Structural constrained virtual histology staining for human coronary imaging using deep learning

TL;DR

This paper introduces Coronary-GAN, a deep learning model that generates virtual histology images from OCT scans, enabling real-time coronary artery visualization and analysis without invasive procedures.

Contribution

The study presents a novel deep learning approach with structural constraints for generating accurate virtual histology images from OCT data.

Findings

Coronary-GAN outperforms conventional GANs in image quality.

Generated images accurately reveal coronary artery layers.

The method enables real-time, non-invasive artery analysis.

Abstract

Histopathological analysis is crucial in artery characterization for coronary artery disease (CAD). However, histology requires an invasive and time-consuming process. In this paper, we propose to generate virtual histology staining using Optical Coherence Tomography (OCT) images to enable real-time histological visualization. We develop a deep learning network, namely Coronary-GAN, to transfer coronary OCT images to virtual histology images. With a special consideration on the structural constraints in coronary OCT images, our method achieves better image generation performance than the conventional GAN-based method. The experimental results indicate that Coronary-GAN generates virtual histology images that are similar to real histology images, revealing the human coronary layers.