Brain Tumor Segmentation Network Using Attention-based Fusion and Spatial Relationship Constraint
This work addresses the challenge of precise tumor delineation for glioma treatment, representing an incremental improvement in medical imaging segmentation.
The paper tackles the problem of automatic brain tumor segmentation from multi-modal MR images by proposing a novel network with attention-based fusion and a spatial relationship constraint, achieving Dice scores of 0.8764, 0.8243, and 0.773 for whole tumor, tumor core, and enhancing tumor, respectively.
Delineating the brain tumor from magnetic resonance (MR) images is critical for the treatment of gliomas. However, automatic delineation is challenging due to the complex appearance and ambiguous outlines of tumors. Considering that multi-modal MR images can reflect different tumor biological properties, we develop a novel multi-modal tumor segmentation network (MMTSN) to robustly segment brain tumors based on multi-modal MR images. The MMTSN is composed of three sub-branches and a main branch. Specifically, the sub-branches are used to capture different tumor features from multi-modal images, while in the main branch, we design a spatial-channel fusion block (SCFB) to effectively aggregate multi-modal features. Additionally, inspired by the fact that the spatial relationship between sub-regions of tumor is relatively fixed, e.g., the enhancing tumor is always in the tumor core, we propose a spatial loss to constrain the relationship between different sub-regions of tumor. We evaluate our method on the test set of multi-modal brain tumor segmentation challenge 2020 (BraTs2020). The method achieves 0.8764, 0.8243 and 0.773 dice score for whole tumor, tumor core and enhancing tumor, respectively.