Learning MRI artefact removal with unpaired data

Siyuan Liu, Kim Han Thung, Liangqiong Qu, Weili Lin, Dinggang Shen, Pew Thian Yap

Research output: Contribution to journalArticlepeer-review

Abstract

Retrospective artefact correction (RAC) improves image quality post acquisition and enhances image usability. Recent machine-learning-driven techniques for RAC are predominantly based on supervised learning, so practical utility can be limited as data with paired artefact-free and artefact-corrupted images are typically insufficient or even non-existent. Here we show that unwanted image artefacts can be disentangled and removed from an image via an RAC neural network learned with unpaired data. This implies that our method does not require matching artefact-corrupted data to be either collected via acquisition or generated via simulation. Experimental results demonstrate that our method is remarkably effective in removing artefacts and retaining anatomical details in images with different contrasts.

Original languageEnglish
Pages (from-to)60-67
Number of pages8
JournalNature Machine Intelligence
Volume3
Issue number1
DOIs
Publication statusPublished - 2021 Jan

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications
  • Human-Computer Interaction
  • Software

Fingerprint Dive into the research topics of 'Learning MRI artefact removal with unpaired data'. Together they form a unique fingerprint.

Cite this