Deep Semi-Supervised Bias Field Correction Of Mr Images

Tal Goldfryd, Shiri Gordon, Tamar Riklin Raviv

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A bias field is an artifact inherent to MRI scanners which is manifested by a smooth intensity variation across the scans. We present an innovative generative approach to address the inverse problem of bias field estimation and removal in a semi-supervised manner. The key contribution is the construction of a compound framework of four interacting, adversarial neural networks. Specifically, we simultaneously train a pair of neural networks, one for the reconstruction of the plain bias field and the other for the reconstruction of a bias-free MRI scan, such that the output of each together with the input biased scans define the loss of the other network. A third network, trained as a bias-field discriminator provides an additional loss to the bias field generator while an MRI segmentation network provides an additional loss to the bias-free MRI generator. We trained and validated our framework using real MRI scans with simulated bias fields and tested it on publicly available brain data-sets as well as private data yielding results competitive with state-of-the-art methods. Code is available upon request.
Original languageEnglish
Title of host publication2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)
Pages1836-1840
Number of pages5
DOIs
StatePublished - 2021

Fingerprint

Dive into the research topics of 'Deep Semi-Supervised Bias Field Correction Of Mr Images'. Together they form a unique fingerprint.

Cite this