@article{Zreik2020b,
title = {Deep learning analysis of coronary arteries in cardiac CT angiography for detection of patients requiring invasive coronary angiography},
author = {M. Zreik, R.W. van Hamersvelt, N. Khalili, J.M. Wolterink, M. Voskuil, M.A. Viergever, T. Leiner, I. Išgum},
url = {https://www.ncbi.nlm.nih.gov/pubmed/31725371},
doi = {10.1109/TMI.2019.2953054},
year = {2020},
date = {2020-05-01},
journal = {Transactions on Medical Imaging},
volume = {39},
number = {5},
pages = {1545-1557},
abstract = {In patients with obstructive coronary artery disease, the functional significance of a coronary artery stenosis needs to be determined to guide treatment. This is typically established through fractional flow reserve (FFR) measurement, performed during invasive coronary angiography (ICA). We present a method for automatic and non-invasive detection of patients requiring ICA, employing deep unsupervised analysis of complete coronary arteries in cardiac CT angiography (CCTA) images. We retrospectively collected CCTA scans of 187 patients, 137 of them underwent invasive FFR measurement in 192 different coronary arteries. These FFR measurements served as a reference standard for the functional significance of the coronary stenosis. The centerlines of the coronary arteries were extracted and used to reconstruct straightened multi-planar reformatted (MPR) volumes. To automatically identify arteries with functionally significant stenosis that require ICA, each MPR volume was encoded into a fixed number of encodings using two disjoint 3D and 1D convolutional autoencoders performing spatial and sequential encodings, respectively. Thereafter, these encodings were employed to classify arteries using a support vector machine classifier. The detection of coronary arteries requiring invasive evaluation, evaluated using repeated cross-validation experiments, resulted in an area under the receiver operating characteristic curve of 0.81±0.02 on the artery-level, and 0.87±0.02 on the patient-level. The results demonstrate the feasibility of automatic non-invasive detection of patients that require ICA and possibly subsequent coronary artery intervention. This could potentially reduce the number of patients that unnecessarily undergo ICA.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{Wolterink2018b,
title = {Coronary artery centerline extraction in cardiac CT angiography using a CNN-based orientation classifier},
author = {J.M. Wolterink, R.W. van Hamersvelt, M.A. Viergever, T. Leiner, I. Išgum},
url = {https://arxiv.org/abs/1810.03143},
year = {2019},
date = {2019-01-01},
journal = {Medical Image Analysis},
volume = {51},
pages = {46-60},
abstract = {Coronary artery centerline extraction in cardiac CT angiography (CCTA) images is a prerequisite for evaluation of stenoses and atherosclerotic plaque. We propose an algorithm that extracts coronary artery centerlines in CCTA using a convolutional neural network (CNN).
A 3D dilated CNN is trained to predict the most likely direction and radius of an artery at any given point in a CCTA image based on a local image patch. Starting from a single seed point placed manually or automatically anywhere in a coronary artery, a tracker follows the vessel centerline in two directions using the predictions of the CNN. Tracking is terminated when no direction can be identified with high certainty.
The CNN was trained using 32 manually annotated centerlines in a training set consisting of 8 CCTA images provided in the MICCAI 2008 Coronary Artery Tracking Challenge (CAT08). Evaluation using 24 test images of the CAT08 challenge showed that extracted centerlines had an average overlap of 93.7% with 96 manually annotated reference centerlines. Extracted centerline points were highly accurate, with an average distance of 0.21 mm to reference centerline points. In a second test set consisting of 50 CCTA scans, 5,448 markers in the coronary arteries were used as seed points to extract single centerlines. This showed strong correspondence between extracted centerlines and manually placed markers. In a third test set containing 36 CCTA scans, fully automatic seeding and centerline extraction led to extraction of on average 92% of clinically relevant coronary artery segments.
The proposed method is able to accurately and efficiently determine the direction and radius of coronary arteries. The method can be trained with limited training data, and once trained allows fast automatic or interactive extraction of coronary artery trees from CCTA images.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{Zreik2018,
title = {A recurrent CNN for automatic detection and classification of coronary artery plaque and stenosis in coronary CT angiography},
author = {M. Zreik, R.W. van Hamersvelt, J.M. Wolterink, T. Leiner, M.A. Viergever, I. Išgum},
url = {https://ieeexplore.ieee.org/abstract/document/8550784
https://arxiv.org/abs/1804.04360},
year = {2018},
date = {2018-11-28},
journal = {IEEE Transactions on Medical Imaging},
volume = {38},
number = {7},
abstract = {Various types of atherosclerotic plaque and varying grades of stenosis could lead to different management of patients with coronary artery disease. Therefore, it is crucial to detect and classify the type of coronary artery plaque, as well as to detect and determine the degree of coronary artery stenosis. This study includes retrospectively collected clinically obtained coronary CT angiography (CCTA) scans of 163 patients. In these, the centerlines of the coronary arteries were extracted and used to reconstruct multi-planar reformatted (MPR) images for the coronary arteries. To define the reference standard, the presence and the type of plaque in the coronary arteries (no plaque, non-calcified, mixed, calcified), as well as the presence and the anatomical significance of coronary stenosis (no stenosis, nonsignificant i.e. < 50% luminal narrowing, significant i.e. ≥ 50% luminal narrowing) were manually annotated in the MPR images by identifying the start- and end-points of the segment of the artery affected by the plaque. To perform automatic analysis, a multi-task recurrent convolutional neural network is applied on coronary artery MPR images. First, a 3D convolutional neural network is utilized to extract features along the coronary artery. Subsequently, the extracted features are aggregated by a recurrent neural network that performs two simultaneous multiclass classification tasks. In the first task, the network detects and characterizes the type of the coronary artery plaque. In the second task, the network detects and determines the anatomical significance of the coronary artery stenosis. The network was trained and tested using CCTA images of 98 and 65 patients, respectively. For detection and characterization of coronary plaque, the method achieved an accuracy of 0.77. For detection of stenosis and determination of its anatomical significance, the method achieved an accuracy of 0.80. The results demonstrate that automatic detection and classification of coronary artery plaque and stenosis are feasible. This may enable automated triage of patients to those without coronary plaque and those with coronary plaque and stenosis in need for further cardiovascular workup.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{vanHamersvelt*2018er,
title = {Deep learning analysis of left ventricular myocardium in CT angiographic intermediate degree coronary stenosis improves the diagnostic accuracy for identification of functionally significant stenosis },
author = {R.W. van Hamersvelt*, M. Zreik*, M. Voskuil, M.A. Viergever, I. Išgum, T. Leiner},
url = {https://link.springer.com/article/10.1007%2Fs00330-018-5822-3},
year = {2018},
date = {2018-10-01},
journal = {European Radiology},
volume = {29},
number = {5},
pages = {2350–2359},
abstract = {Objectives: To evaluate the added value of deep learning (DL) analysis of the left ventricular myocardium (LVM) in resting coronary CT angiography (CCTA) over determination of coronary degree of stenosis (DS), for identification of patients with functionally significant coronary artery stenosis.
Methods: Patients who underwent CCTA prior to an invasive fractional flow reserve (FFR) measurement were retrospectively selected. Highest DS from CCTA was used to classify patients as having non-significant (≤ 24% DS), intermediate (25–69% DS), or significant stenosis (≥ 70% DS). Patients with intermediate stenosis were referred for fully automatic DL analysis of the LVM. The DL algorithm characterized the LVM, and likely encoded information regarding shape, texture, contrast enhancement, and more. Based on these encodings, features were extracted and patients classified as having a non-significant or significant stenosis. Diagnostic performance of the combined method was evaluated and compared to DS evaluation only. Functionally significant stenosis was defined as FFR ≤ 0.8 or presence of angiographic high-grade stenosis (≥ 90% DS).
Results: The final study population consisted of 126 patients (77% male, 59 ± 9 years). Eighty-one patients (64%) had a functionally significant stenosis. The proposed method resulted in improved discrimination (AUC = 0.76) compared to classification based on DS only (AUC = 0.68). Sensitivity and specificity were 92.6% and 31.1% for DS only (≥ 50% indicating functionally significant stenosis), and 84.6% and 48.4% for the proposed method.
Conclusion: The combination of DS with DL analysis of the LVM in intermediate-degree coronary stenosis may result in improved diagnostic performance for identification of patients with functionally significant coronary artery stenosis.},
note = {*equal contribution},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@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}
}

@article{Wolt17,
title = {Generative adversarial networks for noise reduction in low-dose CT},
author = {J.M. Wolterink, T. Leiner, M.A. Viergever, I. Isgum},
url = {http://ieeexplore.ieee.org/document/7934380/},
year = {2017},
date = {2017-05-23},
journal = {IEEE Transactions on Medical Imaging},
volume = {36},
number = {12},
pages = {2536 - 2545},
abstract = {Noise is inherent to low-dose CT acquisition. We propose to train a convolutional neural network (CNN) jointly with an adversarial CNN to estimate routine-dose CT images from low-dose CT images and hence reduce noise. A generator CNN was trained to transform low-dose CT images into routine-dose CT images using voxel-wise loss minimization. An adversarial discriminator CNN was simultaneously trained to distinguish the output of the generator from routine dose CT images. The performance of this discriminator was used as an adversarial loss for the generator. Experiments were performed using CT images of an anthropomorphic phantom containing calcium inserts, as well as patient non-contrast-enhanced cardiac CT images. The phantom and patients were scanned at 20% and 100% routine clinical dose. Three training strategies were compared: the first used only voxel-wise loss, the second combined voxel-wise loss and adversarial loss, and the third used only adversarial loss. The results showed that training with only voxel-wise loss resulted in the highest peak signal-to-noise ratio with respect to reference routine-dose images. However, the CNNs trained with adversarial loss captured image statistics of routine-dose images better. Noise reduction improved quantification of low-density calcified inserts in phantom CT images and allowed coronary calcium scoring in low-dose patient CT images with high noise levels. Testing took less than 10 seconds per CT volume. CNN-based low-dose CT noise reduction in the image domain is feasible. Training with an adversarial network improves the CNN's ability to generate images with an appearance similar to that of reference routine-dose CT images.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{Wolt16b,
title = {Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks},
author = {J.M. Wolterink, T. Leiner, B.D. de Vos, R.W. van Hamersvelt, M.A. Viergever, I. Isgum},
year = {2016},
date = {2016-05-11},
journal = {Medical Image Analysis},
volume = {34},
pages = {123-136},
abstract = {The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular events. CAC is clinically quantified in cardiac calcium scoring CT (CSCT), but it has been shown that cardiac CT angiography (CCTA) may also be used for this purpose. We present a method for automatic CAC quantification in CCTA. This method uses supervised learning to directly identify and quantify CAC without a need for coronary artery extraction commonly used in existing methods. The study included cardiac CT exams of 250 patients for whom both a CCTA and a CSCT scan were available. To restrict the volume-of-interest for analysis, a bounding box around the heart is automatically determined. The bounding box detection algorithm employs a combination of three ConvNets, where each detects the heart in a different orthogonal plane (axial, sagittal, coronal). These ConvNets were trained using 50 cardiac CT exams. In the remaining 200 exams, a reference standard for CAC was defined in CSCT and CCTA. Out of these, 100 CCTA scans were used for training, and the remaining 100 for evaluation of a voxel classification method for CAC identification. The method uses ConvPairs, pairs of convolutional neural networks (ConvNets). The first ConvNet in a pair identifies voxels likely to be CAC, thereby discarding the majority of non-CAC-like voxels such as lung and fatty tissue. The identified CAC-like voxels are further classified by the second ConvNet in the pair, which distinguishes between CAC and CAC-like negatives. Given the different task of each ConvNet, they share their architecture, but not their weights. Input patches are either 2.5D or 3D. The ConvNets are purely convolutional, i.e. no pooling layers are present and fully connected layers are implemented as convolutions, thereby allowing efficient voxel classification. The performance of individual 2.5D and 3D ConvPairs with input sizes of 15 and 25 voxels, as well as the performance of ensembles of these ConvPairs, were evaluated by a comparison with reference annotations in CCTA and CSCT. In all cases, ensembles of ConvPairs outperformed their individual members. The best performing individual ConvPair detected 72% of lesions in the test set, with on average 0.85 false positive (FP) errors per scan. The best performing ensemble combined all ConvPairs and obtained a sensitivity of 71% at 0.48 FP errors per scan. For this ensemble, agreement with the reference mass score in CSCT was excellent (ICC 0.944 [0.918–0.962]). Aditionally, based on the Agatston score in CCTA, this ensemble assigned 83% of patients to the same cardiovascular risk category as reference CSCT. In conclusion, CAC can be accurately automatically identified and quantified in CCTA using the proposed pattern recognition method. This might obviate the need to acquire a dedicated CSCT scan for CAC scoring, which is regularly acquired prior to a CCTA, and thus reduce the CT radiation dose received by patients.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}