Automatic identification of coronary tree anatomy in coronary computed tomography angiography

HAGMN-UQ: Hyper association graph matching network with uncertainty quantification for coronary artery semantic labeling

Coronary artery disease (CAD) is one of the leading causes of death worldwide. Accurate extraction of individual arterial branches from invasive coronary angiograms (ICA) is critical for CAD diagnosis and detection of stenosis. Generating semantic segmentation for coronary arteries through deep learning-based models presents challenges due to the morphological similarity among different types of coronary arteries, making it difficult to maintain high accuracy while keeping low computational complexity. To address this challenge, we propose an innovative approach using the hyper association graph-matching neural network with uncertainty quantification (HAGMN-UQ) for coronary artery semantic labeling on ICAs. The graph-matching procedure maps the arterial branches between two individual graphs, so that the unlabeled arterial segments are classified by the labeled segments, and the coronary artery semantic labeling is achieved. Leveraging hypergraphs not only extends representation capabilities beyond pairwise relationships, but also improves the robustness and accuracy of the graph matching by enabling the modeling of higher-order associations. In addition, employing the uncertainty quantification to determine the trustworthiness of graph matching reduces the required number of comparisons, so as to accelerate the inference speed. Consequently, our model achieved an accuracy of 0.9211 for coronary artery semantic labeling with a fast inference speed, leading to an effective and efficient prediction in real-time clinical decision-making scenarios.

Evolving Role of Coronary CT Angiography in Coronary Angiography and Intervention: A State-of-the-Art Review

PURPOSE OF REVIEW

Despite growing evidence supporting the diagnostic utility of coronary computed tomographic angiography (CCTA) for anatomical assessment of coronary artery disease (CAD), its is underutilized in peri-procedural planning especially in the acute setting.

RECENT FINDINGS

Incorporation of flow reserve measurement techniques into CCTA has expanded its sensitivity and specificity for obstructive disease, and continued improvement in CCTA technology permits more accurate cross-sectional plaque characterization. CCTA has the potential to constitute the mainstay of pre-procedural planning for patients with CAD, who are being considered for percutaneous coronary intervention , reducing their ad hoc nature while facilitating equipment selection and improving catheterization lab safety and throughput. Future studies are needed to compare the cost and benefits of more frequent use of routine pre-procedural CCTA prior to coronary angiography and intervention.

The role of artificial intelligence in coronary CT angiography

Coronary CT angiography (CCTA) offers an efficient and reliable tool for the non-invasive assessment of suspected coronary artery disease through the analysis of coronary artery plaque and stenosis. However, the detailed manual analysis of CCTA is a burdensome task requiring highly skilled experts. Recent advances in artificial intelligence (AI) have made significant progress toward a more comprehensive automated analysis of CCTA images, offering potential improvements in terms of speed, performance and scalability. This work offers an overview of the recent developments of AI in CCTA. We cover methodological advances for coronary artery tree and whole heart analysis, and provide an overview of AI techniques that have shown to be valuable for the analysis of cardiac anatomy and pathology in CCTA. Finally, we provide a general discussion regarding current challenges and limitations, and discuss prospects for future research.

Systematic characterization and automated alignment of coronary tree geometries

Coronary artery disease (CAD) is the most common form of cardiovascular disease, characterized by gradual narrowing of the artery walls due to plaque buildup. Computational fluid dynamics (CFD) is a non-invasive approach often used to investigate how these anatomical changes perturb local hemodynamics and contribute to the pathological mechanism of progression. Therefore, the accuracy of coronary tree alignment and anatomical feature detection is key to understanding these hemodynamically mediated mechanisms. Despite advances, current methods face challenges, such as the need for manual selection of landmarks, often resulting in a semi-automated experience. This study aims to improve this by developing a fully automated system to detect 3D anatomical characteristics and align coronary tree geometries in large clinical datasets. Our proposed algorithm enables full automatic placement of the corresponding centerline points and alignment evaluation through similarity-based assessment of Jaccard index (intersection over union) in a cohort of 73 coronary geometries.

Graph neural networks for automatic extraction and labeling of the coronary artery tree in CT angiography

Purpose

Automatic comprehensive reporting of coronary artery disease (CAD) requires anatomical localization of the coronary artery pathologies. To address this, we propose a fully automatic method for extraction and anatomical labeling of the coronary artery tree using deep learning.

Approach

We include coronary CT angiography (CCTA) scans of 104 patients from two hospitals. Reference annotations of coronary artery tree centerlines and labels of coronary artery segments were assigned to 10 segment classes following the American Heart Association guidelines. Our automatic method first extracts the coronary artery tree from CCTA, automatically placing a large number of seed points and simultaneous tracking of vessel-like structures from these points. Thereafter, the extracted tree is refined to retain coronary arteries only, which are subsequently labeled with a multi-resolution ensemble of graph convolutional neural networks that combine geometrical and image intensity information from adjacent segments.

Results

The method is evaluated on its ability to extract the coronary tree and to label its segments, by comparing the automatically derived and the reference labels. A separate assessment of tree extraction yielded an F 1 score of 0.85. Evaluation of our combined method leads to an average F 1 score of 0.74.

Conclusions

The results demonstrate that our method enables fully automatic extraction and anatomical labeling of coronary artery trees from CCTA scans. Therefore, it has the potential to facilitate detailed automatic reporting of CAD.

Deep Learning-Based Automated Labeling of Coronary Segments for Structured Reporting of Coronary Computed Tomography Angiography in Accordance With Society of Cardiovascular Computed Tomography Guidelines

PURPOSE

To evaluate a novel deep learning (DL)-based automated coronary labeling approach for structured reporting of coronary artery disease according to the guidelines of the Society of Cardiovascular Computed Tomography (CT) on coronary CT angiography (CCTA).

PATIENTS AND METHODS

A retrospective cohort of 104 patients (60.3 ± 10.7 y, 61% males) who had undergone prospectively electrocardiogram-synchronized CCTA were included. Coronary centerlines were automatically extracted, labeled, and validated by 2 expert readers according to Society of Cardiovascular CT guidelines. The DL algorithm was trained on 706 radiologist-annotated cases for the task of automatically labeling coronary artery centerlines. The architecture leverages tree-structured long short-term memory recurrent neural networks to capture the full topological information of the coronary trees by using a two-step approach: a bottom-up encoding step, followed by a top-down decoding step. The first module encodes each sub-tree into fixed-sized vector representations. The decoding module then selectively attends to the aggregated global context to perform the local assignation of labels. To assess the performance of the software, percentage overlap was calculated between the labels of the algorithm and the expert readers.

RESULTS

A total number of 1491 segments were identified. The artificial intelligence-based software approach yielded an average overlap of 94.4% compared with the expert readers' labels ranging from 87.1% for the posterior descending artery of the right coronary artery to 100% for the proximal segment of the right coronary artery. The average computational time was 0.5 seconds per case. The interreader overlap was 96.6%.

CONCLUSIONS

The presented fully automated DL-based coronary artery labeling algorithm provides fast and precise labeling of the coronary artery segments bearing the potential to improve automated structured reporting for CCTA.

A deep learning-based automated algorithm for labeling coronary arteries in computed tomography angiography images

OBJECTIVE

Using two three-dimensional U-Net architectures for myocardium structure extraction and a distance transformation algorithm specifically for the left circumflex artery, we have designed a fully automated algorithm for coronary artery labeling in coronary computed tomography angiography (CCTA) images.

METHODS

In this retrospective analysis, a cohort of 157 patients who had undergone coronary computed tomography angiography (CCTA) was included. An automated coronary artery labeling algorithm was developed using a distance transformation approach to delineate the anatomical segments along the centerlines extracted from the CCTA images. A total of 16 segments were successfully identified and labeled. The algorithm's outcomes were recorded and reviewed by three experts, and the performance of segment detection and labeling was assessed. Additionally, the level of agreement in manually labeled segments between two experts was quantified.

RESULTS

When comparing the labels generated by the experts with those produced by the algorithm, it was necessary to modify or eliminate 117 labels (5.4%) out of 2180 segments assigned by the algorithm. The overall accuracy for label presence was 96.2%, with an average overlap of 94.0% between the expert reference and algorithm-generated labels. Furthermore, the average agreement rate between the two experts stood at 95.0%.

CONCLUSIONS

Based on the labels of the clinical experts, the proposed deep learning algorithm exhibits high accuracy for automatic labeling. Therefore, our proposed method exhibits promising results for the automatic labeling of the coronary arteries and will alleviate the burden on radiologists in the near future.

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.

EAGMN: Coronary artery semantic labeling using edge attention graph matching network

Coronary artery disease (CAD) is one of the primary causes leading deaths worldwide. The presence of atherosclerotic lesions in coronary arteries is the underlying pathophysiological basis of CAD, and accurate extraction of individual arterial branches using invasive coronary angiography (ICA) is crucial for stenosis detection and CAD diagnosis. However, deep-learning-based models face challenges in generating semantic segmentation for coronary arteries due to the morphological similarity among different types of arteries. To address this challenge, we propose an innovative approach called the Edge Attention Graph Matching Network (EAGMN) for coronary artery semantic labeling. Inspired by the learning process of interventional cardiologists in interpreting ICA images, our model compares arterial branches between two individual graphs generated from different ICAs. We begin with extracting individual graphs based on the vascular tree obtained from the ICA. Each node in the individual graph represents an arterial segment, and the EAGMN aims to learn the similarity between nodes from the two individual graphs. By converting the coronary artery semantic segmentation task into a graph node similarity comparison task, identifying the node-to-node correspondence would assign semantic labels for each arterial branch. More specifically, the EAGMN utilizes the association graph constructed from the two individual graphs as input. A graph attention module is employed for feature embedding and aggregation, while a decoder generates the linear assignment for node-to-node semantic mapping. Based on the learned node-to-node relationships, unlabeled coronary arterial segments are classified using the labeled coronary arterial segments, thereby achieving semantic labeling. A dataset with 263 labeled ICAs is used to train and validate the EAGMN. Experimental results indicate the EAGMN achieved a weighted accuracy of 0.8653, a weighted precision of 0.8656, a weighted recall of 0.8653 and a weighted F1-score of 0.8643. Furthermore, we employ ZORRO to provide interpretability and explainability of the graph matching for artery semantic labeling. These findings highlight the potential of the EAGMN for accurate and efficient coronary artery semantic labeling using ICAs. By leveraging the inherent characteristics of ICAs and incorporating graph matching techniques, our proposed model provides a promising solution for improving CAD diagnosis and treatment.

TTN: Topological Transformer Network for Automated Coronary Artery Branch Labeling in Cardiac CT Angiography

OBJECTIVE

Existing methods for automated coronary artery branch labeling in cardiac CT angiography face two limitations: 1) inability to model overall correlation of branches, since differences between branches cannot be captured directly. 2) a serious class imbalance between main and side branches.

METHODS AND PROCEDURES

Inspired by the application of Transformer in sequence data, we propose a topological Transformer network (TTN), which solves the vessel branch labeling from a novel perspective of sequence labeling learning. TTN detects differences between branches by establishing their overall correlation. A topological encoding that represents the positions of vessel segments in the artery tree, is proposed to assist the model in classifying branches. Also, a segment-depth loss is introduced to solve the class imbalance between main and side branches.

RESULTS

On a dataset with 325 CCTA, our method obtains the best overall result on all branches, the best result on side branches, and a competitive result on main branches.

CONCLUSION

TTN solves two limitations in existing methods perfectly, thus achieving the best result in coronary artery branch labeling task. It is the first Transformer based vessel branch labeling method and is notably different from previous methods.

CLINICAL IMPACT

This Pre-Clinical Research can be integrated into a computer-aided diagnosis system to generate cardiovascular disease diagnosis report, assisting clinicians in locating the atherosclerotic plaques.

TaG-Net: Topology-Aware Graph Network for Centerline-Based Vessel Labeling

Anatomical labeling of head and neck vessels is a vital step for cerebrovascular disease diagnosis. However, it remains challenging to automatically and accurately label vessels in computed tomography angiography (CTA) since head and neck vessels are tortuous, branched, and often spatially close to nearby vasculature. To address these challenges, we propose a novel topology-aware graph network (TaG-Net) for vessel labeling. It combines the advantages of volumetric image segmentation in the voxel space and centerline labeling in the line space, wherein the voxel space provides detailed local appearance information, and line space offers high-level anatomical and topological information of vessels through the vascular graph constructed from centerlines. First, we extract centerlines from the initial vessel segmentation and construct a vascular graph from them. Then, we conduct vascular graph labeling using TaG-Net, in which techniques of topology-preserving sampling, topology-aware feature grouping, and multi-scale vascular graph are designed. After that, the labeled vascular graph is utilized to improve volumetric segmentation via vessel completion. Finally, the head and neck vessels of 18 segments are labeled by assigning centerline labels to the refined segmentation. We have conducted experiments on CTA images of 401 subjects, and experimental results show superior vessel segmentation and labeling of our method compared to other state-of-the-art methods.

Predictive value of carotid artery ultrasonography for the risk of coronary artery disease

PURPOSE

To assess carotid intima-media thickness (IMT), carotid plaques, and cardiovascular risk factors in patients with suspected coronary artery disease (CHD) to determine their association and predictive value for CHD.

METHODS

We performed duplex Doppler ultrasonography of the carotid arteries and coronary angiography or CT in 480 patients with suspected CHD, and investigated their personal and medical histories. Patients were then assigned to the CHD or the control group depending on the presence of coronary lesions. Ultrasonography was performed the morning after admission prior to any treatment, coronary angiography, or CT.

RESULTS

Carotid plaques were mainly distributed in the common carotid artery bifurcation, with a significant difference between the CHD and control groups. Plaque incidence (80%) and IMT were significantly higher (P < .001 and P = .012, respectively) in the CHD (80% and 0.84 ± 0.21 mm) than in the control group (49% and 0.76 ± 0.18 mm). The factors significantly associated with CHD were introduced into a multivariate regression model. Male subject (OR = 1.569, 95%CI 1.004-2.453; P = .048) and plaque burden (OR = 0.457, 95%CI 0.210-0.993; P = .048) were significant predictors for CHD occurrence. The presence of carotid plaques performed significantly better than IMT and the Framingham risk score for predicting CHD lesions (P < .001 for both).

CONCLUSIONS

CHD patients showed higher percentage of clinical (plaques) or subclinical (IMT) carotid artery wall change, and the presence of carotid plaques showed better predictive value than IMT and Framingham risk score for the presence of coronary artery lesions.

A model-guided method for improving coronary artery tree extractions from CCTA images

Purpose

Automatically extracted coronary artery trees (CATs) from coronary computed tomography angiography images could contain incorrect extractions which require manual corrections before they can be used in clinical practice. A model-guided method for improving the extracted CAT is described to automatically detect potential incorrect extractions and improve them.

Methods

The proposed method is a coarse-to-fine approach. A coarse improvement is first applied on all vessels in the extracted CAT, and then a fine improvement is applied only on vessels with higher clinical significance. Based upon a decision tree, the proposed method automatically and iteratively performs improvement operations for the entire extracted CAT until it meets the stop criteria. The improvement in the extraction quality obtained by the proposed method is measured using a scoring system. 18 datasets were used to determine optimal values for the parameters involved in the model-guided method and 122 datasets were used for evaluation.

Results

Compared to the initial automatic extractions, the proposed method improves the CATs for 122 datasets from an average quality score of 87 ± 6 to 93 ± 4. The developed method is able to run within 2 min on a typical workstation. The difference in extraction quality after automatic improvement is negatively correlated with the initial extraction quality (R = − 0.694, P < 0.001).

Conclusion

Without deteriorating the initially extracted CATs, the presented method automatically detects incorrect extractions and improves the CATs to an average quality score of 93 guided by anatomical statistical models.

Electronic supplementary material

The online version of this article (10.1007/s11548-018-1891-7) contains supplementary material, which is available to authorized users.