Rapid lipid-laden plaque identification in intravascular OCT imaging based on time-series deep learning

Abstract

Coronary heart disease has the highest rate of death and morbidity in the Western world. Lipid-laden plaques containing a necrotic core may eventually rupture causing heart attack and stroke. Intravascular Optical Coherence Tomography (IV-OCT) imaging has been used for plaque assessment. However, the IV-OCT images are visually interpreted, which is burdensome and require highly trained physicians. This 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. An A-line wise classification methodology based on time-series deep learning is presented to fulfill this aim.