A Self-attention Guided Multi-scale Gradient GAN for Diversified X-ray Image Synthesis

TL;DR

This paper introduces MSG-SAGAN, a novel attention-guided multi-scale gradient GAN architecture that enhances the diversity and quality of synthetic X-ray images by stabilizing training and reducing mode collapse.

Contribution

The paper proposes a new GAN architecture that integrates attention mechanisms with multi-scale gradient learning to improve training stability and image diversity in biomedical image synthesis.

Findings

MSG-SAGAN outperforms MSG-GAN in diversity metrics.

The architecture reduces mode collapse in X-ray image synthesis.

Enhanced training stability demonstrated through improved FID scores.

Abstract

Imbalanced image datasets are commonly available in the domain of biomedical image analysis. Biomedical images contain diversified features that are significant in predicting targeted diseases. Generative Adversarial Networks (GANs) are utilized to address the data limitation problem via the generation of synthetic images. Training challenges such as mode collapse, non-convergence, and instability degrade a GAN's performance in synthesizing diversified and high-quality images. In this work, MSG-SAGAN, an attention-guided multi-scale gradient GAN architecture is proposed to model the relationship between long-range dependencies of biomedical image features and improves the training performance using a flow of multi-scale gradients at multiple resolutions in the layers of generator and discriminator models. The intent is to reduce the impact of mode collapse and stabilize the training of GAN using an attention mechanism with multi-scale gradient learning for diversified X-ray image synthesis. Multi-scale Structural Similarity Index Measure (MS-SSIM) and Frechet Inception Distance (FID) are used to identify the occurrence of mode collapse and evaluate the diversity of synthetic images generated. The proposed architecture is compared with the multi-scale gradient GAN (MSG-GAN) to assess the diversity of generated synthetic images. Results indicate that the MSG-SAGAN outperforms MSG-GAN in synthesizing diversified images as evidenced by the MS-SSIM and FID scores.