High‐Resolution Diffusion‐Weighted Imaging With Self‐Gated Self‐Supervised Unrolled Reconstruction

TL;DR

This paper introduces a self-supervised algorithm for high-resolution diffusion-weighted imaging that improves image quality and reduces scan time, making it suitable for clinical use.

Contribution

The novel contribution is the use of ADMM unrolling for self-gated self-supervised learning in submillimeter-resolution diffusion-weighted imaging.

Findings

ADMM unrolling generalizes across slices and outperforms existing methods in image sharpness and motion robustness.

The technique achieves 0.7 mm isotropic resolution in 10 minutes with improved SNR and tissue delineation.

ADMM unrolling provides clinically feasible inference time for whole brain diffusion imaging.

Abstract

High‐resolution diffusion‐weighted imaging (DWI) is clinically demanding. The purpose of this work is to develop an efficient self‐supervised algorithm unrolling technique for submillimeter‐resolution DWI.

We developed submillimeter DWI acquisition utilizing multi‐band multi‐shot EPI with diffusion shift encoding. We unrolled the alternating direction method of multipliers (ADMM) to perform scan‐specific self‐gated self‐supervised DeepDWI learning for multi‐shot echo planar imaging with diffusion shift encoding on a clinical 7 T scanner.

We demonstrate that (1) ADMM unrolling is generalizable across slices, (2) ADMM unrolling outperforms multiplexed sensitivity‐encoding (MUSE) and compressed sensing with locally‐low rank (LLR) regularization in terms of image sharpness, tissue continuity, and motion robustness, and (3) ADMM unrolling enables clinically feasible inference time.

Our proposed ADMM unrolling enables whole brain DWI of 21 diffusion volumes at 0.7 mm isotropic resolution and 10 min scan, and shows higher signal‐to‐noise ratio (SNR), clearer tissue delineation, and improved motion robustness, which makes it plausible for clinical translation.

Figures