Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory

• Published in: NeuroImage (Orlando, Fla.) Vol. 243; p. 118569
• Main Authors: Zuo, Lianrui, Dewey, Blake E., Liu, Yihao, He, Yufan, Newsome, Scott D., Mowry, Ellen M., Resnick, Susan M., Prince, Jerry L., Carass, Aaron
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.11.2021; Elsevier Limited; Elsevier
• Subjects: Algorithms; Anatomy; Disentangle; Harmonization; Humans; Image Processing, Computer-Assisted - methods; Image synthesis; Image-to-image translation; Information Theory; Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Scanners; Standardization; Image-to-image translation; Image synthesis; Disentangle; Magnetic resonance imaging; Harmonization
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2021.118569

•Unsupervised MR harmonization without traveling subjects.•Unified latent space for MR contrast synthesis.•A novel framework for disentangling contrast and anatomy in MR images.•Downstream segmentation consistency shows significant improvements after harmonization. In magnetic resonance (MR) imaging, a lack of standardization in acquisition often causes pulse sequence-based contrast variations in MR images from site to site, which impedes consistent measurements in automatic analyses. In this paper, we propose an unsupervised MR image harmonization approach, CALAMITI (Contrast Anatomy Learning and Analysis for MR Intensity Translation and Integration), which aims to alleviate contrast variations in multi-site MR imaging. Designed using information bottleneck theory, CALAMITI learns a globally disentangled latent space containing both anatomical and contrast information, which permits harmonization. In contrast to supervised harmonization methods, our approach does not need a sample population to be imaged across sites. Unlike traditional unsupervised harmonization approaches which often suffer from geometry shifts, CALAMITI better preserves anatomy by design. The proposed method is also able to adapt to a new testing site with a straightforward fine-tuning process. Experiments on MR images acquired from ten sites show that CALAMITI achieves superior performance compared with other harmonization approaches.