Self-Supervised Denoising of Diffusion MRI Data Via Spatio-Angular Noise2Noise

Haotian Jiang, Shu Zhang, Xuyun Wen, Hui Cui, Jun Lu, Islem Rekik, Jiquan Ma, Geng Chen

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

1 Scopus citations

Abstract

Diffusion MRI (DMRI) suffers from heavy noise that reduces the accuracy and reliability of the derived diffusion metrics. Existing Deep Learning (DL) methods for DMRI denoising usually rely on training with paired noisy-clean data, which are unavailable in a clinical setting. To this end, we propose a self-supervised DL denoising method, called Spatio-Angular Noise2Noise (SAN2N). We utilize a network trained with paired noisy data that can capture the essential information of underlying clean data for noise reduction. Specifically, SAN2N generates angular neighboring DMRI data based on the geometric structure of q-space sampling points. The resulting data and the original one are then fed to two neighborhood-based x-space sub-samplers to extract 4D similar patches in the spatio-angular domain. Finally, these patches are employed to train our SAN2N with a regularized denoising loss. Extensive experiments on simulated and real datasets demonstrate the superiority of SAN2N over existing DMRI denoising methods.

Original languageEnglish
Title of host publicationIEEE International Symposium on Biomedical Imaging, ISBI 2024 - Conference Proceedings
PublisherIEEE Computer Society
ISBN (Electronic)9798350313338
DOIs
StatePublished - 2024
Event21st IEEE International Symposium on Biomedical Imaging, ISBI 2024 - Athens, Greece
Duration: 27 May 202430 May 2024

Publication series

NameProceedings - International Symposium on Biomedical Imaging
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference21st IEEE International Symposium on Biomedical Imaging, ISBI 2024
Country/TerritoryGreece
CityAthens
Period27/05/2430/05/24

Keywords

  • Denoising
  • Diffusion MRI
  • Self-Supervised Learning
  • Spatio-Angular Domain

Fingerprint

Dive into the research topics of 'Self-Supervised Denoising of Diffusion MRI Data Via Spatio-Angular Noise2Noise'. Together they form a unique fingerprint.

Cite this