Improving Heart Rejection Detection in XPCI Images Using Synthetic Data Augmentation

TL;DR

This paper demonstrates that using synthetic data generated by StyleGAN to augment limited real biopsy images significantly improves deep learning models' ability to detect heart transplant rejection in X-ray phase-contrast images.

Contribution

It introduces a novel data augmentation approach using StyleGAN to address class imbalance in heart rejection detection from biopsy images.

Findings

Synthetic data enhances classification accuracy.

Hybrid training with real and synthetic images yields best results.

GAN-based augmentation is effective in limited-data biomedical imaging.

Abstract

Accurate identification of acute cellular rejection (ACR) in endomyocardial biopsies is essential for effective management of heart transplant patients. However, the rarity of high-grade rejection cases (3R) presents a significant challenge for training robust deep learning models. This work addresses the class imbalance problem by leveraging synthetic data generation using StyleGAN to augment the limited number of real 3R images. Prior to GAN training, histogram equalization was applied to standardize image appearance and improve the consistency of tissue representation. StyleGAN was trained on available 3R biopsy patches and subsequently used to generate 10,000 realistic synthetic images. These were combined with real 0R samples, that is samples without rejection, in various configurations to train ResNet-18 classifiers for binary rejection classification. Three classifier variants were evaluated: one trained on real 0R and synthetic 3R images, another using both synthetic and additional real samples, and a third trained solely on real data. All models were tested on an independent set of real biopsy images. Results demonstrate that synthetic data improves classification performance, particularly when used in combination with real samples. The highest-performing model, which used both real and synthetic images, achieved strong precision and recall for both classes. These findings underscore the value of hybrid training strategies and highlight the potential of GAN-based data augmentation in biomedical image analysis, especially in domains constrained by limited annotated datasets.