Artificial Intelligence in Intracoronary Imaging

Deep learning model DeepNeo predicts neointimal tissue characterization using optical coherence tomography

BACKGROUND

Accurate interpretation of optical coherence tomography (OCT) pullbacks is critical for assessing vascular healing after percutaneous coronary intervention (PCI). Manual analysis is time-consuming and subjective, highlighting the need for a fully automated solution.

METHODS

In this study, 1148 frames from 92 OCT pullbacks were manually annotated to classify neointima as homogeneous, heterogeneous, neoatherosclerosis, or not analyzable on a quadrant level. Stent and lumen contours were annotated in 305 frames for segmentation of the lumen, stent struts, and neointima. We used these annotations to train a deep learning algorithm called DeepNeo. Performance was further evaluated in an animal model (male New Zealand White Rabbits) of neoatherosclerosis using co-registered histopathology images as the gold standard.

RESULTS

DeepNeo demonstrates a strong classification performance for neointimal tissue, achieving an overall accuracy of 75%, which is comparable to manual classification accuracy by two clinical experts (75% and 71%). In the animal model of neoatherosclerosis, DeepNeo achieves an accuracy of 87% when compared with histopathological findings. For segmentation tasks in human pullbacks, the algorithm shows strong performance with mean Dice overlap scores of 0.99 for the lumen, 0.66 for stent struts, and 0.86 for neointima.

CONCLUSIONS

To the best of our knowledge, DeepNeo is the first deep learning algorithm enabling fully automated segmentation and classification of neointimal tissue with performance comparable to human experts. It could standardize vascular healing assessments after PCI, support therapeutic decisions, and improve risk detection for cardiac events.

Optical coherence tomography to guide percutaneous coronary intervention

Percutaneous coronary intervention (PCI) has been most commonly guided by coronary angiography. However, to overcome the inherent limitations of conventional coronary angiography, there has been an increasing interest in the adjunctive tools of intracoronary imaging for PCI guidance. Recently, optical coherence tomography (OCT) has garnered substantial attention as a valid intravascular imaging modality for guiding PCI. However, despite the unparalleled high-resolution imaging capability of OCT, which offers detailed anatomical information on coronary lesion morphology and PCI optimisation, its broad application in routine PCI practice remains limited. Several factors may have curtailed the widespread adoption of OCT-guided PCI in daily practice, including the transitional challenge from intravascular ultrasound (IVUS), the experienced skill required for image acquisition and interpretation, the lack of a uniform algorithm for OCT-guided PCI optimisation, and the limited clinical evidence. Herein, we provide an in-depth review of OCT-guided PCI, involving the technical aspects, optimal strategies for OCT-guided PCI, and the wide application of OCT-guided PCI in various anatomical subsets. Special attention is given to the latest clinical evidence from recent randomised clinical trials with respect to OCT-guided PCI.

Use of Artificial Intelligence Including Multimodal Systems to Improve the Management of Cardiovascular Disease

The rising prevalence of cardiovascular disease presents an escalating challenge for current health services, which are grappling with increasing demands. Innovative changes are imperative to sustain the delivery of high-quality patient care. Recent technologic advances have resulted in the emergence of artificial intelligence as a viable solution. Advanced algorithms are now capable of performing complex analysis of large volumes of data rapidly and with exceptional accuracy. Multimodality artificial intelligence systems handle a diverse range of data including images, text, video, and audio. Compared with single-modality systems, multimodal artificial intelligence systems appear to hold promise for enhancing overall performance and enabling smoother integration into existing workflows. Such systems can empower physicians with clinical decision support and enhanced efficiency. Owing to the complexity of the field, however, truly multimodal artificial intelligence is still scarce in the management of cardiovascular disease. This article aims to cover current research, emerging trends, and the future utilisation of artificial intelligence in the management of cardiovascular disease, with a focus on multimodality systems.

Innovations in Intracoronary Imaging: Present Clinical Practices and Future Outlooks

Engaging intracoronary imaging (IC) techniques such as intravascular ultrasound or optical coherence tomography enables the precise description of vessel architecture. These imaging modalities have well-established roles in providing guidance and optimizing percutaneous coronary intervention (PCI) outcomes. Furthermore, IC is increasingly recognized for its diagnostic capabilities, as it has the unique capacity to reveal vessel wall characteristics that may not be apparent through angiography alone. This manuscript thoroughly reviews the contemporary landscape of IC in clinical practice. Focused on current methodologies, the review explores the utility and advancements in IC techniques. Emphasizing their role in clarifying coronary pathophysiology, guiding PCI, and optimizing patient outcomes, the manuscript critically evaluates the strengths and limitations of each modality. Additionally, the integration of IC into routine clinical workflows and its impact on decision-making processes are discussed. By synthesizing the latest evidence, this review provides valuable insights for clinicians, researchers, and healthcare professionals involved in the dynamic field of interventional cardiology.

Deep Learning Paradigm and Its Bias for Coronary Artery Wall Segmentation in Intravascular Ultrasound Scans: A Closer Look

BACKGROUND AND MOTIVATION

Coronary artery disease (CAD) has the highest mortality rate; therefore, its diagnosis is vital. Intravascular ultrasound (IVUS) is a high-resolution imaging solution that can image coronary arteries, but the diagnosis software via wall segmentation and quantification has been evolving. In this study, a deep learning (DL) paradigm was explored along with its bias.

METHODS

Using a PRISMA model, 145 best UNet-based and non-UNet-based methods for wall segmentation were selected and analyzed for their characteristics and scientific and clinical validation. This study computed the coronary wall thickness by estimating the inner and outer borders of the coronary artery IVUS cross-sectional scans. Further, the review explored the bias in the DL system for the first time when it comes to wall segmentation in IVUS scans. Three bias methods, namely (i) ranking, (ii) radial, and (iii) regional area, were applied and compared using a Venn diagram. Finally, the study presented explainable AI (XAI) paradigms in the DL framework.

FINDINGS AND CONCLUSIONS

UNet provides a powerful paradigm for the segmentation of coronary walls in IVUS scans due to its ability to extract automated features at different scales in encoders, reconstruct the segmented image using decoders, and embed the variants in skip connections. Most of the research was hampered by a lack of motivation for XAI and pruned AI (PAI) models. None of the UNet models met the criteria for bias-free design. For clinical assessment and settings, it is necessary to move from a paper-to-practice approach.

Evaluation of a Rabbit Model of Vascular Stent Healing: Application of Optical Coherence Tomography

Percutaneous coronary intervention (PCI) is a management strategy for symptomatic obstructive coronary artery disease (CAD). Despite advancements, in-stent restenosis (ISR) still imparts a 1-2% annual rate of repeat revascularization-a focus of ongoing translational research. Optical coherence tomography (OCT) provides high resolution virtual histology of stents. Our study evaluates the use of OCT for virtual histological assessment of stent healing in a rabbit aorta model, enabling complete assessment of intraluminal healing throughout the stent. ISR varies based on intra-stent location, stent length, and stent type in a rabbit model-important considerations for translational experimental design. Atherosclerosis leads to more prominent ISR proliferation independent of stent-related factors. The rabbit stent model mirrors clinical observations, while OCT-based virtual histology demonstrates utility for pre-clinical stent assessment. Pre-clinical models should incorporate clinical and stent factors as feasible to maximize translation to clinical practice.

Accuracy of IVUS-Based Machine Learning Segmentation Assessment of Coronary Artery Dimensions and Balloon Sizing

Background

Accurate intravascular ultrasound (IVUS) measurements are important in IVUS-guided percutaneous coronary intervention optimization by choosing the appropriate device size and confirming stent expansion.

Objectives

The purpose of this study was to assess the accuracy of machine learning (ML) automatic segmentation of coronary artery vessel and lumen dimensions and balloon sizing.

Methods

Using expert analysis as the gold standard, ML segmentation of 60 MHz IVUS images was developed using 8,076 IVUS cross-sectional images from 234 patients, which were randomly split into training (83%) and validation (17%) data sets. The performance of ML segmentation was then evaluated using an independent test data set (437 images from 92 patients). The endpoints were the agreement rate between ML vs experts' measurements for appropriate balloon size selection, and lumen and acute stent areas. Appropriate balloon size was determined by rounding down from the mean vessel diameter or rounding up from the mean lumen diameter to the next balloon size. The difference of lumen area ≥0.5 mm2 was considered as clinically significant.

Results

ML model segmentation correlated well with experts' segmentation for training data set with a correlation coefficient of 0.992 and 0.993 for lumen and vessel areas, respectively. The agreement rate in lumen and acute stent areas was 85.5% and 97.0%, respectively. The agreement rate for appropriate balloon size selection was 70.6% by vessel diameter only and 92.4% by adding lumen diameter.

Conclusions

ML model IVUS segmentation measurements were well-correlated with those of experts and selected an appropriate balloon size in more than 90% of images.

Artificial Intelligence in Cardiology: An Australian Perspective

Significant advances have been made in artificial intelligence technology in recent years. Many health care applications have been investigated to assist clinicians and the technology is close to being integrated into routine clinical practice. The high prevalence of cardiac disease in Australia places overwhelming demands on the existing health care system, challenging its capacity to provide quality patient care. Artificial intelligence has emerged as a promising solution. This discussion paper provides an Australian perspective on the current state of artificial intelligence in cardiology, including the benefits and challenges of implementation. This paper highlights some current artificial intelligence applications in cardiology, while also detailing challenges such as data privacy, ethical considerations, and integration within existing health infrastructures. Overall, this paper aims to provide insights into the potential benefits of artificial intelligence in cardiology, while also acknowledging the barriers that need to be addressed to ensure safe and effective implementation into an Australian health system.

Morphologies and composition changes in nonculprit subclinical atherosclerosis in diabetic versus nondiabetic patients with acute coronary syndrome who underwent long-term statin therapy

Although patients are undergoing similar lipid-lowering therapy (LLT) with statins, the outcomes of coronary plaque in diabetic mellitus (DM) and non-DM patients are different. Clinical data of 239 patients in this observational study with acute coronary syndrome was from our previous randomized trial were analyzed at 3 years, and 114 of them underwent OCT detection at baseline and the 1-year follow-up were re-anlayzed by a novel artificial intelligence imaging software for nonculprit subclinical atherosclerosis (nCSA). Normalized total atheroma volume changes (ΔTAVn) of nCSA were the primary endpoint. Plaque progression (PP) was defined as any increase in ΔTAVn. DM patients showed more PP in nCSA (ΔTAVn; 7.41 (- 2.82, 11.85) mm³ vs. - 1.12 (- 10.67, 9.15) mm³, p = 0.009) with similar reduction of low-density lipoprotein cholesterol (LDL-C) from baseline to 1-year. The main reason is that the lipid component in nCSA increases in DM patients and non-significantly decreases in non-DM patients, which leads to a significantly higher lipid TAVn (24.26 (15.05, 40.12) mm³ vs. 16.03 (6.98, 26.54) mm³, p = 0.004) in the DM group than in the non-DM group at the 1-year follow-up. DM was an independent predictor of PP in multivariate logistic regression analysis (OR = 2.731, 95% CI 1.160-6.428, p = 0.021). Major adverse cardiac events (MACEs) related to nCSA at 3 years were higher in the DM group than in the non-DM group (9.5% vs. 1.7%, p = 0.027). Despite a comparable reduction in LDL-C levels after LLT, more PP with an increase in the lipid component of nCSA and a higher incidence of MACEs at the 3-year follow-up was observed in DM patients.Trial registration: ClinicalTrials.gov. identifier: NCT02140801.

Intravascular Imaging During Percutaneous Coronary Intervention: JACC State-of-the-Art Review

Coronary angiography has historically served as the gold standard for diagnosis of coronary artery disease and guidance of percutaneous coronary intervention (PCI). Adjunctive use of contemporary intravascular imaging (IVI) technologies has emerged as a complement to conventional angiography-to further characterize plaque morphology and optimize the performance of PCI. IVI has utility for preintervention lesion and vessel assessment, periprocedural guidance of lesion preparation and stent deployment, and postintervention assessment of optimal endpoints and exclusion of complications. The role of IVI in reducing major adverse cardiac events in complex lesion subsets is emerging, and further studies evaluating broader use are underway or in development. This paper provides an overview of currently available IVI technologies, reviews data supporting their utilization for PCI guidance and optimization across a variety of lesion subsets, proposes best practices, and advocates for broader use of these technologies as a part of contemporary practice.

Vulnerable Atherosclerotic Plaque: Is There a Molecular Signature?

Atherosclerosis and its clinical manifestations, coronary and cerebral artery diseases, are the most common cause of death worldwide. The main pathophysiological mechanism for these complications is the rupture of vulnerable atherosclerotic plaques and subsequent thrombosis. Pathological studies of the vulnerable lesions showed that more frequently, plaques rich in lipids and with a high level of inflammation, responsible for mild or moderate stenosis, are more prone to rupture, leading to acute events. Identifying the vulnerable plaques helps to stratify patients at risk of developing acute vascular events. Traditional imaging methods based on plaque appearance and size are not reliable in prediction the risk of rupture. Intravascular imaging is a novel technique able to identify vulnerable lesions, but it is invasive and an operator-dependent technique. This review aims to summarize the current data from literature regarding the main biomarkers involved in the attempt to diagnose vulnerable atherosclerotic lesions. These biomarkers could be the base for risk stratification and development of the new therapeutic drugs in the treatment of patients with vulnerable atherosclerotic plaques.

Rapid lipid-laden plaque identification in intravascular optical coherence tomography imaging based on time-series deep learning

SIGNIFICANCE

Coronary heart disease has the highest rate of death and morbidity in the Western world. Atherosclerosis is an asymptomatic condition that is considered the primary cause of cardiovascular diseases. The accumulation of low-density lipoprotein triggers an inflammatory process in focal areas of arteries, which leads to the formation of plaques. Lipid-laden plaques containing a necrotic core may eventually rupture, causing heart attack and stroke. Lately, intravascular optical coherence tomography (IV-OCT) imaging has been used for plaque assessment. The interpretation of the IV-OCT images is performed visually, which is burdensome and requires highly trained physicians for accurate plaque identification.

AIM

Our study aims to provide high throughput lipid-laden plaque identification that can assist in vivo imaging by offering faster screening and guided decision making during percutaneous coronary interventions.

APPROACH

An A-line-wise classification methodology based on time-series deep learning is presented to fulfill this aim. The classifier was trained and validated with a database consisting of IV-OCT images of 98 artery sections. A trained physician with expertise in the analysis of IV-OCT imaging provided the visual evaluation of the database that was used as ground truth for training and validation.

RESULTS

This method showed an accuracy, sensitivity, and specificity of 89.6%, 83.6%, and 91.1%, respectively. This deep learning methodology has the potential to increase the speed of lipid-laden plaques identification to provide a high throughput of more than 100 B-scans/s.

CONCLUSIONS

These encouraging results suggest that this method will allow for high throughput video-rate atherosclerotic plaque assessment through automated tissue characterization for in vivo imaging by providing faster screening to assist in guided decision making during percutaneous coronary interventions.

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.

Current State and Future Perspectives of Artificial Intelligence for Automated Coronary Angiography Imaging Analysis in Patients with Ischemic Heart Disease

PURPOSE OF REVIEW

Artificial intelligence (AI) applications in (interventional) cardiology continue to emerge. This review summarizes the current state and future perspectives of AI for automated imaging analysis in invasive coronary angiography (ICA).

RECENT FINDINGS

Recently, 12 studies on AI for automated imaging analysis In ICA have been published. In these studies, machine learning (ML) models have been developed for frame selection, segmentation, lesion assessment, and functional assessment of coronary flow. These ML models have been developed on monocenter datasets (in range 31-14,509 patients) and showed moderate to good performance. However, only three ML models were externally validated. Given the current pace of AI developments for the analysis of ICA, less-invasive, objective, and automated diagnosis of CAD can be expected in the near future. Further research on this technology in the catheterization laboratory may assist and improve treatment allocation, risk stratification, and cath lab logistics by integrating ICA analysis with other clinical characteristics.

Structure attention co-training neural network for neovascularization segmentation in intravascular optical coherence tomography

PURPOSE

To development and validate a Neovascularization (NV) segmentation model in intravascular optical coherence tomography (IVOCT) through deep learning methods.

METHODS AND MATERIALS

A total of 1950 2D slices of 70 IVOCT pullbacks were used in our study. We randomly selected 1273 2D slices from 44 patients as the training set, 379 2D slices from 11 patients as the validation set, and 298 2D slices from the last 15 patients as the testing set. Automatic NV segmentation is quite challenging, as it must address issues of speckle noise, shadow artifacts, high distribution variation, etc. To meet these challenges, a new deep learning-based segmentation method is developed based on a co-training architecture with an integrated structural attention mechanism. Co-training is developed to exploit the features of three consecutive slices. The structural attention mechanism comprises spatial and channel attention modules and is integrated into the co-training architecture at each up-sampling step. A cascaded fixed network is further incorporated to achieve segmentation at the image level in a coarse-to-fine manner.

RESULTS

Extensive experiments were performed involving a comparison with several state-of-the-art deep learning-based segmentation methods. Moreover, the consistency of the results with those of manual segmentation was also investigated. Our proposed NV automatic segmentation method achieved the highest correlation with the manual delineation by interventional cardiologists (the Pearson correlation coefficient is 0.825).

CONCLUSION

In this work, we proposed a co-training architecture with an integrated structural attention mechanism to segment NV in IVOCT images. The good agreement between our segmentation results and manual segmentation indicates that the proposed method has great potential for application in the clinical investigation of NV-related plaque diagnosis and treatment. This article is protected by copyright. All rights reserved.

The evolving role of artificial intelligence in cardiac image analysis

Research in artificial intelligence (AI) have progressed over the last decade. The field of cardiac imaging has seen significant developments using newly developed deep learning methods for automated image analysis and AI tools for disease detection and prognostication. This review article is aimed at those without special background in AI. We review AI concepts and we survey the growing contemporary applications of AI for image analysis in echocardiography, nuclear cardiology, cardiac computed tomography, cardiac magnetic resonance, and invasive angiography.

Artificial intelligence to generate medical images: augmenting the cardiologist's visual clinical workflow

Artificial intelligence (AI) offers great promise in cardiology, and medicine broadly, for its ability to tirelessly integrate vast amounts of data. Applications in medical imaging are particularly attractive, as images are a powerful means to convey rich information and are extensively utilized in cardiology practice. Departing from other AI approaches in cardiology focused on task automation and pattern recognition, we describe a digital health platform to synthesize enhanced, yet familiar, clinical images to augment the cardiologist's visual clinical workflow. In this article, we present the framework, technical fundamentals, and functional applications of the methodology, especially as it pertains to intravascular imaging. A conditional generative adversarial network was trained with annotated images of atherosclerotic diseased arteries to generate synthetic optical coherence tomography and intravascular ultrasound images on the basis of specified plaque morphology. Systems leveraging this unique and flexible construct, whereby a pair of neural networks is competitively trained in tandem, can rapidly generate useful images. These synthetic images replicate the style, and in several ways exceed the content and function, of normally acquired images. By using this technique and employing AI in such applications, one can ameliorate challenges in image quality, interpretability, coherence, completeness, and granularity, thereby enhancing medical education and clinical decision-making.

The Application and Development of Deep Learning in Radiotherapy: A Systematic Review

With the massive use of computers, the growth and explosion of data has greatly promoted the development of artificial intelligence (AI). The rise of deep learning (DL) algorithms, such as convolutional neural networks (CNN), has provided radiation oncologists with many promising tools that can simplify the complex radiotherapy process in the clinical work of radiation oncology, improve the accuracy and objectivity of diagnosis, and reduce the workload, thus enabling clinicians to spend more time on advanced decision-making tasks. As the development of DL gets closer to clinical practice, radiation oncologists will need to be more familiar with its principles to properly evaluate and use this powerful tool. In this paper, we explain the development and basic concepts of AI and discuss its application in radiation oncology based on different task categories of DL algorithms. This work clarifies the possibility of further development of DL in radiation oncology.

Automatic Detection of Atherosclerotic Plaque and Calcification From Intravascular Ultrasound Images by Using Deep Convolutional Neural Networks

Atherosclerosis is the major cause of cardiovascular diseases (CVDs). Intravascular ultrasound (IVUS) is a common imaging modality for diagnosing CVDs. However, an efficient analyzer for IVUS image segmentation is required for assisting cardiologists. In this study, an end-to-end deep-learning convolutional neural network was developed for automatically detecting media-adventitia borders, luminal regions, and calcified plaque in IVUS images. A total of 713 grayscale IVUS images from 18 patients were used as training data for the proposed deep-learning model. The model is constructed using the three modified U-Nets and combined with the concept of cascaded networks to prevent errors in the detection of calcification owing to the interference of pixels outside the plaque regions. Three loss functions (Dice, Tversky, and focal loss) with various characteristics were tested to determine the best setting for the proposed model. The efficacy of the deep-learning model was evaluated by analyzing precision-recall curve. The average precision (AP), Dice score coefficient, precision, sensitivity, and specificity of the predicted and ground truth results were then compared. All training processes were validated using leave-one-subject-out cross-validation. The experimental results showed that the proposed deep-learning model exhibits high performance in segmenting the media-adventitia layers and luminal regions for all loss functions, with all tested metrics being higher than 0.90. For locating calcified tissues, the best result was obtained when the focal loss function was applied to the proposed model, with an AP of 0.73; however, the prediction efficacy was affected by the proportion of calcified tissues within the plaque region when the focal loss function was employed. Compared with commercial software, the proposed method exhibited high accuracy in segmenting IVUS images in some special cases, such as when shadow artifacts or side vessels surrounded the target vessel.

Deep learning-based intravascular ultrasound segmentation for the assessment of coronary artery disease

BACKGROUND

Accurate segmentation of the coronary arteries with intravascular ultrasound (IVUS) is important to optimize coronary stent implantation. Recently, deep learning (DL) methods have been proposed to develop automatic IVUS segmentation. However, most of those have been limited to segmenting the lumen and vessel (i.e. lumen-intima and media-adventitia borders), not applied to segmenting stent dimension. Hence, this study aimed to develop a DL method for automatic IVUS segmentation of stent area in addition to lumen and vessel area.

METHODS

This study included a total of 45,449 images from 1576 IVUS pullback runs. The datasets were randomly split into training, validation, and test datasets (0.7:0.15:0.15). After developing the DL-based system to segment IVUS images using the training and validation datasets, we evaluated the performance through the independent test dataset.

RESULTS

The DL-based segmentation correlated well with the expert-analyzed segmentation with a mean intersection over union (± standard deviation) of 0.80 ± 0.20, correlation coefficient of 0.98 (95% confidence intervals: 0.98 to 0.98), 0.96 (0.95 to 0.96), and 0.96 (0.96 to 0.96) for lumen, vessel, and stent area, and the mean difference (± standard deviation) of 0.02 ± 0.57, -0.44 ± 1.56 and - 0.17 ± 0.74 mm² for lumen, vessel and stent area, respectively.

CONCLUSION

This automated DL-based IVUS segmentation of lumen, vessel and stent area showed an excellent agreement with manual segmentation by experts, supporting the feasibility of artificial intelligence-assisted IVUS assessment in patients undergoing coronary stent implantation.