Cardiac CT Angiography Scans Research Articles

Calculation of left ventricular ejection fraction using an 8-layer residual U-Net with deep supervision based on cardiac CT angiography images versus echocardiography: a comparative study.

Accurate segmentation of the left ventricle (LV) is an important step in assessing cardiac function. Cardiac CT angiography (CCTA) has become an important means of clinical diagnosis of cardiovascular diseases (CVDs) because of its advantages of non-invasive, short examination time and low cost. In order to obtain the segmentation of LV in CCTA scans, we propose a deep learning method based on 8-layer residual U-Net with deep supervision. In this study we compared the left ventricular ejection fraction (LVEF) calculated by deep learning (DL) method (AccuLV) from CCTA to LVEF by conventional two-dimensional echocardiography (EC). This was a retrospective cross-sectional study, and consecutive patients who had undergone CCTA and EC in our hospital from February 2021 to May 2021 were recruited. The current study included 180 patients who had undergone CCTA and EC. To obtain LVEF, we used an 8-layer residual U-Net with deep supervision to segment LV contours from CCTA images and compute LVEF (DL-LVEF). The EC and DL-LVEF measurements were compared. A 50% EC-LVEF cut-off value was used as a reference standard to assess the diagnostic performance of AccuLV in assessing LV function. The overall mean EC-LVEF and DL-LVEF values were 64.0% (52.3%, 69.0%) and 73.0% (52.3%, 77.0%), respectively. Three patient groups were studied: (I) hypertensive patients, (II) postmenopausal women, and (III) diabetes. EC-LVEF and DL-LVEF were found to be positively correlated for all of the included patients (r=0.82, P<0.001), with the detailed results for the three groups as follows: hypertensive patients (r=0.77, P<0.001), postmenopausal women (r=0.92, P<0.001) and diabetes (r=0.88, P<0.001). The diagnostic accuracy, sensitivity, and specificity of the DL method in predicting EC-LVEF <50% for all patients were 93.9%, 92.3%, and 94.3%, and for hypertensive patients were 95.4%, 93.8%, and 95.8%, for postmenopausal women were 87.0%, 100%, and 84.2%, for diabetes were 97.4%, 100%, and 96.6%. In comparison to echocardiography, which is commonly used in clinical setting, AccuLV may be a promising, fully automated tool for rapid and accurate quantification of LV function and thus for making reliable clinical decisions.

An 8-layer residual U-Net with deep supervision for segmentation of the left ventricle in cardiac CT angiography

Accurate segmentation of left ventricle (LV) is a fundamental step in evaluation of cardiac function. Cardiac CT angiography (CCTA) has become an important clinical diagnostic method for cardio-vascular disease (CVD) due to its non-invasive, short exam time, and low cost. To obtain the segmentation of the LV in CCTA scans, we present a deep learning method based on an 8-layer residual U-Net with deep supervision. Based on the original 4-layer U-Net, our method deepened the network to eight layers, which increased the fitting capacity of the network, thus greatly improved its LV recognition capability. Residual blocks were incorporated to optimize the network from the increased depth. Auxiliary paths as deep supervision were introduced to supervise the intermediate information to improve the segmentation quality. In this study, we collected CCTA scans of 100 patients. Eighty patients with 1600 discrete slices were used to train the LV segmentation and the remaining 20 patients with 400 discrete slices were used for testing our method. An interactive graph cut algorithm was utilized reliably to annotate the LV reference standard that was further confirmed by cardiologists. Online data augmentation was performed in the training process to improve the generalization and robustness of our method. Compared with the segmentation results from the original U-Net and FC-DenseNet56 with Dice similarity coefficient (DSC) of 0.878±0.230 and 0.897±0.189, respectively, our method demonstrated higher segmentation accuracy and robustness for varying LV shape, size, and contrast, achieving DSC of 0.927±0.139. Without online data augmentation, our method resulted in inferior performance with DSC of 0.911±0.170. In addition, compared with the provided results from other existing studies in the LV segmentation of cardiac CT images, our method achieved a competitive performance for the LV segmentation. The proposed 8-layer residual U-Net with deep supervision accurately and efficiently segments the LV in CCTA scans. This method has potential advantages to be a reliable segmentation method and useful for the evaluation of cardiac function in the future study.

Deep Learning Analysis of Coronary Arteries in Cardiac CT Angiography for Detection of Patients Requiring Invasive Coronary Angiography.

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.

Coronary artery centerline extraction in cardiac CT angiography using a CNN-based orientation classifier.

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 tracker's 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 ± 0.1s and fully automatic coronary tree extraction required around 20s. 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.

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.

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.

Impact of Increasing Levels of Advanced Iterative Reconstruction on Image Quality in Low-Dose Cardiac CT Angiography

To investigate the effects of an advanced iterative reconstruction (IR) technique on subjective and objective image quality (IQ) in low-dose cardiac CT angiography (CCTA). 30 datasets of prospectively triggered "step-and-shoot" CCTA scans acquired on a 256-slice CT scanner with optimized exposure settings were processed on a prototype IR system using filtered back-projection (FBP) and 4 levels of advanced IR (iDose4, Philips) providing incremental rates of IR (level 2, 4, 6, 7). In addition, the effects of different reconstruction kernels (semi-smooth [CB], standard with edge-enhancement [XCB]) and a "multi-resolution" feature [MR] to preserve the noise power spectrum were evaluated resulting in a total of n = 480 image sets. Contrast-to-noise ratios (CNR) were computed from regions of interest at 9 coronary locations. The subjective IQ was rated on a 4-point-scale with "classic" image appearance and noise-related artifacts as main criteria. At an effective dose of 1.7 ± 0.7 mSv, the CNR significantly improved with every increasing level of IR (range: 14.2 - 27.8; p < 0.001) with the best objective IQ at the highest level of IR (level 7). The subjective IQ, however, was rated best at the medium level of IR (level 4) with minimal artifacts and a more "classic" image appearance when compared to higher IR levels. The XCB kernel provided better subjective ratings than CB (p < 0.05) and the MR feature further increased the IQ at a high level of IR. The objective IQ of low-dose CCTA progressively improves with an increasing level of IR. The best subjective IQ, however, is reached at medium levels of IR combined with an edge-enhancing kernel allowing for preservation of a "classic" image appearance suggesting application in the clinical routine. • iterative reconstruction (IR) improves image quality in low-dose coronary CTA• objective image quality (CNR) enhances with increasing level of IR• best subjective image quality is reached at medium level of IR• "multi-resolution" algorithm further improves image quality at a higher level of IR.