A Vision Transformer-based deep learning model accurately diagnosed coronary layered plaque on optical coherence tomography images, significantly outperforming a standard convolutional neural network model (AUC 0.860 vs 0.799, p<0.001).
Observational (n=873)
Yes
Does a Visual Transformer (ViT)-based deep learning model improve the diagnostic accuracy of coronary layered plaque on OCT images compared to a standard CNN-based model in patients with acute coronary syndromes?
A Vision Transformer-based deep learning model accurately diagnoses coronary layered plaque on OCT images, outperforming standard CNN models and potentially aiding in risk stratification for cardiac events.
Absolute Event Rate: 0.86% vs 0.799%
p-value: p=<0.001
Healed coronary plaques, morphologically characterized by a layered phenotype, are signs of previous plaque destabilization and healing. Recent optical coherence tomography (OCT) studies demonstrated that layered plaque is associated with higher levels of local and systemic inflammation and rapid plaque progression. However, the diagnosis of layered plaque needs expertise in OCT image analysis and is susceptible to inter-observer variability. We developed a deep learning (DL) model for an accurate diagnosis of layered plaque. A Visual Transformer (ViT)-based DL model that integrates information from adjacent frames emulating the cardiologists who review consecutive OCT frames to make a diagnosis was developed and compared with the standard convolutional neural network (CNN) model. A total of 237,021 cross-sectional OCT images from 581 patients collected from 8 sites were used for training and internal validation, and 65,394 images from 292 patients collected from another site were used for external validation. In the five-fold cross-validation, the ViT-based model provided better performance (area under the curve AUC: 0.860; 95% confidence interval CI: 0.855-0.866) than the standard CNN-based model (AUC: 0.799; 95% CI: 0.792-0.805). The ViT-based model (AUC: 0.845; 95% CI: 0.837-0.853) also surpassed the standard CNN-based model (AUC: 0.791; 95% CI: 0.782-0.800) in the external validation. The ViT-based DL model can accurately diagnose a layered plaque, which could help risk stratification for cardiac events.
Araki et al. (Fri,) conducted a observational in Acute coronary syndromes (n=873). Vision Transformer (ViT)-based deep learning model vs. Standard convolutional neural network (CNN)-based model was evaluated on Area under the curve (AUC) for frame-level diagnosis of layered plaque in internal cross-validation (95% CI 0.855-0.866, p=<0.001). A Vision Transformer-based deep learning model accurately diagnosed coronary layered plaque on optical coherence tomography images, significantly outperforming a standard convolutional neural network model (AUC 0.860 vs 0.799, p<0.001).