Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory

Lianrui Zuo, Blake E. Dewey, Yihao Liu, Yufan He, Scott Newsome, Ellen M. Mowry, Susan M. Resnick, Jerry Ladd Prince, Aaron Carass

Research output: Contribution to journalArticlepeer-review

Abstract

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.

Original languageEnglish (US)
Article number118569
JournalNeuroImage
Volume243
DOIs
StatePublished - Nov 2021

Keywords

  • Disentangle
  • Harmonization
  • Image synthesis
  • Image-to-image translation
  • Magnetic resonance imaging

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory'. Together they form a unique fingerprint.

Cite this