MouseGAN++: Unsupervised Disentanglement and Contrastive Representation for Multiple MRI Modalities Synthesis and Structural Segmentation of Mouse Brain

TL;DR

MouseGAN++ is a novel GAN-based framework that synthesizes multiple MRI modalities from single ones and improves mouse brain segmentation accuracy by leveraging disentangled and contrastive learning, especially when multimodal data is scarce.

Contribution

The paper introduces MouseGAN++, a new disentangled and contrastive GAN framework that enhances MRI modality synthesis and mouse brain segmentation, outperforming existing methods.

Findings

Achieves around 10% performance improvement in segmentation accuracy.

Outperforms state-of-the-art methods in MRI modality translation.

Enables robust segmentation with unpaired cross-modality fusion.

Abstract

Segmenting the fine structure of the mouse brain on magnetic resonance (MR) images is critical for delineating morphological regions, analyzing brain function, and understanding their relationships. Compared to a single MRI modality, multimodal MRI data provide complementary tissue features that can be exploited by deep learning models, resulting in better segmentation results. However, multimodal mouse brain MRI data is often lacking, making automatic segmentation of mouse brain fine structure a very challenging task. To address this issue, it is necessary to fuse multimodal MRI data to produce distinguished contrasts in different brain structures. Hence, we propose a novel disentangled and contrastive GAN-based framework, named MouseGAN++, to synthesize multiple MR modalities from single ones in a structure-preserving manner, thus improving the segmentation performance by imputing missing modalities and multi-modality fusion. Our results demonstrate that the translation performance of our method outperforms the state-of-the-art methods. Using the subsequently learned modality-invariant information as well as the modality-translated images, MouseGAN++ can segment fine brain structures with averaged dice coefficients of 90.0% (T2w) and 87.9% (T1w), respectively, achieving around +10% performance improvement compared to the state-of-the-art algorithms. Our results demonstrate that MouseGAN++, as a simultaneous image synthesis and segmentation method, can be used to fuse cross-modality information in an unpaired manner and yield more robust performance in the absence of multimodal data. We release our method as a mouse brain structural segmentation tool for free academic usage at https://github.com/yu02019.