HAGAN: Hybrid Augmented Generative Adversarial Network for Medical Image Synthesis

TL;DR

HAGAN is a novel hybrid GAN model designed for medical image synthesis that enhances structural and textural authenticity, improving the quality and accuracy of synthetic medical images across various datasets.

Contribution

The paper introduces HAGAN, which integrates Attention Mixed Generator, Hierarchical Discriminator, and Reverse Skip Connection to better preserve biological consistency in medical image synthesis.

Findings

HAGAN outperforms existing methods on COVID-CT, ACDC, and BraTS2018 datasets.

Achieves state-of-the-art results in both high- and low-resolution image synthesis.

Enhances local detail accuracy and pathological integrity of synthetic images.

Abstract

Medical Image Synthesis (MIS) plays an important role in the intelligent medical field, which greatly saves the economic and time costs of medical diagnosis. However, due to the complexity of medical images and similar characteristics of different tissue cells, existing methods face great challenges in meeting their biological consistency. To this end, we propose the Hybrid Augmented Generative Adversarial Network (HAGAN) to maintain the authenticity of structural texture and tissue cells. HAGAN contains Attention Mixed (AttnMix) Generator, Hierarchical Discriminator and Reverse Skip Connection between Discriminator and Generator. The AttnMix consistency differentiable regularization encourages the perception in structural and textural variations between real and fake images, which improves the pathological integrity of synthetic images and the accuracy of features in local areas. The Hierarchical Discriminator introduces pixel-by-pixel discriminant feedback to generator for enhancing the saliency and discriminance of global and local details simultaneously. The Reverse Skip Connection further improves the accuracy for fine details by fusing real and synthetic distribution features. Our experimental evaluations on three datasets of different scales, i.e., COVID-CT, ACDC and BraTS2018, demonstrate that HAGAN outperforms the existing methods and achieves state-of-the-art performance in both high-resolution and low-resolution.