Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction

TL;DR

This paper reports on the 2020 fastMRI challenge, showcasing advances in MRI image reconstruction from subsampled data, with diverse submissions and insights into current limitations and future research directions.

Contribution

The paper introduces a new challenge focusing on pathological assessment, a transfer track for external scanner evaluation, and provides comprehensive analysis of submissions and metrics.

Findings

One team achieved top scores in SSIM and radiologist assessments.

Analysis revealed common failure modes across models.

Participant feedback informed future challenge design.

Abstract

Accelerating MRI scans is one of the principal outstanding problems in the MRI research community. Towards this goal, we hosted the second fastMRI competition targeted towards reconstructing MR images with subsampled k-space data. We provided participants with data from 7,299 clinical brain scans (de-identified via a HIPAA-compliant procedure by NYU Langone Health), holding back the fully-sampled data from 894 of these scans for challenge evaluation purposes. In contrast to the 2019 challenge, we focused our radiologist evaluations on pathological assessment in brain images. We also debuted a new Transfer track that required participants to submit models evaluated on MRI scanners from outside the training set. We received 19 submissions from eight different groups. Results showed one team scoring best in both SSIM scores and qualitative radiologist evaluations. We also performed analysis on alternative metrics to mitigate the effects of background noise and collected feedback from the participants to inform future challenges. Lastly, we identify common failure modes across the submissions, highlighting areas of need for future research in the MRI reconstruction community.