What type of study is this?

This is a Quantitative Study study.

September 17, 2025

KOMET: Kspace Optimal Masking for Efficient Training of Zero-shot MRI Reconstruction

Key Points

KOMET achieves improved MRI reconstruction quality, outperforming traditional methods by 2dB PSNR.
The study demonstrates robust performance across various undersampling patterns, like 4x and 8x reductions.
Proposed methods include dynamic k-space masking and joint optimization incorporating sensitivity estimation.
The method may enable more effective accelerated MRI without reliance on fully sampled reference data.

Abstract

Motivation: Zero-shot learning shows promise in various domains but remains underexplored in MRI reconstruction due to inherent challenges in recovering images without supervision of fully sampled data. Goal(s): To develop a stable zero-shot MRI reconstruction framework eliminating the need for fully sampled reference data. Approach: We propose a dynamic k-space masking strategy inspired by masked image modeling, coupled with joint optimization of image reconstruction and coil sensitivity estimation. Results: KOMET shows robust performance across various undersampling patterns (4×, 8× reduction with Gaussian and uniform masks) on FastMRI knee dataset, outperforming traditional parallel imaging methods and recent zero-shot approach with 2dB PSNR improvement. Impact: KOMET establishes a novel framework for stable zero-shot MRI reconstruction by adapting masked modeling to k-space domain. This advancement enables robust acceleration without fully sampled reference data, paving the way for broader clinical application of accelerated MRI.

Mark Helpful

Bookmark

Relay