Jelmer M. Wolterink

Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks

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.

Deep MR to CT Synthesis Using Unpaired Data

MR-only radiotherapy treatment planning requires accurate MR-to-CT synthesis. Current deep learning methods for MR-to-CT synthesis depend on pairwise aligned MR and CT training images of the same patient. However, misalignment between paired images could lead to errors in synthesized CT images. To overcome this, we propose to train a generative adversarial network (GAN) with unpaired MR and CT images. A GAN consisting of two synthesis convolutional neural networks (CNNs) and two discriminator CNNs was trained with cycle consistency to transform 2D brain MR image slices into 2D brain CT image slices and vice versa. Brain MR and CT images of 24 patients were analyzed. A quantitative evaluation showed that the model was able to synthesize CT images that closely approximate reference CT images, and was able to outperform a GAN model trained with paired MR and CT images.

Deep learning for multi-task medical image segmentation in multiple modalities

Automatic segmentation of medical images is an important task for many clinical applications. In practice, a wide range of anatomical structures are visualised using different imaging modalities. In this paper, we investigate whether a single convolutional neural network (CNN) can be trained to perform different segmentation tasks.

Automatic Coronary Calcium Scoring in Cardiac CT Angiography Using Convolutional Neural Networks

The amount of coronary artery calcification CAC is a strong and independent predictor of cardiovascular events. Non-contrast enhanced cardiac CT is considered a reference for quantification of CAC. Recently, it has been shown that CAC may be quantified in cardiac CT angiography CCTA. We present a pattern recognition method that automatically identifies and quantifies CAC in CCTA. The study included CCTA scans of 50 patients equally distributed over five cardiovascular risk categories. CAC in CCTA was identified in two stages. In the first stage, potential CAC voxels were identified using a convolutional neural network CNN. In the second stage, candidate CAC lesions were extracted based on the CNN output for analyzed voxels and thereafter described with a set of features and classified using a Random Forest. Ten-fold stratified cross-validation experiments were performed. CAC volume was quantified per patient and compared with manual reference annotations in the CCTA scan. Bland-Altman bias and limits of agreement between reference and automatic annotations were -15 -198---168 after the first stage and -3 -86 --- 79 after the second stage. The results show that CAC can be automatically identified and quantified in CCTA using the proposed method. This might obviate the need for a dedicated non-contrast-enhanced CT scan for CAC scoring, which is regularly acquired prior to a CCTA scan, and thus reduce the CT radiation dose received by patients.

Automatic Coronary Calcium Scoring in Non-Contrast-Enhanced ECG-Triggered Cardiac CT With Ambiguity Detection

The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular events. We present a system that automatically quantifies total patient and per coronary artery CAC in non-contrast-enhanced, ECG-triggered cardiac CT. The system identifies candidate calcifications that cannot be automatically labeled with high certainty and optionally presents these to an expert for review. Candidates were extracted by intensity-based thresholding and described by location features derived from estimated coronary artery positions, as well as size, shape and intensity features. Next, a two-class classifier distinguished between coronary calcifications and negatives or a multiclass classifier labeled CAC per coronary artery. Candidates that could not be labeled with high certainty were identified by entropy-based ambiguity detection and presented to an expert for review and possible relabeling. The system was evaluated with 530 test images. Using the two-class classifier, the intra-class correlation coefficient (ICC) between reference and automatically determined total patient CAC volume was 0.95. Using the multiclass classifier, the ICC between reference and automatically determined per artery CAC volume was 0.98 (LAD), 0.69 (LCX), and 0.95 (RCA). In 49% of CTs, no ambiguous candidates were identified, while review of the remaining CTs increased the ICC for total patient CAC volume to 1.00, and per artery CAC volume to 1.00 (LAD), 0.95 (LCX), and 0.99 (RCA). In conclusion, CAC can be automatically identified in non-contrast-enhanced ECG-triggered cardiac CT. Ambiguity detection with expert review may enable the application of automatic CAC scoring in the clinic with a performance comparable to that of a human expert.

Dilated Convolutional Neural Networks for Cardiovascular MR Segmentation in Congenital Heart Disease

We propose an automatic method using dilated convolutional neural networks (CNNs) for segmentation of the myocardium and blood pool in cardiovascular MR (CMR) of patients with congenital heart disease (CHD).

ConvNet-Based Localization of Anatomical Structures in 3-D Medical Images

Localization of anatomical structures is a prerequisite for many tasks in a medical image analysis. We propose a method for automatic localization of one or more anatomical structures in 3-D medical images through detection of their presence in 2-D image slices using a convolutional neural network (ConvNet). A single ConvNet is trained to detect the presence of the anatomical structure of interest in axial, coronal, and sagittal slices extracted from a 3-D image. To allow the ConvNet to analyze slices of different sizes, spatial pyramid pooling is applied. After detection, 3-D bounding boxes are created by combining the output of the ConvNet in all slices. In the experiments, 200 chest CT, 100 cardiac CT angiography (CTA), and 100 abdomen CT scans were used. The heart, ascending aorta, aortic arch, and descending aorta were localized in chest CT scans, the left cardiac ventricle in cardiac CTA scans, and the liver in abdomen CT scans. Localization was evaluated using the distances between automatically and manually defined reference bounding box centroids and walls. The best results were achieved in the localization of structures with clearly defined boundaries (e.g., aortic arch) and the worst when the structure boundary was not clearly visible (e.g., liver). The method was more robust and accurate in localization multiple structures.

An evaluation of automatic coronary artery calcium scoring methods with cardiac CT using the orCaScore framework

PURPOSE The amount of coronary artery calcification (CAC) is a strong and independent predictor of cardiovascular disease (CVD) events. In clinical practice, CAC is manually identified and automatically quantified in cardiac CT using commercially available software. This is a tedious and time-consuming process in large-scale studies. Therefore, a number of automatic methods that require no interaction and semiautomatic methods that require very limited interaction for the identification of CAC in cardiac CT have been proposed. Thus far, a comparison of their performance has been lacking. The objective of this study was to perform an independent evaluation of (semi)automatic methods for CAC scoring in cardiac CT using a publicly available standardized framework. METHODS Cardiac CT exams of 72 patients distributed over four CVD risk categories were provided for (semi)automatic CAC scoring. Each exam consisted of a noncontrast-enhanced calcium scoring CT (CSCT) and a corresponding coronary CT angiography (CCTA) scan. The exams were acquired in four different hospitals using state-of-the-art equipment from four major CT scanner vendors. The data were divided into 32 training exams and 40 test exams. A reference standard for CAC in CSCT was defined by consensus of two experts following a clinical protocol. The framework organizers evaluated the performance of (semi)automatic methods on test CSCT scans, per lesion, artery, and patient. RESULTS Five (semi)automatic methods were evaluated. Four methods used both CSCT and CCTA to identify CAC, and one method used only CSCT. The evaluated methods correctly detected between 52% and 94% of CAC lesions with positive predictive values between 65% and 96%. Lesions in distal coronary arteries were most commonly missed and aortic calcifications close to the coronary ostia were the most common false positive errors. The majority (between 88% and 98%) of correctly identified CAC lesions were assigned to the correct artery. Linearly weighted Cohens kappa for patient CVD risk categorization by the evaluated methods ranged from 0.80 to 1.00. CONCLUSIONS A publicly available standardized framework for the evaluation of (semi)automatic methods for CAC identification in cardiac CT is described. An evaluation of five (semi)automatic methods within this framework shows that automatic per patient CVD risk categorization is feasible. CAC lesions at ambiguous locations such as the coronary ostia remain challenging, but their detection had limited impact on CVD risk determination.

Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis

HighlightsPresence of functionally significant coronary stenosis is determined automatically.Functional significance of the stenosis is determined by myocardium analysis.Deep learning is applied to analyze the left ventricle myocardium in coronary CTA.The results demonstrate that identification of patients with low FFR is feasible.This may potentially reduce the number of patients undergoing invasive FFR. Graphical abstract Figure. No Caption available. Abstract In patients with coronary artery stenoses of intermediate severity, the functional significance 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 identification of patients with functionally significant 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 significant 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 classified according to the presence of functionally significant stenosis using an SVM classifier based on the extracted features. Quantitative evaluation of LV myocardium segmentation in 20 images resulted in an average Dice coefficient 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. Classification 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 specificity 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 significant coronary artery stenosis. This might reduce the number of patients undergoing unnecessary invasive FFR measurements.

Submillisievert coronary calcium quantification using model-based iterative reconstruction : A within-patient analysis

PURPOSE To determine the effect of model-based iterative reconstruction (IR) on coronary calcium quantification using different submillisievert CT acquisition protocols. METHODS Twenty-eight patients received a clinically indicated non contrast-enhanced cardiac CT. After the routine dose acquisition, low-dose acquisitions were performed with 60%, 40% and 20% of the routine dose mAs. Images were reconstructed with filtered back projection (FBP), hybrid IR (HIR) and model-based IR (MIR) and Agatston scores, calcium volumes and calcium mass scores were determined. RESULTS Effective dose was 0.9, 0.5, 0.4 and 0.2mSv, respectively. At 0.5 and 0.4mSv, differences in Agatston scores with both HIR and MIR compared to FBP at routine dose were small (-0.1 to -2.9%), while at 0.2mSv, differences in Agatston scores of -12.6 to -14.6% occurred. Reclassification of risk category at reduced dose levels was more frequent with MIR (21-25%) than with HIR (18%). CONCLUSIONS Radiation dose for coronary calcium scoring can be safely reduced to 0.4mSv using both HIR and MIR, while FBP is not feasible at these dose levels due to excessive noise. Further dose reduction can lead to an underestimation in Agatston score and subsequent reclassification to lower risk categories. Mass scores were unaffected by dose reductions.