Brain Segmentation from k-space with End-to-end Recurrent Attention Network

TL;DR

This paper introduces an end-to-end recurrent attention network that directly segments brain MRI from raw k-space data, bypassing traditional image reconstruction and improving segmentation accuracy.

Contribution

It proposes a novel task-driven attention module and a workflow for generating labeled training data directly from raw data, advancing MRI segmentation techniques.

Findings

Outperforms state-of-the-art methods

Effective segmentation directly from raw data

Bridges reconstruction and segmentation tasks

Abstract

The task of medical image segmentation commonly involves an image reconstruction step to convert acquired raw data to images before any analysis. However, noises, artifacts and loss of information due to the reconstruction process are almost inevitable, which compromises the final performance of segmentation. We present a novel learning framework that performs magnetic resonance brain image segmentation directly from k-space data. The end-to-end framework consists of a unique task-driven attention module that recurrently utilizes intermediate segmentation estimation to facilitate image-domain feature extraction from the raw data, thus closely bridging the reconstruction and the segmentation tasks. In addition, to address the challenge of manual labeling, we introduce a novel workflow to generate labeled training data for segmentation by exploiting imaging modality simulators and digital phantoms. Extensive experimental results show that the proposed method outperforms several state-of-the-art methods.