Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis

TL;DR

This paper introduces a novel GAN-based method with a segmentor discriminator for more accurate pseudo-healthy brain image synthesis, improving image quality and clinical utility with less training data.

Contribution

The paper proposes a segmentor discriminator in GANs for better lesion localization and pseudo-healthy image synthesis, outperforming existing methods with reduced data requirements.

Findings

Outperforms state-of-the-art methods on BraTS dataset

Achieves better results with only 30% of training data

Effective on multiple modalities and datasets

Abstract

Synthesizing a subject-specific pathology-free image from a pathological image is valuable for algorithm development and clinical practice. In recent years, several approaches based on the Generative Adversarial Network (GAN) have achieved promising results in pseudo-healthy synthesis. However, the discriminator (i.e., a classifier) in the GAN cannot accurately identify lesions and further hampers from generating admirable pseudo-healthy images. To address this problem, we present a new type of discriminator, the segmentor, to accurately locate the lesions and improve the visual quality of pseudo-healthy images. Then, we apply the generated images into medical image enhancement and utilize the enhanced results to cope with the low contrast problem existing in medical image segmentation. Furthermore, a reliable metric is proposed by utilizing two attributes of label noise to measure the health of synthetic images. Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods. The method achieves better performance than the existing methods with only 30\% of the training data. The effectiveness of the proposed method is also demonstrated on the LiTS and the T1 modality of BraTS. The code and the pre-trained model of this study are publicly available at https://github.com/Au3C2/Generator-Versus-Segmentor.