X-ray Coronary Angiography Research Articles

X-ray coronary angiography background subtraction by adaptive weighted total variation regularized online RPCA

Objective.X-ray coronary angiograms (XCA) are widely used in diagnosing and treating cardiovascular diseases. Various structures with independent motion patterns in the background of XCA images and limitations in the dose of injected contrast agent have resulted in low-contrast XCA images. Background subtraction methods have been developed to enhance the visibility and contrast of coronary vessels in XCA sequences, consequently reducing the requirement for excessive contrast agent injections.Approach.The current study proposes an adaptive weighted total variation regularized online RPCA (WTV-ORPCA) method, which is a low-rank and sparse subspaces decomposition approach to subtract the background of XCA sequences. In the proposed method, the images undergo initial preprocessing using morphological operators to eliminate large-scale background structures and achieve image homogenization. Subsequently, the decomposition algorithm decomposes the preprocessed images into background and foreground subspaces. This step applies an adaptive weighted TV constraint to the foreground subspace to ensure the spatial coherency of the finally extracted coronary vessel images.Main results.To evaluate the effectiveness of the proposed background subtraction method, some qualitative and quantitative experiments are conducted on two clinical and synthetic low-contrast XCA datasets containing videos from 21 patients. The obtained results are compared with six state-of-the-art methods employing three different assessment criteria. By applying the proposed method to the clinical dataset, the mean values of the global contrast-to-noise ratio, local contrast-to-noise ratio, structural similarity index, and reconstruction error (RE) are obtained as5.976,3.173,0.987, and0.026, respectively. These criteria over the low-contrast synthetic dataset were4.851,2.942,0.958, and0.034, respectively.Significance.The findings demonstrate the superiority of the proposed method in improving the contrast and visibility of coronary vessels, preserving the integrity of the vessel structure, and minimizing REs without imposing excessive computational complexity.

TCT-201 Deep Learning-Based Segmentation of Coronary Arteries and Stenosis Detection in X-Ray Coronary Angiography: From Training to External Validation

TCT-201 Deep Learning-Based Segmentation of Coronary Arteries and Stenosis Detection in X-Ray Coronary Angiography: From Training to External Validation

Online Tree-Structure-Constrained RPCA for Background Subtraction of X-ray Coronary Angiography Images

Background and objectiveBackground subtraction of X-ray coronary angiograms (XCA) can significantly improve the diagnosis and treatment of coronary vessel diseases. The XCA background is complex and dynamic due to structures with different intensities and independent motion patterns, making XCA background subtraction challenging. MethodsThe current work proposes an online tree-structure-constrained robust PCA (OTS-RPCA) method to subtract the XCA background. A morphological closing operation is used as a pre-processing step to remove large-scale structures like the spine, chest and diaphragm. In the following, the XCA sequence is decomposed into three different subspaces: low-rank background, residual dynamic background and vascular foreground. A tree-structured norm is introduced and applied to the vascular submatrix to guarantee the vessel spatial coherency. Moreover, the residual dynamic background is separately extracted to remove noise and motion artifacts from the vascular foreground. The proposed algorithm also employs an adaptive regularization coefficient that tracks the vessel area changes in the XCA frames. ResultsThe proposed method is evaluated on two datasets of real clinical and synthetic low-contrast XCA sequences of 38 patients using the global and local contrast-to-noise ratio (CNR) and structural similarity index (SSIM) criteria. For the real XCA dataset, the average values of global CNR, local CNR and SSIM are 6.27, 3.07 and 0.97, while these values over the synthetic low-contrast dataset are obtained as 5.15, 2.69 and 0.94, respectively. The implemented quantitative and qualitative experiments verify the superiority of the proposed method over seven selected state-of-the-art methods in increasing the coronary vessel contrast and preserving the vessel structure. ConclusionsThe proposed OTS-RPCA background subtraction method accurately subtracts backgrounds from XCA images. Our method might provide the basis for reducing the contrast agent dose and the number of needed injections in coronary interventions.

CAS‐GAN: A Novel Generative Adversarial Network‐Based Architecture for Coronary Artery Segmentation

ABSTRACTAccurate and automated segmentation of x‐ray coronary angiography (XRCA) is crucial for both diagnosing and treating coronary artery diseases. Despite the outstanding results achieved by deep learning (DL)‐based methods in this area, this task remains challenging due to several factors such as poor image quality, the presence of motion artifacts, and inherent variability in vessel structure sizes. To address this challenge, this paper introduces a novel GAN‐based architecture for coronary artery segmentation using XRCA images. This architecture includes a novel U‐Net variant with two types of self‐attention blocks in the generator segment. An auxiliary path connects the attention block and the prediction block to enhance feature generalization, improving vessel structure delineation, especially thin vessels in low‐contrast regions. In parallel, the discriminator network employs a residual CNN with similar attention blocks for balanced performance and improved predictive capabilities. With a streamlined 6.74 M parameters, the resulting architecture surpasses existing methods in efficiency. We assess its efficacy on three coronary artery datasets: our private “CORONAR,” and the public “DCA1” and “CHUAC” datasets. Empirical results showcase our model's superiority across these datasets, utilizing both original and preprocessed images. Notably, our proposed architecture achieves the highest F1‐score of 0.7972 for the CHUAC dataset, 0.8245 for the DCA1 dataset, and 0.8333 for the CORONAR dataset.

Coronary Vessel Segmentation in X-ray Angiography Images Using Edge-Based Tracking Method

Automated extraction of coronary arteries is an essential process in the diagnosis of treatment for coronary artery disease (CAD) with computer assistance. Accurately outlining the coronary artery is difficult when using X-ray coronary angiography (XCA) because of the low signal-to-noise ratio and the presence of interfering background structures. In this paper, a new approach for segmenting vessels in angiograms is presented, specifically designed to tackle the difficulties arising from non-uniform illumination, artifacts, and noise present in angiographic images. The proposed method employs an edge-based tracking tool to generate an initial probability map for segmentation. A segmentation method based on coronary vessel tracking is presented for finding the border and centerline of the vessel. The proposed method is designed based on two main components: preprocessing and tracking. In the preprocessing stage, a guided filter and edge-sharpening algorithms are used to enhance the features of the original image. In the tracking stage, an initial point is selected, and using the Gaussian property, a semi-circle operator is applied to track the line perpendicular to the vessel. The proposed method demonstrated remarkable performance in terms of sensitivity and specificity, achieving values of 86.93 and 99.61, respectively. Additionally, the method achieved an accuracy rate of 97.81. Notably, the proposed method outperformed existing state-of-the-art segmentation methods, as indicated by its higher dice score. These impressive results signify a significant advancement in the field of vessel segmentation, highlighting the effectiveness and superiority of the proposed approach.

Diagnostic performance of 3.0 T unenhanced Dixon water-fat separation coronary MR angiography in patients with low-to-intermediate risk of coronary artery disease

PurposeTo evaluate the diagnostic performance of 3.0 T unenhanced compressed-sensing sensitivity encoding (CS-SENSE) Dixon water-fat separation coronary MR angiography (CMRA) in patients with low-to-intermediate risk of coronary artery disease (CAD) and its ability to grade the severity of CAD based on Coronary Artery Disease Reporting and Data System (CAD-RADS). MethodsA total of 55 patients who was clinically evaluated as low-to-intermediate risk of CAD were finally included to undergo both 3.0 T CS-SENSE water-fat separation CMRA and coronary computed tomography angiography (CCTA), and 11 of them also underwent X-ray coronary angiography (CAG). The severity of coronary artery disease was graded in patients who had completed both CCTA and CMRA examinations by the use of CAD-RADS reports for the patients with stable chest pain, and the diagnostic consistency between the two approaches was evaluated. Diagnostic performance of CMRA was assessed using the combination of CCTA and CAG as the reference standard for excluding or confirming CAD respectively. ResultsThe sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and diagnostic accuracy of 3.0 T unenhanced water-fat separation coronary MRA were 90.0%, 95.0%, 81.8%, 97.4% and 94.0% for a patient-based analysis respectively. In comparison with CCTA, 3.0 T Dixon water-fat separation CMRA demonstrated excellent consistency in grading the severity of coronary heart disease according to CAD-RADS (0.77 for kappa value). ConclusionIn the group of low-to-intermediate probability for CAD, 3.0 T unenhanced CS-SENSE Dixon water-fat separation CMRA can present satisfactory diagnostic performance for the exclusion of CAD with high sensitivity and negative predictive value as well as the evaluation of grading the severity of coronary artery disease.

Co-registered optical coherence tomography and X-ray angiography for the prediction of fractional flow reserve.

Cardiovascular disease (CVD) stands as the leading global cause of mortality, and coronary artery disease (CAD) has the highest prevalence, contributing to 42% of these fatalities. Recognizing the constraints inherent in the anatomical assessment of CAD, Fractional Flow Reserve (FFR) has emerged as a pivotal functional diagnostic metric. Herein, we assess the potential of employing an ensemble approach with deep neural networks (DNN) to predict invasively measured Fractional Flow Reserve (FFR) using raw anatomical data extracted from both optical coherence tomography (OCT) and X-ray coronary angiography (XA). In this study, we used a challenging dataset, with 46% of the lesions falling within the FFR range of 0.75 to 0.85. Despite this complexity, our model achieved an accuracy of 84.3%, demonstrating a sensitivity of 87.5% and a specificity of 81.4%. Our results demonstrate that incorporating both OCT and XA signals, co-registered, as inputs for the DNN model leads to an important increase in overall accuracy.

Dataset for Automatic Region-based Coronary Artery Disease Diagnostics Using X-Ray Angiography Images

X-ray coronary angiography is the most common tool for the diagnosis and treatment of coronary artery disease. It involves the injection of contrast agents into coronary vessels using a catheter to highlight the coronary vessel structure. Typically, multiple 2D X-ray projections are recorded from different angles to improve visualization. Recent advances in the development of deep-learning-based tools promise significant improvement in diagnosing and treating coronary artery disease. However, the limited public availability of annotated X-ray coronary angiography image datasets presents a challenge for objective assessment and comparison of existing tools and the development of novel methods. To address this challenge, we introduce a novel ARCADE dataset with 2 objectives: coronary vessel classification and stenosis detection. Each objective contains 1500 expert-labeled X-ray coronary angiography images representing: i) coronary artery segments; and ii) the locations of stenotic plaques. These datasets will serve as a benchmark for developing new methods and assessing existing approaches for the automated diagnosis and risk assessment of coronary artery disease.

Locating X-Ray Coronary Angiogram Keyframes via Long Short-Term Spatiotemporal Attention With Image-to-Patch Contrastive Learning.

Locating the start, apex and end keyframes of moving contrast agents for keyframe counting in X-ray coronary angiography (XCA) is very important for the diagnosis and treatment of cardiovascular diseases. To locate these keyframes from the class-imbalanced and boundary-agnostic foreground vessel actions that overlap complex backgrounds, we propose long short-term spatiotemporal attention by integrating a convolutional long short-term memory (CLSTM) network into a multiscale Transformer to learn the segment- and sequence-level dependencies in the consecutive-frame-based deep features. Image-to-patch contrastive learning is further embedded between the CLSTM-based long-term spatiotemporal attention and Transformer-based short-term attention modules. The imagewise contrastive module reuses the long-term attention to contrast image-level foreground/background of XCA sequence, while patchwise contrastive projection selects the random patches of backgrounds as convolution kernels to project foreground/background frames into different latent spaces. A new XCA video dataset is collected to evaluate the proposed method. The experimental results show that the proposed method achieves a mAP (mean average precision) of 72.45% and a F-score of 0.8296, considerably outperforming the state-of-the-art methods. The source code is available at https://github.com/Binjie-Qin/STA-IPCon.

Patient-specific in silico 3D coronary model in cardiac catheterisation laboratories.

Coronary artery disease is caused by the buildup of atherosclerotic plaque in the coronary arteries, affecting the blood supply to the heart, one of the leading causes of death around the world. X-ray coronary angiography is the most common procedure for diagnosing coronary artery disease, which uses contrast material and x-rays to observe vascular lesions. With this type of procedure, blood flow in coronary arteries is viewed in real-time, making it possible to detect stenoses precisely and control percutaneous coronary interventions and stent insertions. Angiograms of coronary arteries are used to plan the necessary revascularisation procedures based on the calculation of occlusions and the affected segments. However, their interpretation in cardiac catheterisation laboratories presently relies on sequentially evaluating multiple 2D image projections, which limits measuring lesion severity, identifying the true shape of vessels, and analysing quantitative data. In silico modelling, which involves computational simulations of patient-specific data, can revolutionise interventional cardiology by providing valuable insights and optimising treatment methods. This paper explores the challenges and future directions associated with applying patient-specific in silico models in catheterisation laboratories. We discuss the implications of the lack of patient-specific in silico models and how their absence hinders the ability to accurately predict and assess the behaviour of individual patients during interventional procedures. Then, we introduce the different components of a typical patient-specific in silico model and explore the potential future directions to bridge this gap and promote the development and utilisation of patient-specific in silico models in the catheterisation laboratories.

Simultaneous, free-breathing, non-contrast 3D whole-heart coronary magnetic resonance angiography and vulnerable plaque imaging in patients with suspected acute coronary syndrome

Abstract Background Coronary artery high-risk plaque identified on cardiovascular magnetic resonance (CMR) is associated with future coronary events, independent of coronary artery luminal stenosis. We have recently developed a 3-dimensional whole-heart free-breathing non-contrast CMR sequence that allows for simultaneous high-resolution visualisation of the coronary arteries and vulnerable plaque on co-registered bright and black blood images (iT2prep-BOOST) with 100% respiratory scan efficiency. Objectives To validate iT2prep-BOOST in patients with non-ST-segment elevation myocardial infarction (NSTEMI) against the reference standard imaging modalities of invasive X-ray coronary angiography and intravascular imaging [optical coherence tomography (OCT)/intravascular ultrasound (IVUS)]. Methods 41 consecutive patients with suspected NSTEMI, based upon clinical history, electrocardiographic changes and positive high-sensitivity troponin assays, were recruited into the study. Invasive coronary angiography ± intravascular imaging was used to classify coronary segments into the following categories: normal, non-culprit and culprit segments; stenosed segments as well as segments with vulnerable plaque features (lipid, calcium, fibroatheroma, thin cap fibroatheroma (TCFA), plaque rupture and thrombus). The highest plaque/myocardial signal intensity ratio (PMR) in each coronary segment was analysed on iT2prep-BOOST. Results The mean iT2prep-BOOST acquisition time was 10.8 ± 1.3 minutes. The mean ± standard error of mean (SEM) PMR of culprit segments was significantly higher than non-culprit segments, which was significantly higher than normal segments (1.01 ± 0.05 vs. 0.67 ± 0.01 vs. 0.35 ± 0.01, P<0.001). Coronary segments with lipid, calcium and fibroatheroma had a significantly higher PMR compared to normal coronary segments (P<0.001) but lower than segments with TCFA, plaque rupture and thrombus (P<0.001). There was a progressive increase in PMR with increasing degree of coronary stenosis (P<0.001). Patients with type 2 diabetes, hypertension, hyperlipidaemia and family history of coronary artery disease had a significantly higher PMR on iT2prep-BOOST (P<0.001, P=0.02, P=0.04 and P=0.02 respectively). Finally, PMR was positively correlated with HbA1c, total cholesterol, non-HDL cholesterol, LDL cholesterol and triglyceride levels (P<0.001, P=0.02, P=0.02, P=0.05 and P=0.05 respectively). Conclusions In summary, the proposed iT2prep-BOOST framework has the potential to simultaneously acquire coronary artery angiography and to differentiate normal segments from non-culprit and culprit plaque segments. Furthermore, PMR is associated with both biochemical and patient related risk factors for coronary artery disease (CAD). The long-term prognostic value of PMR needs to be investigated in a longitudinal multi-centre study of patients with suspected CAD.Figure 1Figures 2 and 3

Robust implementation of foreground extraction and vessel segmentation for X-ray coronary angiography image sequence

The extraction of contrast-filled vessels from X-ray coronary angiography (XCA) image sequence has important clinical significance for intuitively diagnosis and therapy. In this study, the XCA image sequence is regarded as a 3D tensor input, the vessel layer is regarded as a sparse tensor, and the background layer is regarded as a low-rank tensor. Using tensor nuclear norm (TNN) minimization, a novel method for vessel layer extraction based on tensor robust principal component analysis (TRPCA) is proposed. Furthermore, considering the irregular movement of vessels and the low-frequency dynamic disturbance of surrounding irrelevant tissues, the total variation (TV) regularized spatial–temporal constraint is introduced to smooth the foreground layer. Subsequently, for vessel layer images with uneven contrast distribution, a two-stage region growing (TSRG) method is utilized for vessel enhancement and segmentation. A global threshold method is used as the preprocessing to obtain main branches, and the Radon-Like features (RLF) filter is used to enhance and connect broken minor segments. The final binary vessel mask is constructed by combining the two intermediate results. The visibility of TV-TRPCA algorithm for foreground extraction is evaluated on clinical XCA image sequences and third-party dataset, which can effectively improve the performance of commonly used vessel segmentation algorithms. Based on TV-TRPCA, the accuracy of TSRG algorithm for vessel segmentation is further evaluated. Both qualitative and quantitative results validate the superiority of the proposed method over existing state-of-the-art approaches.

Segmentation of X-ray coronary angiography with an artificial intelligence deep learning model: Impact in operator visual assessment of coronary stenosis severity.

Visual assessment of the percentage diameter stenosis (%DSVE ) of lesions is essential in coronary angiography (CAG) interpretation. We have previously developed an artificial intelligence (AI) model capable of accurate CAG segmentation. We aim to compare operators' %DSVE in angiography versus AI-segmented images. Quantitative coronary analysis (QCA) %DS (%DSQCA ) was previously performed in our published validation dataset. Operators were asked to estimate %DSVE of lesions in angiography versus AI-segmented images in separate sessions and differences were assessed using angiography %DSQCA as reference. A total of 123 lesions were included. %DSVE was significantly higher in both the angiography (77% ± 20% vs. 56% ± 13%, p < 0.001) and segmentation groups (59% ± 20% vs. 56% ± 13%, p < 0.001), with a much smaller absolute %DS difference in the latter. For lesions with %DSQCA of 50%-70% (60% ± 5%), an even higher discrepancy was found (angiography: 83% ± 13% vs. 60% ± 5%, p < 0.001; segmentation: 63% ± 15% vs. 60% ± 5%, p < 0.001). Similar, less pronounced, findings were observed for %DSQCA < 50% lesions, but not %DSQCA > 70% lesions. Agreement between %DSQCA /%DSVE across %DSQCA strata (<50%, 50%-70%, >70%) was approximately twice in the segmentation group (60.4% vs. 30.1%; p < 0.001). %DSVE inter-operator differences were smaller with segmentation. %DSVE was much less discrepant with segmentation versus angiography. Overestimation of %DSQCA < 70% lesions with angiography was especially common. Segmentation may reduce %DSVE overestimation and thus unwarranted revascularization.

Feasibility study of MEMS-based stenosis detection using a prototypical catheter design with intravascular scanning probes (IVSPs).

X-ray coronary angiography (XRA) is a standard clinical method for diagnosing coronary artery disease (CAD). However, despite continuous improvements in XRA technology, it has limitations that include being visible only in color contrast, and the information it provides on coronary artery plaques is not comprehensive due to its low signal-to-noise ratio and limited resolution. In this study, we propose a novel diagnostic tool, a MEMS-based smart catheter with an intravascular scanning probe (IVSP), to complement XRA and verify its effectiveness and feasibility. The IVSP catheter uses Pt strain gauges embedded on the probe to examine the characteristics of a blood vessel, such as the degree of stenosis and morphological structures of the vessel walls, through physical contact. The feasibility test results showed that the output signals of the IVSP catheter reflected the morphological structure of the phantom glass vessel that mimicked stenosis. In particular, the IVSP catheter successfully assessed the morphology of the stenosis, which was only 17% of the cross-sectional diameter obstructed. In addition, the strain distribution on the probe surface was studied using finite element analysis (FEA), and a correlation between the experimental and FEA results was derived.

Exhaustive matching of 3D/2D coronary artery structure based on imperfect segmentations.

The 3D/2D coronary artery registration technique has been developed for the guidance of the percutaneous coronary intervention. It introduces the absent 3D structural information by fusing the pre-operative computed tomography angiography (CTA) volume with the intra-operative X-ray coronary angiography (XCA) image. To conduct the registration, an accurate matching of the coronary artery structures extracted from the two imaging modalities is an essential step. In this study, we propose an exhaustive matching algorithm to solve this problem. First, by recognizing the fake bifurcations in the XCA image caused by projection and concatenating the fractured centerline fragments, the original XCA topological structure is restored. Then, the vessel segments in the two imaging modalities are removed orderly, which generates all the potential structures to simulate the imperfect segmentation results. Finally, the CTA and XCA structures are compared pairwise, and the matching result is obtained by searching for the structure pair with the minimum similarity score. The experiments were conducted based on a clinical dataset collected from 46 patients and comprising of 240 CTA/XCA data pairs. And the results show that the proposed method is very effective, which achieves an accuracy of 0.960 for recognizing the fake bifurcations in the XCA image and an accuracy of 0.896 for matching the CTA/XCA vascular structures. The proposed exhaustive structure matching algorithm is simple and straightforward without any impractical assumption or time-consuming computations. With this method, the influence of the imperfect segmentations is eliminated and the accurate matching could be achieved efficiently. This lays a good foundation for the subsequent 3D/2D coronary artery registration task.

Assessment of Myocardial Viability and Risk Stratification in Coronary Chronic Total Occlusion: A Qualitative and Quantitative Stress Cardiac MRI Study.

Indicators for assessing myocardial viability and risk stratification in patients with coronary chronic total occlusion (CTO) are still in the research stage. To use stress-MRI to assess myocardial function, blood perfusion, and viability and to explore their relationship with collateral circulation. Prospective. Fifty-one patients with CTO in at least one major artery confirmed by X-ray coronary angiography (male: 46; age 55.2 ± 10.8 years). 3.0T; TurboFlash, balanced steady-state free precession cine, and phase-sensitive inversion recovery sequences. Stress-MRI was used to obtain qualitative and quantitative parameters of segmental myocardium. Myocardial segments supplied by CTO target vessels were grouped according to the degree of collateral circulation assessed by radiographic coronary angiography (no/mild, moderate, or good). Depending on qualitative stress perfusion assessment and late gadolinium enhancement (LGE) extent, segments were also categorized as negative, viable, or trans-infarcted. Independent sample Student's t-test, one-way analysis of variance (ANOVA) test, Mann-Whitney U test, Kruskal-Wallis test, Spearman correlation coefficient (r). P < 0.05 was considered statistically significant. A total of 334 segments were supplied by CTO target vessels. The radial strain (RS), circumferential strain (CS), longitudinal strain (LS) of the negative, viable, and trans-infarcted regions showed a significant and stepwise impairment. Myocardial blood flow at rest was positively correlated with RS, CS, and LS (r = 0.42, 0.43, 0.38, respectively). Among the different collateral circulation, there were no significant differences in RS, CS, LS, and LGE volume (P = 0.788, 0.562, 0.122, 0.170, respectively), and there were also no statistically significant differences in the proportions of negative, viable, and trans-infarcted regions (P = 0.372). Myocardial perfusion obtained by stress-MRI combined with strain and LGE may comprehensively evaluate myocardial function and viability, and has potential to facilitate risk stratification of CTO. 2 TECHNICAL EFFICACY: Stage 1.

Identification of coronary artery stenosis based on hybrid segmentation and feature fusion

Coronary artery disease has been the utmost mutual heart disease in the past decades. Various research is going on to prevent this disease. Obstructive CAD occurs when one or more of the coronary arteries which supply blood to myocardium are narrowed owing to plaque build-up on the arteries’ inner walls, causing stenosis. The fundamental task required for the interpretation of coronary angiography is identification and quantification of severity of stenosis within the coronary circulation. Medical experts use X-ray coronary angiography to identify blood vessel/artery stenosis. Due to the artefact, the image has less clarity and it will be challenging for the medical expert to find the stenosis in the coronary artery. The solution to the problem a computational framework is proposed to segment the artery and spot the location of stenosis in the artery. Here the author presented an automatic method to detect stenosis from the X-ray angiogram image. A unified Computational method of Jerman, Level-set, fine-tuning the artery structure, is developed to extract the segmented artery features and detect the artery’s stenosis. The current experimental outcomes illustrate that this computational method achieves average specificity, sensitivity, Accuracy, precision and F-scores of 95%, 97.5%, 98%, 97.5% and 97.5%, respectively.

Prior skeleton based online deep reinforcement learning for coronary artery centerline extraction.

Coronary centerline extraction is an essential technique for X-ray coronary angiography (XCA) image analysis, which provides qualitative and quantitative guidance for percutaneous coronary intervention (PCI). In this paper, an online deep reinforcement learning method for coronary centerline extraction is proposed based on the prior vascular skeleton. Firstly, with XCA image preprocessing (foreground extraction and vessel segmentation) results, the improved ZhangSuen image thinning algorithm is used to rapidly extract the preliminary vascular skeleton network. On this basis, according to the spatial-temporal and morphological continuity of the angiography image sequence, the connectivity of different branches is determined using k-means clustering, and the vessel segments are then grouped, screened, and reconnected to obtain the aorta and its major branches. Finally, using the previous results as prior information, an online Deep Q-Network (DQN) reinforcement learning method is proposed to optimize each branch simultaneously. It comprehensively considers grayscale intensity and eigenvector continuity to achieve the combination of data-driven and model-driven without pre-training. Experimental results on clinical images and the third-party dataset demonstrate that the proposed method can accurately extract, restructure, and optimize the centerline of XCA images with a higher overall accuracy than the existing state-of-the-art methods.

Coronary X-ray angiography segmentation using Artificial Intelligence: a multicentric validation study of a deep learning model

IntroductionWe previously developed an artificial intelligence (AI) model for automatic coronary angiography (CAG) segmentation, using deep learning. To validate this approach, the model was applied to a new dataset and results are reported.MethodsRetrospective selection of patients undergoing CAG and percutaneous coronary intervention or invasive physiology assessment over a one month period from four centers. A single frame was selected from images containing a lesion with a 50–99% stenosis (visual estimation). Automatic Quantitative Coronary Analysis (QCA) was performed with a validated software. Images were then segmented by the AI model. Lesion diameters, area overlap [based on true positive (TP) and true negative (TN) pixels] and a global segmentation score (GSS – 0 -100 points) - previously developed and published - were measured.Results123 regions of interest from 117 images across 90 patients were included. There were no significant differences between lesion diameter, percentage diameter stenosis and distal border diameter between the original/segmented images. There was a statistically significant albeit minor difference [0,19 mm (0,09–0,28)] regarding proximal border diameter. Overlap accuracy ((TP + TN)/(TP + TN + FP + FN)), sensitivity (TP / (TP + FN)) and Dice Score (2TP / (2TP + FN + FP)) between original/segmented images was 99,9%, 95,1% and 94,8%, respectively. The GSS was 92 (87–96), similar to the previously obtained value in the training dataset.Conclusionthe AI model was capable of accurate CAG segmentation across multiple performance metrics, when applied to a multicentric validation dataset. This paves the way for future research on its clinical uses.

Diagnostic accuracy of whole heart coronary magnetic resonance angiography: a systematic review and meta-analysis

BackgroundThe purpose of this meta-analysis was to comprehensively investigate the diagnostic ability of 1.5 T and 3.0 T whole heart coronary angiography (WHCA) to detect significant coronary artery disease (CAD) on X-ray coronary angiography. MethodsA literature search of electronic databases, including PubMed, Web of Science Core Collection, Cochrane advanced search, and EMBASE, was performed to retrieve and integrate articles showing significant CAD detectability of 1.5 and 3.0 T WHCA. ResultsData from 1899 patients from 34 studies were included in the meta-analysis. 1.5 T WHCA had a summary area under ROC of 0.88 in the patient-based analysis, 0.90 in the vessel-based analysis, and 0.92 in the segment-based analysis. These values for 3.0 T WHCA were 0.94, 0.95, 0.96, respectively. Contrast-enhanced 3.0 T WHCA had significantly higher specificity than non-contrast-enhanced 1.5 T WHCA on a patient-based analysis (0.87, 95% CI 0.80–0.92 vs. 0.74, 95% CI 0.64–0.82, P = 0.02). There were no differences in diagnostic performance on a patient-based analysis by use of vasodilators, beta-blockers or between Asian and Western countries. ConclusionsThe diagnostic performance of WHCA was deemed satisfactory, with contrast-enhanced 3.0 T WHCA exhibiting higher specificity compared to non-contrast-enhanced 1.5 T WHCA in a patient-based analysis. There were no significant differences in diagnostic performance on a patient-based analysis in terms of vasodilator or beta-blocker use, nor between Asian and Western countries. However, further large-scale multicentre studies are crucial for the widespread global adoption of WHCA.