in the NELSON trial. The algorithm was trained with 100 NELSON scans. Volume and Agatston scores were computed for manual and automatic scores. Subjects were assigned to a cardiovascular risk category based on the Agatston score (0-10, 11-100, 101-400, >400). Agreement was determined as proportion of agreement in risk category assignment. Reliability was determined using linearly weighted к for risk category assignment and two-way-mixed intraclass correlation coefficient (ICC) for volume scores. RESULTS Three (2.0%) scans were excluded due to metal artifacts. In the remaining scans, the reference median CAC volume was 52.3 mm3 (P25-P75: 0-287.3 mm3). 83.6% of these scans were automatically assigned to the correct risk category. Reliability of the automatic scoring was very good for both risk category assignment (к=0.83) and volume scores (ICC=0.80). CONCLUSION Automatic coronary calcium scoring in lung cancer screening CT scans is feasible. To achieve good agreement with manual scores representative training data was not necessary. |
PhD Theses |
|
| 1. | N. Lessmann Machine learning based quantification of extrapulmonary diseases in chest CT PhD Thesis Utrecht University, The Netherlands, 2019, ISBN: 978-94-6323-607-2. @phdthesis{Lessmann2019c, title = {Machine learning based quantification of extrapulmonary diseases in chest CT}, author = {N. Lessmann}, isbn = {978-94-6323-607-2}, year = {2019}, date = {2019-06-25}, school = {Utrecht University, The Netherlands}, keywords = {}, pubstate = {published}, tppubtype = {phdthesis} } |