Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution

TL;DR

This paper demonstrates that combining extreme k-space undersampling with deep learning superresolution can significantly accelerate MRI scans while maintaining diagnostic image quality, with promising results at acceleration factors up to x64.

Contribution

It introduces a novel approach of ultra-high undersampling in MRI combined with deep learning enhancement, surpassing previous acceleration limits and validating clinical diagnostic preservation.

Findings

Achieved an MSE of 0.00114, PSNR of 29.6 dB, SSIM of 0.956 at x16 acceleration.

Explored extreme undersampling factors of x32 and x64 for potential clinical use.

Radiologist survey confirms diagnostic value of recovered images.

Abstract

We went below the MRI acceleration factors (a.k.a., k-space undersampling) reported by all published papers that reference the original fastMRI challenge, and then considered powerful deep learning based image enhancement methods to compensate for the underresolved images. We thoroughly study the influence of the sampling patterns, the undersampling and the downscaling factors, as well as the recovery models on the final image quality for both the brain and the knee fastMRI benchmarks. The quality of the reconstructed images surpasses that of the other methods, yielding an MSE of 0.00114, a PSNR of 29.6 dB, and an SSIM of 0.956 at x16 acceleration factor. More extreme undersampling factors of x32 and x64 are also investigated, holding promise for certain clinical applications such as computer-assisted surgery or radiation planning. We survey 5 expert radiologists to assess 100 pairs of images and show that the recovered undersampled images statistically preserve their diagnostic value.