Robbert W. van Hamersvelt

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 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.

Effect of radiation dose reduction and iterative reconstruction on computer-aided detection of pulmonary nodules: Intra-individual comparison

OBJECTIVE To evaluate the effect of radiation dose reduction and iterative reconstruction (IR) on the performance of computer-aided detection (CAD) for pulmonary nodules. METHODS In this prospective study twenty-five patients were included who were scanned for pulmonary nodule follow-up. Image acquisition was performed at routine dose and three reduced dose levels in a single session by decreasing mAs-values with 45%, 60% and 75%. Tube voltage was fixed at 120 kVp for patients ≥ 80 kg and 100 kVp for patients < 80 kg. Data were reconstructed with filtered back projection (FBP), iDose(4) (levels 1,4,6) and IMR (levels 1-3). All noncalcified solid pulmonary nodules ≥ 4 mm identified by two radiologists in consensus served as the reference standard. Subsequently, nodule volume was measured with CAD software and compared to the reference consensus. The numbers of true-positives, false-positives and missed pulmonary nodules were evaluated as well as the sensitivity. RESULTS Median effective radiation dose was 2.2 mSv at routine dose and 1.2, 0.9 and 0.6 mSv at respectively 45%, 60% and 75% reduced dose. A total of 28 pulmonary nodules were included. With FBP at routine dose, 89% (25/28) of the nodules were correctly identified by CAD. This was similar at reduced dose levels with FBP, iDose(4) and IMR. CAD resulted in a median number of false-positives findings of 11 per scan with FBP at routine dose (93% of the CAD marks) increasing to 15 per scan with iDose(4) (95% of the CAD marks) and 26 per scan (96% of the CAD marks) with IMR at the lowest dose level. CONCLUSION CAD can identify pulmonary nodules at submillisievert dose levels with FBP, hybrid and model-based IR. However, the number of false-positive findings increased using hybrid and especially model-based IR at submillisievert dose while dose reduction did not affect the number of false-positives with FBP.

Automatic segmentation of the left ventricle in cardiac CT angiography using convolutional neural networks

Accurate delineation of the left ventricle (LV) is an important step in evaluation of cardiac function. In this paper, we present an automatic method for segmentation of the LV in cardiac CT angiography (CCTA) scans. Segmentation is performed in two stages. First, a bounding box around the LV is detected using a combination of three convolutional neural networks (CNNs). Subsequently, to obtain the segmentation of the LV, voxel classification is performed within the defined bounding box using a CNN. The study included CCTA scans of sixty patients, fifty scans were used to train the CNNs for the LV localization, five scans were used to train LV segmentation and the remaining five scans were used for testing the method. Automatic segmentation resulted in the average Dice coefficient of 0.85 and mean absolute surface distance of 1.1 mm. The results demonstrate that automatic segmentation of the LV in CCTA scans using voxel classification with convolutional neural networks is feasible.

Pulmonary Nodule Volumetry at Different Low Computed Tomography Radiation Dose Levels With Hybrid and Model-Based Iterative Reconstruction: A Within Patient Analysis.

Objective The aim of the study was to determine the effects of dose reduction and iterative reconstruction (IR) on pulmonary nodule volumetry. Methods In this prospective study, 25 patients scheduled for follow-up of pulmonary nodules were included. Computed tomography acquisitions were acquired at 4 dose levels with a median of 2.1, 1.2, 0.8, and 0.6 mSv. Data were reconstructed with filtered back projection (FBP), hybrid IR, and model-based IR. Volumetry was performed using semiautomatic software. Results At the highest dose level, more than 91% (34/37) of the nodules could be segmented, and at the lowest dose level, this was more than 83%. Thirty-three nodules were included for further analysis. Filtered back projection and hybrid IR did not lead to significant differences, whereas model-based IR resulted in lower volume measurements with a maximum difference of −11% compared with FBP at routine dose. Conclusions Pulmonary nodule volumetry can be accurately performed at a submillisievert dose with both FBP and hybrid IR.

Aortic Valve and Thoracic Aortic Calcification Measurements: How Low Can We Go in Radiation Dose?

Objective This study aimed to determine the lowest radiation dose and iterative reconstruction level(s) at which computed tomography (CT)–based quantification of aortic valve calcification (AVC) and thoracic aortic calcification (TAC) is still feasible. Methods Twenty-eight patients underwent a cardiac CT and 20 patients a chest CT at 4 different dose levels (routine dose and approximately 40%, 60%, and 80% reduced dose). Data were reconstructed with filtered back projection, 3 iDose4 levels, and 3 iterative model-based reconstruction levels. Two observers scored subjective image quality. The AVC and TAC were quantified using mass and compared to the reference scan (routine dose reconstructed with filtered back projection). Results In cardiac CT at 0.35 mSv (60% reduced), all scans reconstructed with iDose4 (all levels) were diagnostic, calcification detection errors occurred in only 1 patient, and there were no significant differences in mass scores compared to the reference scan. Similar results were found for chest CT at 0.48 mSv (75% reduced) with iDose4 levels 4 and 6 and iterative model reconstruction levels 1 and 2. Conclusions Iterative reconstruction enables AVC and TAC quantification on CT at submillisievert dose.

Dual energy CT to reveal pseudo leakage of frozen elephant trunk

In this case report dual energy CT information was used to reveal a pseudo leakage of a frozen elephant trunk stent. Different materials, which could not be distinguished based on attenuation number, were distinguished with the use of material decomposition algorithms using DECT acquisitions. By using material decomposition imaging, the DECT system proved that in this case the extraluminal densities were not caused by leakage but by a Teflon Felt supported suture.

Coronary Artery Centerline Extraction in Cardiac CT Angiography Using a CNN-Based Orientation Classifier

&NA; Coronary artery centerline extraction in cardiac CT angiography (CCTA) images is a prerequisite for evaluation of stenoses and atherosclerotic plaque. In this work, we propose an algorithm that extracts coronary artery centerlines in CCTA using a convolutional neural network (CNN). In the proposed method, 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 is trained using manually annotated centerlines in training images. No image preprocessing is required, so that the process is guided solely by the local image values around the trackers location. The CNN was trained using a training set consisting of 8 CCTA images with a total of 32 manually annotated centerlines provided in the MICCAI 2008 Coronary Artery Tracking Challenge (CAT08). Evaluation was performed within the CAT08 challenge using a test set consisting of 24 CCTA test images in which 96 centerlines were extracted. The extracted centerlines had an average overlap of 93.7% with manually annotated reference centerlines. Extracted centerline points were highly accurate, with an average distance of 0.21 mm to reference centerline points. Based on these results the method ranks third among 25 publicly evaluated methods in CAT08. In a second test set consisting of 50 CCTA scans acquired at our institution (UMCU), an expert placed 5448 markers in the coronary arteries, along with radius measurements. Each marker was used as a seed point to extract a single centerline, which was compared to the other markers placed by the expert. This showed strong correspondence between extracted centerlines and manually placed markers. In a third test set containing 36 CCTA scans from the MICCAI 2014 Challenge on Automatic Coronary Calcium Scoring (orCaScore), fully automatic seeding and centerline extraction was evaluated using a segment‐wise analysis. This showed that the algorithm is able to fully‐automatically extract on average 92% of clinically relevant coronary artery segments. Finally, the limits of agreement between reference and automatic artery radius measurements were found to be below the size of one voxel in both the CAT08 dataset and the UMCU dataset. Extraction of a centerline based on a single seed point required on average 0.4 ± 0.1 s and fully automatic coronary tree extraction required around 20 s. The proposed method is able to accurately and efficiently determine the direction and radius of coronary arteries based on information derived directly from the image data. 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.

Anterior longitudinal ligament in diffuse idiopathic skeletal hyperostosis: Ossified or displaced?: “THE ALL IN DISH”

Diffuse idiopathic skeletal hyperostosis (DISH) is often theorized to be an ossification of the anterior longitudinal ligament (ALL). Using computed tomography (CT) imaging and cryomacrotome sectioning, we investigated the spatial relationship between the ALL and newly formed bone in DISH to test this hypothesis. In the current study, four human cadaveric spines diagnosed with DISH using CT imaging were frozen and sectioned using a cryomacrotome. Photographs were obtained of the specimen at 125 µm intervals. Manual segmentations of the ALL on cryomacrotome photographs were projected onto the three‐dimensional reconstructed CT scans. The presence and location of newly formed bone were assessed in relationship to the location of the ALL. The ALL could be identified and segmented on the photographs at all levels. The ALL was located at the midline at levels where no new bone had formed. At the locations where new bone had abundantly formed, the ALL was displaced towards to the contralateral side and not replaced by bony tissue. The displacement of the—morphologically normal appearing—ALL away from the newly formed bone implies that newly formed bone in DISH may not originate from the ALL.