Unified Multimodal Coherent Field: Synchronous Semantic-Spatial-Vision Fusion for Brain Tumor Segmentation
This addresses the problem of unstable performance in boundary delineation and hierarchy preservation for brain tumor segmentation in medical imaging, offering a new technical pathway for multimodal fusion in precision medicine.
The paper tackled brain tumor segmentation from MRI images by proposing the Unified Multimodal Coherent Field method, which synchronously fuses visual, semantic, and spatial information, achieving average Dice coefficients of 0.8579 and 0.8977 on BraTS 2020 and 2021 datasets with a 4.18% improvement over mainstream architectures.
Brain tumor segmentation requires accurate identification of hierarchical regions including whole tumor (WT), tumor core (TC), and enhancing tumor (ET) from multi-sequence magnetic resonance imaging (MRI) images. Due to tumor tissue heterogeneity, ambiguous boundaries, and contrast variations across MRI sequences, methods relying solely on visual information or post-hoc loss constraints show unstable performance in boundary delineation and hierarchy preservation. To address this challenge, we propose the Unified Multimodal Coherent Field (UMCF) method. This method achieves synchronous interactive fusion of visual, semantic, and spatial information within a unified 3D latent space, adaptively adjusting modal contributions through parameter-free uncertainty gating, with medical prior knowledge directly participating in attention computation, avoiding the traditional "process-then-concatenate" separated architecture. On Brain Tumor Segmentation (BraTS) 2020 and 2021 datasets, UMCF+nnU-Net achieves average Dice coefficients of 0.8579 and 0.8977 respectively, with an average 4.18% improvement across mainstream architectures. By deeply integrating clinical knowledge with imaging features, UMCF provides a new technical pathway for multimodal information fusion in precision medicine.