PuSH - Publication Server of Helmholtz Zentrum München

Yu, Z.* ; Han, X.* ; Zhang, S.* ; Feng, J.* ; Peng, T. ; Zhang, X.Y.*

MouseGAN++: Unsupervised disentanglement and contrastive representation for multiple MRI modalities synthesis and structural segmentation of mouse brain.

IEEE Trans. Med. Imaging, DOI: 10.1109/TMI.2022.3225528 (2022)
Postprint DOI
Open Access Green
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.
Additional Metrics?
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Keywords Disentangled Representations ; Generative Adversarial Network ; Mouse Brain ; Mri ; Segmentation
ISSN (print) / ISBN 0278-0062
e-ISSN 1558-254X
Publisher Institute of Electrical and Electronics Engineers (IEEE)
Publishing Place New York, NY [u.a.]
Reviewing status Peer reviewed