Direct Cardiac Segmentation from Undersampled K-space Using Transformers

TL;DR

This paper introduces DiSK, a transformer-based method that directly segments cardiac structures from undersampled k-space data, bypassing image reconstruction and improving accuracy across various acceleration factors.

Contribution

The novel DiSK approach directly derives cardiac segmentation from sparse k-space data using transformers, avoiding intermediate image reconstruction and reducing information loss.

Findings

Outperforms image-based baselines in Dice and Hausdorff metrics

Maintains high segmentation accuracy across acceleration factors 4 to 64

Effectively leverages redundant k-space information for segmentation

Abstract

The prevailing deep learning-based methods of predicting cardiac segmentation involve reconstructed magnetic resonance (MR) images. The heavy dependency of segmentation approaches on image quality significantly limits the acceleration rate in fast MR reconstruction. Moreover, the practice of treating reconstruction and segmentation as separate sequential processes leads to artifact generation and information loss in the intermediate stage. These issues pose a great risk to achieving high-quality outcomes. To leverage the redundant k-space information overlooked in this dual-step pipeline, we introduce a novel approach to directly deriving segmentations from sparse k-space samples using a transformer (DiSK). DiSK operates by globally extracting latent features from 2D+time k-space data with attention blocks and subsequently predicting the segmentation label of query points. We evaluate our model under various acceleration factors (ranging from 4 to 64) and compare against two image-based segmentation baselines. Our model consistently outperforms the baselines in Dice and Hausdorff distances across foreground classes for all presented sampling rates.