Enhanced Diagnosis of Plaque Erosion by Deep Learning in Patients With Acute Coronary Syndromes

Background: Acute coronary syndromes caused by plaque erosion might be potentially managed conservatively without stenting. Currently, the diagnosis of plaque erosion requires expertise in optical coherence tomographic (OCT) image interpretation. In addition, the current deep learning (DL) approaches for OCT image interpretation are based on a single frame, without integrating the information from adjacent frames. Objectives: The aim of this study was to develop a novel DL model to facilitate an accurate diagnosis of plaque erosion. Methods: A novel “Transformer”-based DL model was developed that integrates information from adjacent frames emulating the cardiologists who review consecutive OCT frames to make a diagnosis and compared with the standard convolutional neural network (CNN) DL model. A total of 237,021 cross-sectional OCT images from 581 patients were used for training and internal validation, and 65,394 images from 292 patients from another dataset were used for external validation. Model performances were evaluated using the area under the receiver-operating characteristic curve (AUC). Results: For the frame-level diagnosis of plaque erosion, the Transformer model showed superior performance than the CNN model, with an AUC of 0.94 compared with 0.85 in the external validation. For the lesion-level diagnosis, the Transformer model showed improved diagnostic performance compared with the CNN model, with an AUC of 0.91 compared with 0.84 in the external validation. Conclusions: This newly developed Transformer model will help cardiologists diagnose plaque erosion with high accuracy in patients with acute coronary syndromes.