Brain Segmentation from k-space with End-to-end Recurrent Attention Network
This addresses medical image segmentation for MRI analysis by eliminating reconstruction errors, though it is incremental as it builds on existing segmentation and simulation techniques.
The authors tackled brain segmentation from raw MRI k-space data, bypassing reconstruction to avoid noise and artifacts, and achieved superior performance over state-of-the-art methods.
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.