Deep learning segmentation of major vessels in X-ray coronary angiography

LASF: a local adaptive segmentation framework for coronary angiogram segments

Coronary artery disease (CAD) remains the leading cause of death globally, highlighting the critical need for accurate diagnostic tools in medical imaging. Traditional segmentation methods for coronary angiograms often struggle with vessel discontinuity and inaccuracies, impeding effective diagnosis and treatment planning. To address these challenges, we developed the Local Adaptive Segmentation Framework (LASF), enhancing the YOLOv8 architecture with dilation and erosion algorithms to improve the continuity and precision of vascular image segmentation. We further enriched the ARCADE dataset by meticulously annotating both proximal and distal vascular segments, thus broadening the dataset's applicability for training robust segmentation models. Our comparative analyses reveal that LASF outperforms well-known models such as UNet and DeepLabV3Plus, demonstrating superior metrics in precision, recall, and F1-score across various testing scenarios. These enhancements ensure more reliable and accurate segmentation, critical for clinical applications. LASF represents a significant advancement in the segmentation of vascular images within coronary angiograms. By effectively addressing the common issues of vessel discontinuity and segmentation accuracy, LASF stands to improve the clinical management of CAD, offering a promising tool for enhancing diagnostic accuracy and patient outcomes in medical settings.

Deep learning based coronary vessels segmentation in X-ray angiography using temporal information

Invasive coronary angiography (ICA) is the gold standard imaging modality during cardiac interventions. Accurate segmentation of coronary vessels in ICA is required for aiding diagnosis and creating treatment plans. Current automated algorithms for vessel segmentation face task-specific challenges, including motion artifacts and unevenly distributed contrast, as well as the general challenge inherent to X-ray imaging, which is the presence of shadows from overlapping organs in the background. To address these issues, we present Temporal Vessel Segmentation Network (TVS-Net) model that fuses sequential ICA information into a novel densely connected 3D encoder-2D decoder structure with a loss function based on elastic interaction. We develop our model using an ICA dataset comprising 323 samples, split into 173 for training, 82 for validation, and 68 for testing, with a relatively relaxed annotation protocol that produced coarse-grained samples, and achieve 83.4% Dice and 84.3% recall on the test dataset. We additionally perform an external evaluation over 60 images from a local hospital, achieving 78.5% Dice and 82.4% recall and outperforming the state-of-the-art approaches. We also conduct a detailed manual re-segmentation for evaluation only on a subset of the first dataset under strict annotation protocol, achieving a Dice score of 86.2% and recall of 86.3% and surpassing even the coarse-grained gold standard used in training. The results indicate our TVS-Net is effective for multi-frame ICA segmentation, highlights the network's generalizability and robustness across diverse settings, and showcases the feasibility of weak supervision in ICA segmentation.

Lightweight U-Net for Blood Vessels Segmentation in X-Ray Coronary Angiography

Blood vessel segmentation in X-ray coronary angiography (XCA) plays a crucial role in diagnosing cardiovascular diseases, enabling a precise assessment of arterial structures. However, segmentation is challenging due to a low signal-to-noise ratio, interfering background structures, and vessel bifurcations, which hinder the accuracy of deep learning models. Additionally, deep learning models for this task often require high computational resources, limiting their practical application in real-time clinical settings. This study proposes a lightweight variant of the U-Net architecture using a structured kernel pruning strategy inspired by the Lottery Ticket Hypothesis. The pruning method systematically removes entire convolutional filters from each layer based on a global reduction factor, generating compact subnetworks that retain key representational capacity. This results in a significantly smaller model without compromising the segmentation performance. This approach is evaluated on two benchmark datasets, demonstrating consistent improvements in segmentation accuracy compared to the vanilla U-Net. Additionally, model complexity is significantly reduced from 31 M to 1.9 M parameters, improving efficiency while maintaining high segmentation quality.

Transformer and Attention-Based Architectures for Segmentation of Coronary Arterial Walls in Intravascular Ultrasound: A Narrative Review

Background: The leading global cause of death is coronary artery disease (CAD), necessitating early and precise diagnosis. Intravascular ultrasound (IVUS) is a sophisticated imaging technique that provides detailed visualization of coronary arteries. However, the methods for segmenting walls in the IVUS scan into internal wall structures and quantifying plaque are still evolving. This study explores the use of transformers and attention-based models to improve diagnostic accuracy for wall segmentation in IVUS scans. Thus, the objective is to explore the application of transformer models for wall segmentation in IVUS scans to assess their inherent biases in artificial intelligence systems for improving diagnostic accuracy. Methods: By employing the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, we pinpointed and examined the top strategies for coronary wall segmentation using transformer-based techniques, assessing their traits, scientific soundness, and clinical relevancy. Coronary artery wall thickness is determined by using the boundaries (inner: lumen-intima and outer: media-adventitia) through cross-sectional IVUS scans. Additionally, it is the first to investigate biases in deep learning (DL) systems that are associated with IVUS scan wall segmentation. Finally, the study incorporates explainable AI (XAI) concepts into the DL structure for IVUS scan wall segmentation. Findings: Because of its capacity to automatically extract features at numerous scales in encoders, rebuild segmented pictures via decoders, and fuse variations through skip connections, the UNet and transformer-based model stands out as an efficient technique for segmenting coronary walls in IVUS scans. Conclusions: The investigation underscores a deficiency in incentives for embracing XAI and pruned AI (PAI) models, with no UNet systems attaining a bias-free configuration. Shifting from theoretical study to practical usage is crucial to bolstering clinical evaluation and deployment.

Artificial intelligence in interventional radiology: Current concepts and future trends

While artificial intelligence (AI) is already well established in diagnostic radiology, it is beginning to make its mark in interventional radiology. AI has the potential to dramatically change the daily practice of interventional radiology at several levels. In the preoperative setting, recent advances in deep learning models, particularly foundation models, enable effective management of multimodality and increased autonomy through their ability to function minimally without supervision. Multimodality is at the heart of patient-tailored management and in interventional radiology, this translates into the development of innovative models for patient selection and outcome prediction. In the perioperative setting, AI is manifesting itself in applications that assist radiologists in image analysis and real-time decision making, thereby improving the efficiency, accuracy, and safety of interventions. In synergy with advances in robotic technologies, AI is laying the groundwork for an increased autonomy. From a research perspective, the development of artificial health data, such as AI-based data augmentation, offers an innovative solution to this central issue and promises to stimulate research in this area. This review aims to provide the medical community with the most important current and future applications of AI in interventional radiology.

DCA-YOLOv8: A Novel Framework Combined with AICI Loss Function for Coronary Artery Stenosis Detection

Coronary artery stenosis detection remains a challenging task due to the complex vascular structure, poor quality of imaging pictures, poor vessel contouring caused by breathing artifacts and stenotic lesions that often appear in a small region of the image. In order to improve the accuracy and efficiency of detection, a new deep-learning technique based on a coronary artery stenosis detection framework (DCA-YOLOv8) is proposed in this paper. The framework consists of a histogram equalization and canny edge detection preprocessing (HEC) enhancement module, a double coordinate attention (DCA) feature extraction module and an output module that combines a newly designed loss function, named adaptive inner-CIoU (AICI). This new framework is called DCA-YOLOv8. The experimental results show that the DCA-YOLOv8 framework performs better than existing object detection algorithms in coronary artery stenosis detection, with precision, recall, F1-score and mean average precision (mAP) at 96.62%, 95.06%, 95.83% and 97.6%, respectively. In addition, the framework performs better in the classification task, with accuracy at 93.2%, precision at 92.94%, recall at 93.5% and F1-score at 93.22%. Despite the limitations of data volume and labeled data, the proposed framework is valuable in applications for assisting the cardiac team in making decisions by using coronary angiography results.

G2ViT: Graph Neural Network-Guided Vision Transformer Enhanced Network for retinal vessel and coronary angiograph segmentation

Blood vessel segmentation is a crucial stage in extracting morphological characteristics of vessels for the clinical diagnosis of fundus and coronary artery disease. However, traditional convolutional neural networks (CNNs) are confined to learning local vessel features, making it challenging to capture the graph structural information and fail to perceive the global context of vessels. Therefore, we propose a novel graph neural network-guided vision transformer enhanced network (G2ViT) for vessel segmentation. G2ViT skillfully orchestrates the Convolutional Neural Network, Graph Neural Network, and Vision Transformer to enhance comprehension of the entire graphical structure of blood vessels. To achieve deeper insights into the global graph structure and higher-level global context cognizance, we investigate a graph neural network-guided vision transformer module. This module constructs graph-structured representation in an unprecedented manner using the high-level features extracted by CNNs for graph reasoning. To increase the receptive field while ensuring minimal loss of edge information, G2ViT introduces a multi-scale edge feature attention module (MEFA), leveraging dilated convolutions with different dilation rates and the Sobel edge detection algorithm to obtain multi-scale edge information of vessels. To avoid critical information loss during upsampling and downsampling, we design a multi-level feature fusion module (MLF2) to fuse complementary information between coarse and fine features. Experiments on retinal vessel datasets (DRIVE, STARE, CHASE_DB1, and HRF) and coronary angiography datasets (DCA1 and CHUAC) indicate that the G2ViT excels in robustness, generality, and applicability. Furthermore, it has acceptable inference time and computational complexity and presents a new solution for blood vessel segmentation.

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.

Artificial intelligence-based quantitative coronary angiography of major vessels using deep-learning

BACKGROUND

Quantitative coronary angiography (QCA) offers objective and reproducible measures of coronary lesions. However, significant inter- and intra-observer variability and time-consuming processes hinder the practical application of on-site QCA in the current clinical setting. This study proposes a novel method for artificial intelligence-based QCA (AI-QCA) analysis of the major vessels and evaluates its performance.

METHODS

AI-QCA was developed using three deep-learning models trained on 7658 angiographic images from 3129 patients for the precise delineation of lumen boundaries. An automated quantification method, employing refined matching for accurate diameter calculation and iterative updates of diameter trend lines, was embedded in the AI-QCA. A separate dataset of 676 coronary angiography images from 370 patients was retrospectively analyzed to compare AI-QCA with manual QCA performed by expert analysts. A match was considered between manual and AI-QCA lesions when the minimum lumen diameter (MLD) location identified manually coincided with the location identified by AI-QCA. Matched lesions were evaluated in terms of diameter stenosis (DS), MLD, reference lumen diameter (RLD), and lesion length (LL).

RESULTS

AI-QCA exhibited a sensitivity of 89% in lesion detection and strong correlations with manual QCA for DS, MLD, RLD, and LL. Among 995 matched lesions, most cases (892 cases, 80%) exhibited DS differences ≤10%. Multiple lesions of the major vessels were accurately identified and quantitatively analyzed without manual corrections.

CONCLUSION

AI-QCA demonstrates promise as an automated tool for analysis in coronary angiography, offering potential advantages for the quantitative assessment of coronary lesions and clinical decision-making.

Artificial intelligence in interventional radiology: state of the art

Artificial intelligence (AI) has demonstrated great potential in a wide variety of applications in interventional radiology (IR). Support for decision-making and outcome prediction, new functions and improvements in fluoroscopy, ultrasound, computed tomography, and magnetic resonance imaging, specifically in the field of IR, have all been investigated. Furthermore, AI represents a significant boost for fusion imaging and simulated reality, robotics, touchless software interactions, and virtual biopsy. The procedural nature, heterogeneity, and lack of standardisation slow down the process of adoption of AI in IR. Research in AI is in its early stages as current literature is based on pilot or proof of concept studies. The full range of possibilities is yet to be explored.Relevance statement Exploring AI's transformative potential, this article assesses its current applications and challenges in IR, offering insights into decision support and outcome prediction, imaging enhancements, robotics, and touchless interactions, shaping the future of patient care.Key points• AI adoption in IR is more complex compared to diagnostic radiology.• Current literature about AI in IR is in its early stages.• AI has the potential to revolutionise every aspect of IR.

Optimizing ensemble U-Net architectures for robust coronary vessel segmentation in angiographic images

Automated coronary angiography assessment requires precise vessel segmentation, a task complicated by uneven contrast filling and background noise. Our research introduces an ensemble U-Net model, SE-RegUNet, designed to accurately segment coronary vessels using 100 labeled angiographies from angiographic images. SE-RegUNet incorporates RegNet encoders and squeeze-and-excitation blocks to enhance feature extraction. A dual-phase image preprocessing strategy further improves the model's performance, employing unsharp masking and contrast-limited adaptive histogram equalization. Following fivefold cross-validation and Ranger21 optimization, the SE-RegUNet 4GF model emerged as the most effective, evidenced by performance metrics such as a Dice score of 0.72 and an accuracy of 0.97. Its potential for real-world application is highlighted by its ability to process images at 41.6 frames per second. External validation on the DCA1 dataset demonstrated the model's consistent robustness, achieving a Dice score of 0.76 and an accuracy of 0.97. The SE-RegUNet 4GF model's precision in segmenting blood vessels in coronary angiographies showcases its remarkable efficiency and accuracy. However, further development and clinical testing are necessary before it can be routinely implemented in medical practice.

Explaining decisions of a light-weight deep neural network for real-time coronary artery disease classification in magnetic resonance imaging

In certain healthcare settings, such as emergency or critical care units, where quick and accurate real-time analysis and decision-making are required, the healthcare system can leverage the power of artificial intelligence (AI) models to support decision-making and prevent complications. This paper investigates the optimization of healthcare AI models based on time complexity, hyper-parameter tuning, and XAI for a classification task. The paper highlights the significance of a lightweight convolutional neural network (CNN) for analysing and classifying Magnetic Resonance Imaging (MRI) in real-time and is compared with CNN-RandomForest (CNN-RF). The role of hyper-parameter is also examined in finding optimal configurations that enhance the model's performance while efficiently utilizing the limited computational resources. Finally, the benefits of incorporating the XAI technique (e.g. GradCAM and Layer-wise Relevance Propagation) in providing transparency and interpretable explanations of AI model predictions, fostering trust, and error/bias detection are explored. Our inference time on a MacBook laptop for 323 test images of size 100x100 is only 2.6 sec, which is merely 8 milliseconds per image while providing comparable classification accuracy with the ensemble model of CNN-RF classifiers. Using the proposed model, clinicians/cardiologists can achieve accurate and reliable results while ensuring patients' safety and answering questions imposed by the General Data Protection Regulation (GDPR). The proposed investigative study will advance the understanding and acceptance of AI systems in connected healthcare settings.

Validation of artificial intelligence-based quantitative coronary angiography

Background

Coronary angiography is fundamental for the diagnosis and treatment of coronary artery disease. Manual quantitative coronary angiography (QCA) is accurate and reproducible; however, it is time-consuming and labor-intensive. However, recent advancements in artificial intelligence (AI) have enabled automated and rapid analysis of medical images, addressing the need for real-time quantitative coronary analysis.

Aims

This study aimed to evaluate the accuracy of AI-based QCA (AI-QCA) compared with that via manual QCA and clinician acceptance.

Methods

This retrospective, single-center study was conducted in two phases. Phase 1 was a pilot study comparing AI-QCA with manual QCA and visual estimation. It involved 15 patients who underwent coronary angiography at Seoul National University Bundang Hospital between September 2011 and July 2021. Phase 2 included a larger cohort of 762 patients, with 1002 coronary angiograms analyzed between May 2020 and April 2021.

Results

In phase 1, AI-QCA and manual QCA consistency varied among the observers, with AI-QCA showing superior consistency compared with visual estimation. However, a strong correlation between AI-QCA and manual-QCA was found in phase 2. AI-QCA accurately identified and quantitatively analyzed multiple lesions in the major vessels, providing results comparable with those of manual QCA.

Conclusions

AI-QCA demonstrated high concordance with manual QCA, offering real-time analysis and reduced workload. Therefore, AI-QCA has the potential to be a valuable tool for diagnosing and treating coronary artery disease, necessitating further studies for clinical validation.

Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography

BACKGROUND

Invasive coronary angiography (ICA) is a primary imaging modality that visualizes the lumen area of coronary arteries for diagnosis and interventional guidance. In the current practice of quantitative coronary analysis (QCA), semi-automatic segmentation tools require labor-intensive and time-consuming manual correction, limiting their application in the catheterization room.

PURPOSE

This study aims to propose rank-based selective ensemble methods that improve the segmentation performance and reduce morphological errors that limit fully automated quantification of coronary artery using deep-learning segmentation of ICA.

METHODS

Two selective ensemble methods proposed in this work integrated the weighted ensemble approach with per-image quality estimation. The segmentation outcomes from five base models with different loss functions were ranked either by mask morphology or estimated dice similarity coefficient (DSC). The final output was determined by imposing different weights according to the ranks. The ranking criteria based on mask morphology were formulated from empirical insight to avoid frequent types of segmentation errors (MSEN), while the estimation of DSCs was performed by comparing the pseudo-ground truth generated from a meta-learner (ESEN). Five-fold cross-validation was performed with the internal dataset of 7426 coronary angiograms from 2924 patients, and prediction model was externally validated with 556 images of 226 patients.

RESULTS

The selective ensemble methods improved the segmentation performance with DSCs up to 93.07% and provided a better delineation of coronary lesion with local DSCs of up to 93.93%, outperforming all individual models. Proposed methods also minimized the chances of mask disconnection in the most narrowed regions to 2.10%. The robustness of the proposed methods was also evident in the external validation. Inference time for major vessel segmentation was approximately one-sixth of a second.

CONCLUSION

Proposed methods successfully reduced morphological errors in the predicted masks and were able to enhance the robustness of the automatic segmentation. The results suggest better applicability of real-time QCA-based diagnostic methods in routine clinical settings.

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

BACKGROUND

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.

METHODS

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.

RESULTS

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.

CONCLUSION

%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.

CathAI: fully automated coronary angiography interpretation and stenosis estimation

Coronary angiography is the primary procedure for diagnosis and management decisions in coronary artery disease (CAD), but ad-hoc visual assessment of angiograms has high variability. Here we report a fully automated approach to interpret angiographic coronary artery stenosis from standard coronary angiograms. Using 13,843 angiographic studies from 11,972 adult patients at University of California, San Francisco (UCSF), between April 1, 2008 and December 31, 2019, we train neural networks to accomplish four sequential necessary tasks for automatic coronary artery stenosis localization and estimation. Algorithms are internally validated against criterion-standard labels for each task in hold-out test datasets. Algorithms are then externally validated in real-world angiograms from the University of Ottawa Heart Institute (UOHI) and also retrained using quantitative coronary angiography (QCA) data from the Montreal Heart Institute (MHI) core lab. The CathAI system achieves state-of-the-art performance across all tasks on unselected, real-world angiograms. Positive predictive value, sensitivity and F1 score are all ≥90% to identify projection angle and ≥93% for left/right coronary artery angiogram detection. To predict obstructive CAD stenosis (≥70%), CathAI exhibits an AUC of 0.862 (95% CI: 0.843-0.880). In UOHI external validation, CathAI achieves AUC 0.869 (95% CI: 0.830-0.907) to predict obstructive CAD. In the MHI QCA dataset, CathAI achieves an AUC of 0.775 (95%. CI: 0.594-0.955) after retraining. In conclusion, multiple purpose-built neural networks can function in sequence to accomplish automated analysis of real-world angiograms, which could increase standardization and reproducibility in angiographic coronary stenosis assessment.

The Application of Deep Learning for the Segmentation and Classification of Coronary Arteries

In recent years, the prevalence of coronary artery disease (CAD) has become one of the leading causes of death around the world. Accurate stenosis detection of coronary arteries is crucial for timely treatment. Cardiologists use visual estimations when reading coronary angiography images to diagnose stenosis. As a result, they face various challenges which include high workloads, long processing times and human error. Computer-aided segmentation and classification of coronary arteries, as to whether stenosis is present or not, significantly reduces the workload of cardiologists and human errors caused by manual processes. Moreover, deep learning techniques have been shown to aid medical experts in diagnosing diseases using biomedical imaging. Thus, this study proposes the use of automatic segmentation of coronary arteries using U-Net, ResUNet-a, UNet++, models and classification using DenseNet201, EfficientNet-B0, Mobilenet-v2, ResNet101 and Xception models. In the case of segmentation, the comparative analysis of the three models has shown that U-Net achieved the highest score with a 0.8467 Dice score and 0.7454 Jaccard Index in comparison with UNet++ and ResUnet-a. Evaluation of the classification model's performances has shown that DenseNet201 performed better than other pretrained models with 0.9000 accuracy, 0.9833 specificity, 0.9556 PPV, 0.7746 Cohen's Kappa and 0.9694 Area Under the Curve (AUC).

Perceptual Data Augmentation for Biomedical Coronary Vessel Segmentation

Sufficient annotated data is critical to the success of deep learning methods. Annotating for vessel segmentation in X-ray coronary angiograms is extremely difficult because of the small and complex structures to be processed. Although unsupervised domain adaptation methods can be utilized to alleviate the annotation burden by using data in other domains, e.g., eye fundus images, these methods cannot perform well due to the characteristic of medical images. Data augmentation can help improve the similarity of source domain and target domain in unsupervised domain adaptation tasks. Existing data augmentation methods play a limited role in improving domain adaptation performance, especially for special medical image segmentation tasks. In this paper, we propose an effective perceptual data augmentation method to improve the similarity between eye fundus images and coronary angiograms by synthesizing virtual samples. Auto Foreground Augment method is designed to search for geometric transformations that improve the similarity between foreground vessels of eye fundus images and coronary angiograms. The Haar Wavelet-Based Perceptual Similarity Index is utilized to guide the synthesis of virtual samples in foreground and background mixup. Extensive experiments show that our data augmentation method can synthesize high-quality virtual samples and thus improve the domain adaptation performance. To our best knowledge, this is the first work to apply perceptual data augmentation to vessel segmentation in coronary angiograms.

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

INTRODUCTION

We 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.

METHODS

Retrospective 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.

RESULTS

123 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.

CONCLUSION

the 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.

A benchmark study of convolutional neural networks in fully automatic segmentation of aortic root

Recent clinical studies have suggested that introducing 3D patient-specific aortic root models into the pre-operative assessment procedure of transcatheter aortic valve replacement (TAVR) would reduce the incident rate of peri-operative complications. Tradition manual segmentation is labor-intensive and low-efficient, which cannot meet the clinical demands of processing large data volumes. Recent developments in machine learning provided a viable way for accurate and efficient medical image segmentation for 3D patient-specific models automatically. This study quantitively evaluated the auto segmentation quality and efficiency of the four popular segmentation-dedicated three-dimensional (3D) convolutional neural network (CNN) architectures, including 3D UNet, VNet, 3D Res-UNet and SegResNet. All the CNNs were implemented in PyTorch platform, and low-dose CTA image sets of 98 anonymized patients were retrospectively selected from the database for training and testing of the CNNs. The results showed that despite all four 3D CNNs having similar recall, Dice similarity coefficient (DSC), and Jaccard index on the segmentation of the aortic root, the Hausdorff distance (HD) of the segmentation results from 3D Res-UNet is 8.56 ± 2.28, which is only 9.8% higher than that of VNet, but 25.5% and 86.4% lower than that of 3D UNet and SegResNet, respectively. In addition, 3D Res-UNet and VNet also performed better in the 3D deviation location of interest analysis focusing on the aortic valve and the bottom of the aortic root. Although 3D Res-UNet and VNet are evenly matched in the aspect of classical segmentation quality evaluation metrics and 3D deviation location of interest analysis, 3D Res-UNet is the most efficient CNN architecture with an average segmentation time of 0.10 ± 0.04 s, which is 91.2%, 95.3% and 64.3% faster than 3D UNet, VNet and SegResNet, respectively. The results from this study suggested that 3D Res-UNet is a suitable candidate for accurate and fast automatic aortic root segmentation for pre-operative assessment of TAVR.

Progressive Perception Learning for Main Coronary Segmentation in X-Ray Angiography

Main coronary segmentation from the X-ray angiography images is important for the computer-aided diagnosis and treatment of coronary disease. However, it confronts the challenge at three different image granularities (the semantic, surrounding, and local levels). The challenge includes the semantic confusion between the main and collateral vessels, low contrast between the foreground vessel and background surroundings, and local ambiguity near the vessel boundaries. The traditional hand-crafted feature-based methods may be insufficient because they may lack the semantic relationship information and may not distinguish the main and collateral vessels. The existing deep learning-based methods seem to have issues due to the deficiency in the long-distance semantic relationship capture, the foreground and background interference adaptability, and the boundary detail information preservation. To solve the main coronary segmentation challenge, we propose the progressive perception learning (PPL) framework to inspect these three different image granularities. Specifically, the PPL contains the context, interference, and boundary perception modules. The context perception is designed to focus on the main coronary vessel based on the semantic dependence capture among different coronary segments. The interference perception is designed to purify the feature maps based on the foreground vessel enhancement and background artifact suppression. The boundary perception is designed to highlight the boundary details based on boundary feature extraction through the intersection between the foreground and background predictions. Extensive experiments on 1085 subjects show that the PPL is effective (e.g., the overall Dice is greater than 95%), and superior to thirteen state-of-the-art coronary segmentation methods.

Deep learning-based end-to-end automated stenosis classification and localization on catheter coronary angiography

Background

Automatic coronary angiography (CAG) assessment may help in faster screening and diagnosis of stenosis in patients with atherosclerotic disease. We aimed to provide an end-to-end workflow that separates cases with normal or mild stenoses from those with higher stenosis severities to facilitate safety screening of a large volume of the CAG images.

Methods

A deep learning-based end-to-end workflow was employed as follows: (1) Candidate frame selection from CAG videograms with Convolutional Neural Network (CNN) + Long Short Term Memory (LSTM) network, (2) Stenosis classification with Inception-v3 using 2 or 3 categories (<25%, >25%, and/or total occlusion) with and without redundancy training, and (3) Stenosis localization with two methods of class activation map (CAM) and anchor-based feature pyramid network (FPN). Overall 13,744 frames from 230 studies were used for the stenosis classification training and fourfold cross-validation for image-, artery-, and per-patient-level. For the stenosis localization training and fourfold cross-validation, 690 images with > 25% stenosis were used.

Results

Our model achieved an accuracy of 0.85, sensitivity of 0.96, and AUC of 0.86 in per-patient level stenosis classification. Redundancy training was effective to improve classification performance. Stenosis position localization was adequate with better quantitative results in anchor-based FPN model, achieving global-sensitivity for left coronary artery (LCA) and right coronary artery (RCA) of 0.68 and 0.70.

Conclusion

We demonstrated a fully automatic end-to-end deep learning-based workflow that eliminates the vessel extraction and segmentation step in coronary artery stenosis classification and localization on CAG images. This tool may be useful to facilitate safety screening in high-volume centers and in clinical trial settings.

Accuracy of Artificial Intelligence-Based Automated Quantitative Coronary Angiography Compared to Intravascular Ultrasound: Retrospective Cohort Study. (Preprint)

BACKGROUND

An accurate quantitative analysis of coronary artery stenotic lesions is essential to make optimal clinical decisions. Recent advances in computer vision and machine learning technology have enabled the automated analysis of coronary angiography.

OBJECTIVE

The aim of this paper is to validate the performance of artificial intelligence-based quantitative coronary angiography (AI-QCA) in comparison with that of intravascular ultrasound (IVUS).

METHODS

This retrospective study included patients who underwent IVUS-guided coronary intervention at a single tertiary center in Korea. Proximal and distal reference areas, minimal luminal area, percent plaque burden, and lesion length were measured by AI-QCA and human experts using IVUS. First, fully automated QCA analysis was compared with IVUS analysis. Next, we adjusted the proximal and distal margins of AI-QCA to avoid geographic mismatch. Scatter plots, Pearson correlation coefficients, and Bland-Altman were used to analyze the data.

RESULTS

A total of 54 significant lesions were analyzed in 47 patients. The proximal and distal reference areas, as well as the minimal luminal area, showed moderate to strong correlation between the 2 modalities (correlation coefficients of 0.57, 0.80, and 0.52, respectively; P<.001). The correlation was weaker for percent area stenosis and lesion length, although statistically significant (correlation coefficients of 0.29 and 0.33, respectively). AI-QCA tended to measure reference vessel areas smaller and lesion lengths shorter than IVUS did. Systemic proportional bias was not observed in Bland-Altman plots. The biggest cause of bias originated from the geographic mismatch of AI-QCA with IVUS. Discrepancies in the proximal or distal lesion margins were observed between the 2 modalities, which were more frequent at the distal margins. After the adjustment of proximal or distal margins, there was a stronger correlation of proximal and distal reference areas between AI-QCA and IVUS (correlation coefficients of 0.70 and 0.83, respectively).

CONCLUSIONS

AI-QCA showed a moderate to strong correlation compared with IVUS in analyzing coronary lesions with significant stenosis. The main discrepancy was in the perception of the distal margins by AI-QCA, and the correction of margins improved the correlation coefficients. We believe that this novel tool could provide confidence to treating physicians and help in making optimal clinical decisions.

Application of machine learning and complex network measures to an EEG dataset from ayahuasca experiments

Ayahuasca is a blend of Amazonian plants that has been used for traditional medicine by the inhabitants of this region for hundreds of years. Furthermore, this plant has been demonstrated to be a viable therapy for a variety of neurological and mental diseases. EEG experiments have found specific brain regions that changed significantly due to ayahuasca. Here, we used an EEG dataset to investigate the ability to automatically detect changes in brain activity using machine learning and complex networks. Machine learning was applied at three different levels of data abstraction: (A) the raw EEG time series, (B) the correlation of the EEG time series, and (C) the complex network measures calculated from (B). Further, at the abstraction level of (C), we developed new measures of complex networks relating to community detection. As a result, the machine learning method was able to automatically detect changes in brain activity, with case (B) showing the highest accuracy (92%), followed by (A) (88%) and (C) (83%), indicating that connectivity changes between brain regions are more important for the detection of ayahuasca. The most activated areas were the frontal and temporal lobe, which is consistent with the literature. F3 and PO4 were the most important brain connections, a significant new discovery for psychedelic literature. This connection may point to a cognitive process akin to face recognition in individuals during ayahuasca-mediated visual hallucinations. Furthermore, closeness centrality and assortativity were the most important complex network measures. These two measures are also associated with diseases such as Alzheimer's disease, indicating a possible therapeutic mechanism. Moreover, the new measures were crucial to the predictive model and suggested larger brain communities associated with the use of ayahuasca. This suggests that the dissemination of information in functional brain networks is slower when this drug is present. Overall, our methodology was able to automatically detect changes in brain activity during ayahuasca consumption and interpret how these psychedelics alter brain networks, as well as provide insights into their mechanisms of action.

Deep learning applications in coronary anatomy imaging: a systematic review and meta-analysis

Background

The application of deep learning on medical imaging is growing in prevalence in the recent literature. One of the most studied areas is coronary artery disease (CAD). Imaging of coronary artery anatomy is fundamental, which has led to a high number of publications describing a variety of techniques. The aim of this systematic review is to review the evidence behind the accuracy of deep learning applications in coronary anatomy imaging.

Methods

The search for the relevant studies, which applied deep learning on coronary anatomy imaging, was performed in a systematic approach on MEDLINE and EMBASE databases, followed by reviewing of abstracts and full texts. The data from the final studies was retrieved using data extraction forms. A meta-analysis was performed on a subgroup of studies, which looked at fractional flow reserve (FFR) prediction. Heterogeneity was tested using tau², I² and Q tests. Finally, a risk of bias was performed using Quality Assessment of Diagnostic Accuracy Studies (QUADAS) approach.

Results

A total of 81 studies met the inclusion criteria. The most common imaging modality was coronary computed tomography angiography (CCTA) (58%) and the most common deep learning method was convolutional neural network (CNN) (52%). The majority of studies demonstrated good performance metrics. The most common outputs were focused on coronary artery segmentation, clinical outcome prediction, coronary calcium quantification and FFR prediction, and most studies reported area under the curve (AUC) of ≥80%. The pooled diagnostic odds ratio (DOR) derived from 8 studies looking at FFR prediction using CCTA was 12.5 using the Mantel-Haenszel (MH) method. There was no significant heterogeneity amongst studies according to Q test (P=0.2496).

Conclusions

Deep learning has been used in many applications on coronary anatomy imaging, most of which are yet to be externally validated and prepared for clinical use. The performance of deep learning, especially CNN models, proved to be powerful and some applications have already translated into medical practice, such as computed tomography (CT)-FFR. These applications have the potential to translate technology into better care of CAD patients.

A Novel Method for Improving the Accuracy of MR-derived Patient-specific Vascular Models using X-ray Angiography

MR imaging, a noninvasive radiation-free imaging modality commonly used during clinical follow up, has been widely utilized to reconstruct realistic 3D vascular models for patient-specific analysis. In recent work, we used patient-specific hemodynamic analysis of the circle of Willis to noninvasively assess stroke risk in pediatric Moyamoya disease (MMD)-a progressive steno-occlusive cerebrovascular disorder that leads to recurrent stroke. The objective was to identify vascular regions with critically high wall shear rate (WSR) that signifies elevated stroke risk. However, sources of error such as insufficient resolution of MR images can negatively impact vascular model accuracy, especially in areas of severe pathological narrowing, and thus diminish clinical relevance of simulation results, as local hemodynamics are sensitive to vessel geometry. To improve the accuracy of MR-derived vascular models, we have developed a novel method for adjusting model vessel geometry utilizing 2D X-ray angiography (XA), which is considered the gold standard for clinically assessing vessel caliber. In this workflow, "virtual angiographies" (VAs) of 3D MR-derived vascular models are conducted, producing 2D projections that are compared with corresponding XA images to guide the local adjustment of modeled vessels. This VA-comparison-adjustment loop is iterated until the two agree, as confirmed by an expert neuroradiologist. Using this method, we generated models of the circle of Willis of two patients with a history of unilateral stroke. Blood flow simulations were performed using a Navier-Stokes solver within an isogeometric analysis framework, and WSR distributions were quantified. Results for one patient show as much as 45% underestimation of local WSR in the stenotic left anterior cerebral artery (LACA), and up to a 56% underestimation in the right anterior cerebral artery when using the initial MR-derived model compared to the XA-adjusted model. To evaluate whether XA-based adjustment improves model accuracy, vessel cross-sectional areas of the pre- and post-adjustment models were compared to those seen in 3D CTA images of the same patient. CTA has superior resolution and signal-to-noise ratio compared to MR imaging but is not commonly used in the clinic due to radiation exposure concerns, especially in pediatric patients. While the vessels in the initial model had normalized root mean squared deviations (NRMSDs) ranging from 26% to 182% and 31% to 69% in two patients with respect to CTA, the adjusted vessel NRMSDs were comparatively smaller (32% to 53% and 11% to 42%). In the mildly stenotic LACA of patient 1, the NRMSDs for the pre- and post-adjusted models were 49% and 32%, respectively. These findings suggest that our XA-based adjustment method can considerably improve the accuracy of vascular models, and thus, stroke-risk prediction. An accurate, individualized assessment of stroke risk would be of substantial help in guiding the timing of preventive surgical interventions in pediatric MMD patients.

DS6, Deformation-Aware Semi-Supervised Learning: Application to Small Vessel Segmentation with Noisy Training Data

Blood vessels of the brain provide the human brain with the required nutrients and oxygen. As a vulnerable part of the cerebral blood supply, pathology of small vessels can cause serious problems such as Cerebral Small Vessel Diseases (CSVD). It has also been shown that CSVD is related to neurodegeneration, such as Alzheimer’s disease. With the advancement of 7 Tesla MRI systems, higher spatial image resolution can be achieved, enabling the depiction of very small vessels in the brain. Non-Deep Learning-based approaches for vessel segmentation, e.g., Frangi’s vessel enhancement with subsequent thresholding, are capable of segmenting medium to large vessels but often fail to segment small vessels. The sensitivity of these methods to small vessels can be increased by extensive parameter tuning or by manual corrections, albeit making them time-consuming, laborious, and not feasible for larger datasets. This paper proposes a deep learning architecture to automatically segment small vessels in 7 Tesla 3D Time-of-Flight (ToF) Magnetic Resonance Angiography (MRA) data. The algorithm was trained and evaluated on a small imperfect semi-automatically segmented dataset of only 11 subjects; using six for training, two for validation, and three for testing. The deep learning model based on U-Net Multi-Scale Supervision was trained using the training subset and was made equivariant to elastic deformations in a self-supervised manner using deformation-aware learning to improve the generalisation performance. The proposed technique was evaluated quantitatively and qualitatively against the test set and achieved a Dice score of 80.44 ± 0.83. Furthermore, the result of the proposed method was compared against a selected manually segmented region (62.07 resultant Dice) and has shown a considerable improvement (18.98%) with deformation-aware learning.

Detecting Coronary Artery Disease from Computed Tomography Images Using a Deep Learning Technique

In recent times, coronary artery disease (CAD) has become one of the leading causes of morbidity and mortality across the globe. Diagnosing the presence and severity of CAD in individuals is essential for choosing the best course of treatment. Presently, computed tomography (CT) provides high spatial resolution images of the heart and coronary arteries in a short period. On the other hand, there are many challenges in analyzing cardiac CT scans for signs of CAD. Research studies apply machine learning (ML) for high accuracy and consistent performance to overcome the limitations. It allows excellent visualization of the coronary arteries with high spatial resolution. Convolutional neural networks (CNN) are widely applied in medical image processing to identify diseases. However, there is a demand for efficient feature extraction to enhance the performance of ML techniques. The feature extraction process is one of the factors in improving ML techniques’ efficiency. Thus, the study intends to develop a method to detect CAD from CT angiography images. It proposes a feature extraction method and a CNN model for detecting the CAD in minimum time with optimal accuracy. Two datasets are utilized to evaluate the performance of the proposed model. The present work is unique in applying a feature extraction model with CNN for CAD detection. The experimental analysis shows that the proposed method achieves 99.2% and 98.73% prediction accuracy, with F1 scores of 98.95 and 98.82 for benchmark datasets. In addition, the outcome suggests that the proposed CNN model achieves the area under the receiver operating characteristic and precision-recall curve of 0.92 and 0.96, 0.91 and 0.90 for datasets 1 and 2, respectively. The findings highlight that the performance of the proposed feature extraction and CNN model is superior to the existing models.

Initial experience of a deep learning application for the differentiation of Kikuchi-Fujimoto's disease from tuberculous lymphadenitis on neck CECT

Neck contrast-enhanced CT (CECT) is a routine tool used to evaluate patients with cervical lymphadenopathy. This study aimed to evaluate the ability of convolutional neural networks (CNNs) to classify Kikuchi-Fujimoto's disease (KD) and cervical tuberculous lymphadenitis (CTL) on neck CECT in patients with benign cervical lymphadenopathy. A retrospective analysis of consecutive patients with biopsy-confirmed KD and CTL in a single center, from January 2012 to June 2020 was performed. This study included 198 patients of whom 125 patients (mean age, 25.1 years ± 8.7, 31 men) had KD and 73 patients (mean age, 41.0 years ± 16.8, 34 men) had CTL. A neuroradiologist manually labelled the enlarged lymph nodes on the CECT images. Using these labels as the reference standard, a CNNs was developed to classify the findings as KD or CTL. The CT images were divided into training (70%), validation (10%), and test (20%) subsets. As a supervised augmentation method, the Cut&Remain method was applied to improve performance. The best area under the receiver operating characteristic curve for classifying KD from CTL for the test set was 0.91. This study shows that the differentiation of KD from CTL on neck CECT using a CNNs is feasible with high diagnostic performance.

Deep learning-based fully automatic segmentation of the maxillary sinus on cone-beam computed tomographic images

The detection of maxillary sinus wall is important in dental fields such as implant surgery, tooth extraction, and odontogenic disease diagnosis. The accurate segmentation of the maxillary sinus is required as a cornerstone for diagnosis and treatment planning. This study proposes a deep learning-based method for fully automatic segmentation of the maxillary sinus, including clear or hazy states, on cone-beam computed tomographic (CBCT) images. A model for segmentation of the maxillary sinuses was developed using U-Net, a convolutional neural network, and a total of 19,350 CBCT images were used from 90 maxillary sinuses (34 clear sinuses, 56 hazy sinuses). Post-processing to eliminate prediction errors of the U-Net segmentation results increased the accuracy. The average prediction results of U-Net were a dice similarity coefficient (DSC) of 0.9090 ± 0.1921 and a Hausdorff distance (HD) of 2.7013 ± 4.6154. After post-processing, the average results improved to a DSC of 0.9099 ± 0.1914 and an HD of 2.1470 ± 2.2790. The proposed deep learning model with post-processing showed good performance for clear and hazy maxillary sinus segmentation. This model has the potential to help dental clinicians with maxillary sinus segmentation, yielding equivalent accuracy in a variety of cases.

Classification of Left and Right Coronary Arteries in Coronary Angiographies Using Deep Learning

Multi-frame X-ray images (videos) of the coronary arteries obtained using coronary angiography (CAG) provide detailed information about the anatomy and blood flow in the coronary arteries and play a pivotal role in diagnosing and treating ischemic heart disease. Deep learning has the potential to quickly and accurately quantify narrowings and blockages of the arteries from CAG videos. A CAG consists of videos acquired separately for the left coronary artery and the right coronary artery (LCA and RCA, respectively). The pathology for LCA and RCA is typically only reported for the entire CAG, and not for the individual videos. However, training of stenosis quantification models is difficult when the RCA and LCA information of the videos are unknown. Here, we present a deep learning-based approach for classifying LCA and RCA in CAG videos. Our approach enables linkage of videos with the reported pathological findings. We manually labeled 3545 and 520 videos (approximately seven videos per CAG) to enable training and testing of the models, respectively. We obtained F1 scores of 0.99 on the test set for LCA and RCA classification LCA and RCA classification on the test set. The classification performance was further investigated with extensive experiments across different model architectures (R(2+1)D, X3D, and MVIT), model input sizes, data augmentations, and the number of videos used for training. Our results showed that CAG videos could be accurately curated using deep learning, which is an essential preprocessing step for a downstream application in diagnostics of coronary artery disease.

Research Progress of Machine Learning and Deep Learning in Intelligent Diagnosis of the Coronary Atherosclerotic Heart Disease

The coronary atherosclerotic heart disease is a common cardiovascular disease with high morbidity, disability, and societal burden. Early, precise, and comprehensive diagnosis of the coronary atherosclerotic heart disease is of great significance. The rise of artificial intelligence technologies, represented by machine learning and deep learning, provides new methods to address the above issues. In recent years, artificial intelligence has achieved an extraordinary progress in multiple aspects of coronary atherosclerotic heart disease diagnosis, including the construction of intelligent diagnostic models based on artificial intelligence algorithms, applications of artificial intelligence algorithms in coronary angiography, coronary CT angiography, intravascular imaging, cardiac magnetic resonance, and functional parameters. This paper presents a comprehensive review of the technical background and current state of research on the application of artificial intelligence in the diagnosis of the coronary atherosclerotic heart disease and analyzes recent challenges and perspectives in this field.

Prime Time for Artificial Intelligence in Interventional Radiology

Machine learning techniques, also known as artificial intelligence (AI), is about to dramatically change workflow and diagnostic capabilities in diagnostic radiology. The interest in AI in Interventional Radiology is rapidly gathering pace. With this early interest in AI in procedural medicine, IR could lead the way to AI research and clinical applications for all interventional medical fields. This review will address an overview of machine learning, radiomics and AI in the field of interventional radiology, enumerating the possible applications of such techniques, while also describing techniques to overcome the challenge of limited data when applying these techniques in interventional radiology. Lastly, this review will address common errors in research in this field and suggest pathways for those interested in learning and becoming involved about AI.

Study of Vertebral Artery Dissection by Ultrasound Superb Microvascular Imaging Based on Deep Neural Network Model

To assess the diagnostic value of ultrasound Superb Microvascular Imaging (SMI) and versus Doppler ultrasound (TCD) for microvascular structure and aerodynamic changes in vertebral artery dissection (VAD). In this paper, we firstly simulate the process of clinician recognition of vertebral artery dissection and propose a combination of a priori shape information of vertebral artery dissection and deep folly convolutional networks (DFCNs) for IVUS. In this paper, 15 patients with vertebral artery dissection confirmed by SMI, digital subtraction angiography (DSA), or computed tomography angiography (CTA) from 2020 to 2021 were selected, and the true and false lumen diameters, peak systolic flow velocity (PSV), end-diastolic flow velocity (EDV) and PSV, EDV, and plasticity index (PI) of the intracranial vertebral artery were measured. Among the 15 patients with VAD, 4 (27%, 4/15) had trauma-induced secondary vertebral artery entrapment and 11 (73%, 11/15) had spontaneous entrapment without a clear cause. According to the structural characteristics of the vessels, there were 11 cases (73%, 11/15) of double-lumen, intramural hematoma, and vertebral artery dissection aneurysm, and 11 cases (73%, 11/15) of V1 segment. SMI not only provides an objective assessment of the vascular morphology and aerodynamic changes in VAD but also, in combination with TCD, can further determine the opening of the traffic branches in the posterior circulation, providing reliable information for the early diagnosis and treatment of microvascular dissection of the vertebral artery.

Prime Time for Artificial Intelligence in Interventional Radiology

Machine learning techniques, also known as artificial intelligence (AI), is about to dramatically change workflow and diagnostic capabilities in diagnostic radiology. The interest in AI in Interventional Radiology is rapidly gathering pace. With this early interest in AI in procedural medicine, IR could lead the way to AI research and clinical applications for all interventional medical fields. This review will address an overview of machine learning, radiomics and AI in the field of interventional radiology, enumerating the possible applications of such techniques, while also describing techniques to overcome the challenge of limited data when applying these techniques in interventional radiology. Lastly, this review will address common errors in research in this field and suggest pathways for those interested in learning and becoming involved about AI.

Quantitative coronary angiography versus intravascular ultrasound guidance for drug-eluting stent implantation (GUIDE-DES): study protocol for a randomised controlled non-inferiority trial

INTRODUCTION

Angiography remains the gold standard for guiding percutaneous coronary intervention (PCI). However, it is prone to suboptimal stent results due to the visual estimation of coronary measurements. Although the benefit of intravascular ultrasound (IVUS)-guided PCI is becoming increasingly recognised, IVUS is not affordable for many catheterisation laboratories. Thus, a more practical and standardised angiography-based approach is necessary to support stent implantation.

METHODS AND ANALYSIS

The Quantitative Coronary Angiography versus Intravascular Ultrasound Guidance for Drug-Eluting Stent Implantation trial is a randomised, investigator-initiated, multicentre, open-label, non-inferiority trial comparing the quantitative coronary angiography (QCA)-guided PCI strategy with IVUS-guided PCI in all-comer patients with significant coronary artery disease. A novel, standardised, QCA-based PCI protocol for the QCA-guided group will be provided to all participating operators, while the PCI optimisation criteria will be predefined for both strategies. A total of 1528 patients will be randomised to either group at a 1:1 ratio. The primary endpoint is the 12-month cumulative incidence of target-lesion failure defined as a composite of cardiac death, target-vessel myocardial infarction or ischaemia-driven target-lesion revascularisation. Clinical follow-up assessments are scheduled at 1, 6 and 12 months for all patients enrolled in the study.

ETHICS AND DISSEMINATION

Ethics approval for this study was granted by the Institutional Review Board of Asan Medical Center (no. 2017-0060). Informed consent will be obtained from every participant. The study findings will be published in peer-reviewed journal articles and disseminated through public forums and academic conference presentations. Cost-effectiveness and secondary imaging analyses will be shared in secondary papers.

TRIAL REGISTRATION NUMBER

NCT02978456.

Implementing Machine Learning in Interventional Cardiology: The Benefits Are Worth the Trouble

Driven by recent innovations and technological progress, the increasing quality and amount of biomedical data coupled with the advances in computing power allowed for much progress in artificial intelligence (AI) approaches for health and biomedical research. In interventional cardiology, the hope is for AI to provide automated analysis and deeper interpretation of data from electrocardiography, computed tomography, magnetic resonance imaging, and electronic health records, among others. Furthermore, high-performance predictive models supporting decision-making hold the potential to improve safety, diagnostic and prognostic prediction in patients undergoing interventional cardiology procedures. These applications include robotic-assisted percutaneous coronary intervention procedures and automatic assessment of coronary stenosis during diagnostic coronary angiograms. Machine learning (ML) has been used in these innovations that have improved the field of interventional cardiology, and more recently, deep Learning (DL) has emerged as one of the most successful branches of ML in many applications. It remains to be seen if DL approaches will have a major impact on current and future practice. DL-based predictive systems also have several limitations, including lack of interpretability and lack of generalizability due to cohort heterogeneity and low sample sizes. There are also challenges for the clinical implementation of these systems, such as ethical limits and data privacy. This review is intended to bring the attention of health practitioners and interventional cardiologists to the broad and helpful applications of ML and DL algorithms to date in the field. Their implementation challenges in daily practice and future applications in the field of interventional cardiology are also discussed.

Plaque erosion and acute coronary syndromes: phenotype, molecular characteristics and future directions

Although acute coronary syndromes (ACS) remain one of the leading causes of death, the clinical presentation has changed over the past three decades with a decline in the incidence of ST-segment elevation myocardial infarction (STEMI) and an increase in non-STEMI. This epidemiological shift is at least partially explained by changes in plaque biology as a result of the widespread use of statins. Historically, atherosclerotic plaque rupture of the fibrous cap was thought to be the main culprit in ACS. However, plaque erosion with an intact fibrous cap is now responsible for about one third of ACS and up to two thirds of non-STEMI. Two major research approaches have enabled a better understanding of plaque erosion. First, advanced intravascular imaging has provided opportunities for an 'optical biopsy' and extensive phenotyping of coronary plaques in living patients. Second, basic science experiments have shed light on the unique molecular characteristics of plaque erosion. At present, patients with ACS are still uniformly treated with coronary stents irrespective of the underlying pathobiology. However, pilot studies indicate that patients with plaque erosion might be treated conservatively without coronary stenting. In this Review, we discuss the patient phenotype and the molecular characteristics in atherosclerotic plaque erosion and provide our vision for a potential major shift in the management of patients with plaque erosion.

Coronary Angiography Print: An Automated Accurate Hidden Biometric Method Based on Filtered Local Binary Pattern Using Coronary Angiography Images

Background and purpose: Biometrics is a commonly studied research issue for both biomedical engineering and forensics sciences. Besides, the purpose of hidden biometrics is to discover hidden biometrics features. This work aims to demonstrate the biometric identification ability of coronary angiography images. Material and method: A new coronary angiography images database was collected to develop an automatic identification model. The used database was collected from 51 subjects and contains 2156 images. The developed model has to preprocess; feature generation using local binary pattern; feature selection with neighborhood component analysis; and classification phases. In the preprocessing phase; image rotations; median filter; Gaussian filter; and speckle noise addition functions have been used to generate filtered images. A multileveled extractor is presented using local binary pattern and maximum pooling together. The generated features are fed to neighborhood component analysis and the selected features are classified using k nearest neighbor classifier. Results: The presented angiography image identification method attained 99.86% classification accuracy on the collected database. Conclusions: The obtained findings demonstrate that the angiography images can be utilized as biometric identification. Moreover, we discover a new hidden biometric feature using coronary angiography images and name of this hidden biometric is coronary angiography print.

A Simple Method for Automatic 3D Reconstruction of Coronary Arteries From X-Ray Angiography

Automatic three-dimensional (3-D) reconstruction of the coronary arteries (CA) from medical imaging modalities is still a challenging task. In this study, we present a deep learning-based method of automatic identification of the two ends of the vessel from X-ray coronary angiography (XCA). We also present a method of using template models of CA in matching the two-dimensional segmented vessels from two different angles of XCA. For the deep learning network, we used a U-net consisting of an encoder (Resnet) and a decoder. The two ends of the vessel were manually labeled to generate training images. The network was trained with 2,342, 1,907, and 1,523 labeled images for the left anterior descending (LAD), left circumflex (LCX), and right coronary artery (RCA), respectively. For template models of CA, ten reconstructed 3-D models were averaged for each artery. The accuracy of correspondence using template models was compared with that of manual matching. The deep learning network pointed the proximal region (20% of the total length) in 97.7, 97.5, and 96.4% of 315, 201, and 167 test images for LAD, LCX, and RCA, respectively. The success rates in pointing the distal region were 94.9, 89.8, and 94.6%, respectively. The average distances between the projected points from the reconstructed 3-D model to the detector and the points on the segmented vessels were not statistically different between the template and manual matchings. The computed FFR was not significantly different between the two matchings either. Deep learning methodology is feasible in identifying the two ends of the vessel in XCA, and the accuracy of using template models is comparable to that of manual correspondence in matching the segmented vessels from two angles.

AngioNet: a convolutional neural network for vessel segmentation in X-ray angiography

Coronary Artery Disease (CAD) is commonly diagnosed using X-ray angiography, in which images are taken as radio-opaque dye is flushed through the coronary vessels to visualize the severity of vessel narrowing, or stenosis. Cardiologists typically use visual estimation to approximate the percent diameter reduction of the stenosis, and this directs therapies like stent placement. A fully automatic method to segment the vessels would eliminate potential subjectivity and provide a quantitative and systematic measurement of diameter reduction. Here, we have designed a convolutional neural network, AngioNet, for vessel segmentation in X-ray angiography images. The main innovation in this network is the introduction of an Angiographic Processing Network (APN) which significantly improves segmentation performance on multiple network backbones, with the best performance using Deeplabv3+ (Dice score 0.864, pixel accuracy 0.983, sensitivity 0.918, specificity 0.987). The purpose of the APN is to create an end-to-end pipeline for image pre-processing and segmentation, learning the best possible pre-processing filters to improve segmentation. We have also demonstrated the interchangeability of our network in measuring vessel diameter with Quantitative Coronary Angiography. Our results indicate that AngioNet is a powerful tool for automatic angiographic vessel segmentation that could facilitate systematic anatomical assessment of coronary stenosis in the clinical workflow.

Applications of artificial intelligence in cardiovascular imaging

Research into artificial intelligence (AI) has made tremendous progress over the past decade. In particular, the AI-powered analysis of images and signals has reached human-level performance in many applications owing to the efficiency of modern machine learning methods, in particular deep learning using convolutional neural networks. Research into the application of AI to medical imaging is now very active, especially in the field of cardiovascular imaging because of the challenges associated with acquiring and analysing images of this dynamic organ. In this Review, we discuss the clinical questions in cardiovascular imaging that AI can be used to address and the principal methodological AI approaches that have been developed to solve the related image analysis problems. Some approaches are purely data-driven and rely mainly on statistical associations, whereas others integrate anatomical and physiological information through additional statistical, geometric and biophysical models of the human heart. In a structured manner, we provide representative examples of each of these approaches, with particular attention to the underlying computational imaging challenges. Finally, we discuss the remaining limitations of AI approaches in cardiovascular imaging (such as generalizability and explainability) and how they can be overcome.

Prognosis of Coronary Atherosclerotic Burden in Non-Ischemic Dilated Cardiomyopathies

Background: Atherosclerosis is associated with a worse prognosis in many diseases such as ischemic cardiomyopathy, but its impact in non-ischemic dilated cardiomyopathy (dCMP) is lesser known. Our aim was to study the prognostic impact of coronary atherosclerotic burden (CAB) in patients with dCMP. Methods: Consecutive patients with dCMP and left ventricular (LV) dysfunction diagnosed by concomitant analysis of invasive coronary angiography (ICA) and CMR imaging were identified from registry-database. CAB was measured by Gensini score. The primary composite endpoint was the occurrence of major adverse cardiovascular events (MACE) defined as cardiovascular (CV) mortality, non-fatal MI and unplanned myocardial revascularization. The results of 139 patients constituting the prospective study population (mean age 59.4 ± 14.7 years old, 74% male), average LV ejection fraction was 31.1 ± 11.02%, median Gensini score was 0 (0–3), and mid-wall late gadolinium enhancement (LGE) was the most frequent LGE pattern (42%). Over a median follow-up of 2.8 years, 9% of patients presented MACE. Patients with MACE had significantly higher CAB compared to those who were free of events (0 (0–3) vs. 3.75 (2–15), p < 0.0001). CAB remained the significant predictor of MACE on multivariate logistic analysis (OR: 1.12, CI: 1.01–1.23, p = 0.02). Conclusion: High CAB may be a new prognostic factor in dCMP patients.

Tissue clearing and imaging methods for cardiovascular development

Tissue imaging in 3D using visible light is limited and various clearing techniques were developed to increase imaging depth, but none provides universal solution for all tissues at all developmental stages. In this review, we focus on different tissue clearing methods for 3D imaging of heart and vasculature, based on chemical composition (solvent-based, simple immersion, hyperhydration, and hydrogel embedding techniques). We discuss in detail compatibility of various tissue clearing techniques with visualization methods: fluorescence preservation, immunohistochemistry, nuclear staining, and fluorescent dyes vascular perfusion. We also discuss myocardium visualization using autofluorescence, tissue shrinking, and expansion. Then we overview imaging methods used to study cardiovascular system and live imaging. We discuss heart and vessels segmentation methods and image analysis. The review covers the whole process of cardiovascular system 3D imaging, starting from tissue clearing and its compatibility with various visualization methods to the types of imaging methods and resulting image analysis.

Real-time coronary artery stenosis detection based on modern neural networks

Invasive coronary angiography remains the gold standard for diagnosing coronary artery disease, which may be complicated by both, patient-specific anatomy and image quality. Deep learning techniques aimed at detecting coronary artery stenoses may facilitate the diagnosis. However, previous studies have failed to achieve superior accuracy and performance for real-time labeling. Our study is aimed at confirming the feasibility of real-time coronary artery stenosis detection using deep learning methods. To reach this goal we trained and tested eight promising detectors based on different neural network architectures (MobileNet, ResNet-50, ResNet-101, Inception ResNet, NASNet) using clinical angiography data of 100 patients. Three neural networks have demonstrated superior results. The network based on Faster-RCNN Inception ResNet V2 is the most accurate and it achieved the mean Average Precision of 0.95, F1-score 0.96 and the slowest prediction rate of 3 fps on the validation subset. The relatively lightweight SSD MobileNet V2 network proved itself as the fastest one with a low mAP of 0.83, F1-score of 0.80 and a mean prediction rate of 38 fps. The model based on RFCN ResNet-101 V2 has demonstrated an optimal accuracy-to-speed ratio. Its mAP makes up 0.94, F1-score 0.96 while the prediction speed is 10 fps. The resultant performance-accuracy balance of the modern neural networks has confirmed the feasibility of real-time coronary artery stenosis detection supporting the decision-making process of the Heart Team interpreting coronary angiography findings.

Dynamic Chest X-Ray Using a Flat-Panel Detector System: Technique and Applications

Dynamic X-ray (DXR) is a functional imaging technique that uses sequential images obtained by a flat-panel detector (FPD). This article aims to describe the mechanism of DXR and the analysis methods used as well as review the clinical evidence for its use. DXR analyzes dynamic changes on the basis of X-ray translucency and can be used for analysis of diaphragmatic kinetics, ventilation, and lung perfusion. It offers many advantages such as a high temporal resolution and flexibility in body positioning. Many clinical studies have reported the feasibility of DXR and its characteristic findings in pulmonary diseases. DXR may serve as an alternative to pulmonary function tests in patients requiring contact inhibition, including patients with suspected or confirmed coronavirus disease 2019 or other infectious diseases. Thus, DXR has a great potential to play an important role in the clinical setting. Further investigations are needed to utilize DXR more effectively and to establish it as a valuable diagnostic tool.

Clinical applications of artificial intelligence in cardiology on the verge of the decade

Artificial intelligence (AI) has been hailed as the fourth industrial revolution and its influence on people's lives is increasing. The research on AI applications in medicine is progressing rapidly. This revolution shows promise for more precise diagnoses, streamlined workflows, increased accessibility to healthcare services and new insights into ever-growing population-wide datasets. While some applications have already found their way into contemporary patient care, we are still in the early days of the AI-era in medicine. Despite the popularity of these new technologies, many practitioners lack an understanding of AI methods, their benefits, and pitfalls. This review aims to provide information about the general concepts of machine learning (ML) with special focus on the applications of such techniques in cardiovascular medicine. It also sets out the current trends in research related to medical applications of AI. Along with new possibilities, new threats arise - acknowledging and understanding them is as important as understanding the ML methodology itself. Therefore, attention is also paid to the current opinions and guidelines regarding the validation and safety of AI-powered tools.