Artificial Intelligence-based Approaches for Characterizing Plaque Components From Intravascular Optical Coherence Tomography Imaging: Integration Into Clinical Decision Support Systems

Abstract

Intravascular optical coherence tomography (IVOCT) is emerging as an effective imaging technique for accurately characterizing coronary atherosclerotic plaques. This technique provides detailed information on plaque morphology and composition, enabling the identification of high-risk features associated with coronary artery disease and adverse cardiovascular events. However, despite advancements in imaging technology and image assessment, the adoption of IVOCT in clinical practice remains limited. Manual plaque assessment by experts is time-consuming, prone to errors, and affected by high inter-observer variability. To increase productivity, precision, and reproducibility, researchers are increasingly integrating artificial intelligence (AI)-based techniques into IVOCT analysis pipelines. Machine learning algorithms, trained on labelled datasets, have demonstrated robust classification of various plaque types. Deep learning models, particularly convolutional neural networks, further improve performance by enabling automatic feature extraction. This reduces the reliance on predefined criteria, which often require domain-specific expertise, and allow for more flexible and comprehensive plaque characterization. AI-driven approaches aim to facilitate the integration of IVOCT into routine clinical practice, potentially transforming this technique from a research tool into a powerful aid for clinical decision-making. This narrative review aims to (i) provide a comprehensive overview of AI-based methods for analyzing IVOCT images of coronary arteries, with a focus on plaque characterization, and (ii) explore the clinical translation of AI to IVOCT, highlighting AI-powered tools for plaque characterization currently intended for commercial and/or clinical use. While these technologies represent significant progress, current solutions remain limited in the range of plaque features these methods can assess. Additionally, many of these solutions are confined to specific regulatory or research settings. Therefore, this review highlights the need for further advancements in AI-based IVOCT analysis, emphasizing the importance of additional validation and improved integration with clinical systems to enhance plaque characterization, support clinical decision-making, and advance risk prediction.

Keywords: artificial intelligence; atherosclerotic plaque; automated plaque characterization; clinical decision support systems; deep learning; intravascular imaging; machine learning; optical coherence tomography.

Fig. 1.

Main components of an atherosclerotic plaque as visible in intravascular optical coherence tomography images. Each plaque is characterized by its composition and microstructure, both of which can contribute to plaque rupture under certain conditions. The primary components of an atherosclerotic plaque include fibrous, lipidic, or calcified tissues. The microstructures commonly found in atherosclerotic plaques may include thin cap fibroatheroma, cholesterol crystals, thrombi, neovascularization, and macrophages. Image features are indicated by white arrows. Adapted with permission from [22, 23, 24]. TCFA, thin cap fibroatheroma.

Fig. 2.

Main pipeline of machine learning (ML)-based systems for plaque composition characterization from intravascular optical coherence tomography. Specifically, the process outlined by Prabhu et al. [43], which includes the preprocessing phase, features extraction phase, ML model application, and A-line classification, is detailed as an example. Adapted with permission from [43]. 2D, 2-Dimensional; 3D, 3-Dimensional.

Fig. 3.

Main pipeline of deep learning (DL)-based systems for plaque composition characterization from intravascular optical coherence tomography (IVOCT). The main steps involved in plaque composition characterization, including preprocessing phase, DL model application, and IVOCT image segmentation, are illustrated. Adapted with permission from [36] and [68].

Fig. 4.

Graphical user interface of the Ultreon 2.0 software (Abbott Laboratories). (A) Angiographic view of a coronary vessel imaged using IVOCT. (B) Example of a cross-sectional IVOCT image (i.e., IVOCT frame) of the analyzed vessel, with Ultreon’s morphological assessment view showing automated calcium detection (calcium is highlighted by an orange arc). (C) Quantitative display of the calcium arc, thickness, and longitudinal extent, along with lumen diameter information. (D) Longitudinal reconstruction of the vessel from IVOCT imaging data: the current IVOCT frame is indicated by a thicker white line, while IVOCT frames with a total calcium angle greater than 180° are marked by orange lines.

Fig. 5.

Schematic of the process for integrating image-derived biomarkers with patients’ clinical characteristics in artificial intelligence models to evaluate coronary artery disease, assess risk, and create individualized medical care. Adapted with permission from [114].