SCPAT-GAN: Structural Constrained and Pathology Aware Convolutional Transformer-GAN for Virtual Histology Staining of Human Coronary OCT images

TL;DR

SCPAT-GAN is a novel transformer-based GAN that generates virtual histology from coronary OCT images, incorporating structural constraints and pathology awareness to improve accuracy and guidance in treatment of coronary artery disease.

Contribution

It introduces a new transformer-GAN model with structural constraints and pathology guidance for virtual histology generation from OCT images.

Findings

Effective virtual histology generation demonstrated.

Improved mapping of pathological regions.

Enhanced structural and pathological accuracy.

Abstract

There is a significant need for the generation of virtual histological information from coronary optical coherence tomography (OCT) images to better guide the treatment of coronary artery disease. However, existing methods either require a large pixel-wisely paired training dataset or have limited capability to map pathological regions. To address these issues, we proposed a structural constrained, pathology aware, transformer generative adversarial network, namely SCPAT-GAN, to generate virtual stained H&E histology from OCT images. The proposed SCPAT-GAN advances existing methods via a novel design to impose pathological guidance on structural layers using transformer-based network.