Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory
Lists
Only you see this
Abstract
Highlights•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.
BibTeX
@inproceedings{zuo2021unsupervised,
author = {Lianrui Zuo and Blake E. Dewey and Yihao Liu and Yufan He and Scott D. Newsome and Ellen M. Mowry and Susan M. Resnick and Jerry L. Prince and Aaron Carass},
title = {{Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory}},
booktitle = {NeuroImage},
year = {2021},
url = {https://openreview.net/forum?id=BvWVLNkxj0},
}Loading related content...