Research map / Vision-language and multimodal / Cross-modal learning
Sequential Information Bottleneck Fusion: Towards Robust and Generalizable Multi-Modal Brain Tumor Segmentation
TIANYI LIU, Xi Yang, Wei Wang, Anh Nguyen, Haochuan Jiang, Kaizhu Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add modality reordering strategy (ablation) | SMSN · BRATS20 | Dice WT (%): 85.75 -> 87.14 | Improved |
| add modality reordering strategy (ablation) | SMSN · BRATS20 | Dice TC (%): 76.38 -> 78.80 | Improved |
| add modality reordering strategy (ablation) | SMSN · BRATS20 | Dice ET (%): 63.09 -> 63.00 | Hurt |
| add reconstruction loss Lr (ablation) | SMSN · BRATS20 | Dice TC (%): 76.82 -> 78.80 | Improved |
| add reconstruction loss Lr (ablation) | SMSN · BRATS20 | Dice ET (%): 62.16 -> 63.00 | Hurt |
| add specific feature extraction module with orthogonality loss (ablation) | SMSN · BRATS20 | Dice WT (%): 85.57 -> 87.14 | Improved |
| add specific feature extraction module with orthogonality loss (ablation) | SMSN · BRATS20 | Dice TC (%): 76.19 -> 78.80 | Improved |
| add orthogonality loss Lo (ablation) | SMSN · BRATS20 | Dice TC (%): 76.61 -> 78.80 | Improved |
| add orthogonality loss Lo (ablation) | SMSN · BRATS20 | Dice ET (%): 63.19 -> 63.00 | Hurt |
| use SMSN sequential information bottleneck fusion instead of M2FTrans | M2FTrans · BRATS18 | Dice ET (%): 54.95 -> 62.39 | Improved |
| use SMSN instead of M2FTrans on unseen metastases | M2FTrans · Brain metastases transfer | Dice TC (%): 38.62 -> 45.70 | Improved |
| vary IB hyperparameters beta and gamma (ablation) | SMSN · BRATS18 ET | Dice ET (%): 56.71 -> 62.39 | Mixed |
Closest papers by meaning
- Semantic-guided Masked Mutual Learning for Multi-modal Brain Tumor Segmentation with Arbitrary Missing Modalities (AAAI 2025 · similarity 0.90)
- Incomplete Multi-modal Brain Tumor Segmentation via Learnable Sorting State Space Model (CVPR 2025 · similarity 0.89)
- KMD: Koopman Multi-modality Decomposition for Generalized Brain Tumor Segmentation under Incomplete Modalities (CVPR 2025 · similarity 0.87)
- TMFormer: Token Merging Transformer for Brain Tumor Segmentation with Missing Modalities (AAAI 2024 · similarity 0.87)
- UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation (NeurIPS 2025 · similarity 0.87)
- Federated Modality-Specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
