AI-driven framework for calcium detection in atherosclerotic lesions using intracoronary optical coherence tomography

Coronary atherosclerosis is a chronic inflammatory disease that gradually leads to lumen narrowing. Intravascular optical coherence tomography (OCT) offers the possibility to evaluate the three-dimensional microstructure of the arterial wall at high resolution, allowing for atherosclerotic plaque characterization. In this study, artificial intelligence-based methods were employed to develop a framework for identifying atherosclerotic plaque features in OCT images of coronary arteries. The framework consists of two steps: (i) image preprocessing for image cleaning, and (ii) identification of the targeted plaque feature. Calcium was selected as the plaque feature of interest due to its relevance as a hallmark of atherosclerosis. The implemented model exhibited fair performance and allowed the identification of calcium within the arterial wall. Further improvements of the current model include increasing its effectiveness and precision as well as its application to other plaque features and events, such as plaque rupture.