TBI-GAN: An Adversarial Learning Approach for Data Synthesis on Traumatic Brain Segmentation

TL;DR

This paper introduces TBI-GAN, a novel adversarial learning model that synthesizes traumatic brain injury MR scans with corresponding labels, significantly improving data augmentation for better segmentation performance.

Contribution

The paper presents the first TBI image and label synthesis method using GANs, with a registration-based augmentation pipeline to enhance data diversity.

Findings

Synthesized high-quality TBI images and labels.

Improved traumatic brain segmentation accuracy.

Enhanced data augmentation effectiveness.

Abstract

Brain network analysis for traumatic brain injury (TBI) patients is critical for its consciousness level assessment and prognosis evaluation, which requires the segmentation of certain consciousness-related brain regions. However, it is difficult to construct a TBI segmentation model as manually annotated MR scans of TBI patients are hard to collect. Data augmentation techniques can be applied to alleviate the issue of data scarcity. However, conventional data augmentation strategies such as spatial and intensity transformation are unable to mimic the deformation and lesions in traumatic brains, which limits the performance of the subsequent segmentation task. To address these issues, we propose a novel medical image inpainting model named TBI-GAN to synthesize TBI MR scans with paired brain label maps. The main strength of our TBI-GAN method is that it can generate TBI images and corresponding label maps simultaneously, which has not been achieved in the previous inpainting methods for medical images. We first generate the inpainted image under the guidance of edge information following a coarse-to-fine manner, and then the synthesized intensity image is used as the prior for label inpainting. Furthermore, we introduce a registration-based template augmentation pipeline to increase the diversity of the synthesized image pairs and enhance the capacity of data augmentation. Experimental results show that the proposed TBI-GAN method can produce sufficient synthesized TBI images with high quality and valid label maps, which can greatly improve the 2D and 3D traumatic brain segmentation performance compared with the alternatives.