Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 11, 2025Open Access

A Multi-Modal Fusion Framework for Brain Tumor Segmentation Based on 3D Spatial-Language-Vision Integration and Bidirectional Interactive Attention Mechanism

View Full Paper
Ask AI
Bookmark
Share

Authors

MZM. ZhangKPKaiwen Pan

Discussion

Loading...

Member takes

Overview

A novel approach improves segmentation accuracy in brain tumor detection using multi-modal information.

Key Points

  • The method achieved an average Dice coefficient of 0.8505 for brain tumor segmentation.
  • Evaluated on the BraTS 2020 dataset, the method outperformed SCAU-Net and 3D U-Net.
  • The framework integrates 3D MRI data with clinical descriptions using a semantic fusion adapter.
  • Ablation studies highlighted the importance of semantic and spatial modules for boundary precision.

Cite This Study

Zhang et al. (2025) studied this question.

synapsesocial.com/papers/68e9b2e4ba7d64b6fc133202https://doi.org/10.21203/rs.3.rs-7112498/v1
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Multimodal Fusion for Enhanced Semantic Segmentation in Brain Tumor Imaging: Integrating Deep Learning and Guided Filtering Via Advanced 3D Semantic Segmentation Architectures2024 · 11 citations
  2. 2A Multimodal Dense Parallel Global Attention Mechanism for Brain Tumor Image Segmentation2026
  3. 3Brain tumor segmentation by combining MultiEncoder UNet with wavelet fusion2024 · 1 citations
  4. 4Brain tumor image segmentation algorithm based on multimodal feature fusion of Bayesian weight distribution2024 · 1 citations
  5. 5Intelligent delineation of breast tumor ROI based on multimodal feature fusion2026