Reconstruction-free segmentation from undersampled k-space using transformers

TL;DR

This paper introduces a transformer-based method for direct cardiac segmentation from undersampled k-space MRI data, bypassing image reconstruction and enabling higher acceleration factors for better segmentation quality.

Contribution

It presents a novel transformer architecture that directly segments from sparse k-space data, extending MRI acceleration limits beyond traditional image-based methods.

Findings

Outperforms image-based segmentation at high acceleration factors

Enables direct segmentation from undersampled k-space data

Circumvents the need for intermediate image reconstruction

Abstract

Motivation: High acceleration factors place a limit on MRI image reconstruction. This limit is extended to segmentation models when treating these as subsequent independent processes. Goal: Our goal is to produce segmentations directly from sparse k-space measurements without the need for intermediate image reconstruction. Approach: We employ a transformer architecture to encode global k-space information into latent features. The produced latent vectors condition queried coordinates during decoding to generate segmentation class probabilities. Results: The model is able to produce better segmentations across high acceleration factors than image-based segmentation baselines. Impact: Cardiac segmentation directly from undersampled k-space samples circumvents the need for an intermediate image reconstruction step. This allows the potential to assess myocardial structure and function on higher acceleration factors than methods that rely on images as input.