Deep-learning-based image segmentation for image-based computational hemodynamic analysis of abdominal aortic aneurysms: a comparison study.

Computational hemodynamics is increasingly being used to quantify hemodynamic characteristics in and around abdominal aortic aneurysms (AAA) in a patient-specific fashion. However, the time-consuming manual annotation hinders the clinical translation of computational hemodynamic analysis. Thus, we investigate the feasibility of using deep-learning-based image segmentation methods to reduce the time required for manual segmentation. Two of the latest deep-learning-based image segmentation methods, ARU-Net and CACU-Net, were used to test the feasibility of automated computer model creation for computational hemodynamic analysis. Morphological features and hemodynamic metrics of 30 computed tomography angiography (CTA) scans were compared between pre-dictions and manual models. The DICE score for both networks was 0.916, and the correlation value was above 0.95, indicating their ability to generate models comparable to human segmentation. The Bland-Altman analysis shows a good agreement between deep learning and manual segmentation results. Compared with manual (computational hemodynamics) model recreation, the time for automated computer model generation was significantly reduced (from ∼2 h to ∼10 min). Automated image segmentation can significantly reduce time expenses on the recreation of patient-specific AAA models. Moreover, our study showed that both CACU-Net and ARU-Net could accomplish AAA segmentation, and CACU-Net outperformed ARU-Net in terms of accuracy and time-saving.

Automatic extraction of coronary arteries using deep learning in invasive coronary angiograms.

BACKGROUND: Accurate extraction of coronary arteries from invasive coronary angiography (ICA) images is essential for the diagnosis and risk stratification of coronary artery disease (CAD). OBJECTIVE: In this study, a novel deep learning (DL) method is proposed for automatically extracting coronary arteries from ICA images. METHODS: A convolutional neural network (CNN) was developed with full-scale skip connections and full-scale deep supervisions. The encoder architecture was based on the residual and inception modules to obtain multi-scale features from multiple convolutional layers with different window shapes. Transfer learning was utilized to improve both the initial performance and learning efficiency. A hybrid loss function was employed to further optimize the segmentation model. RESULTS: The model was tested on a data set of 616 ICAs obtained from 210 patients, composed of 437 images for training, 49 images for validation, and 130 images for testing. The segmentation model achieved a Dice score of 0.8942, a sensitivity of 0.8735, a specificity of 0.9954, and a Hausdorff distance of 6.0794 mm; it could predict arteries for a single ICA frame in 0.2114 seconds. CONCLUSIONS: The results showed that our model outperformed the state-of-the-art deep-learning models. Our new method has great potential for clinical use.

AGMN: Association Graph-based Graph Matching Network for Coronary Artery Semantic Labeling on Invasive Coronary Angiograms.

Semantic labeling of coronary arterial segments in invasive coronary angiography (ICA) is important for automated assessment and report generation of coronary artery stenosis in computer-aided coronary artery disease (CAD) diagnosis. However, separating and identifying individual coronary arterial segments is challenging because morphological similarities of different branches on the coronary arterial tree and human-to-human variabilities exist. Inspired by the training procedure of interventional cardiologists for interpreting the structure of coronary arteries, we propose an association graph-based graph matching network (AGMN) for coronary arterial semantic labeling. We first extract the vascular tree from invasive coronary angiography (ICA) and convert it into multiple individual graphs. Then, an association graph is constructed from two individual graphs where each vertex represents the relationship between two arterial segments. Thus, we convert the arterial segment labeling task into a vertex classification task; ultimately, the semantic artery labeling becomes equivalent to identifying the artery-to-artery correspondence on graphs. More specifically, the AGMN extracts the vertex features by the embedding module using the association graph, aggregates the features from adjacent vertices and edges by graph convolution network, and decodes the features to generate the semantic mappings between arteries. By learning the mapping of arterial branches between two individual graphs, the unlabeled arterial segments are classified by the labeled segments to achieve semantic labeling. A dataset containing 263 ICAs was employed to train and validate the proposed model, and a five-fold cross-validation scheme was performed. Our AGMN model achieved an average accuracy of 0.8264, an average precision of 0.8276, an average recall of 0.8264, and an average F1-score of 0.8262, which significantly outperformed existing coronary artery semantic labeling methods. In conclusion, we have developed and validated a new algorithm with high accuracy, interpretability, and robustness for coronary artery semantic labeling on ICAs.

Automatic extraction and stenosis evaluation of coronary arteries in invasive coronary angiograms.

BACKGROUND: Coronary artery disease (CAD) is the leading cause of death in the United States (US) and a major contributor to healthcare cost. Accurate segmentation of coronary arteries and detection of stenosis from invasive coronary angiography (ICA) are crucial in clinical decision making. PURPOSE: We aim to develop an automatic method to extract coronary arteries by deep learning and detect arterial stenosis from ICAs. METHODS: In this study, a deep learning model which integrates a feature pyramid with a U-Net++ model was developed to automatically segment coronary arteries in ICAs. A compound loss function which contains Dice loss, dilated Dice loss, and L2 regularization was utilized to train the proposed segmentation model. Following the segmentation, an algorithm which extracts vascular centerlines, calculates the diameters, and measures the stenotic levels, was developed to detect arterial stenosis. RESULTS AND CONCLUSIONS: In the dataset consisting of 314 ICAs obtained from 99 patients, the segmentation model achieved an average Dice score of 0.8899, a sensitivity of 0.8595, and a specificity of 0.9960. In addition, the stenosis detection algorithm achieved a true positive rate of 0.6840 and a positive predictive value of 0.6998 on all types of stenosis, which has great promise to advance to clinical uses and could provide auxiliary suggestions for CAD diagnosis and treatment.