Research map / Detection and segmentation / CNN features
M-Net: MRI Brain Tumor Sequential Segmentation Network via Mesh-Cast
Jiacheng Lu, Hui Ding, Shiyu Zhang, Guoping Huo
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 Mamba SSM Mesh-Cast sequential module with TPS training (ablation) | M-Net backbone · BraTS 2019 | Dice ET (%): 90.41 -> 91.43 | Improved |
| add Transformer Mesh-Cast module (slice input) (ablation) | M-Net backbone · BraTS 2019 | Dice ET (%): 90.41 -> 90.29 | No clear effect |
| add LSTM Mesh-Cast module (slice input) (ablation) | M-Net backbone · BraTS 2019 | Dice WT (%): 87.17 -> 87.59 | Improved |
| train with TPS instead of slice input (ablation) | M-Net with Mamba SSM · BraTS 2019 | Dice ET (%): 90.65 -> 91.43 | Improved |
| train with TPS instead of slice input (ablation) | M-Net with Transformer · BraTS 2019 | Dice WT (%): 87.24 -> 87.56 | Improved |
| train with TPS instead of slice input (ablation) | M-Net with LSTM · BraTS 2019 | Dice WT (%): 87.59 -> 88.06 | Improved |
| add temporal modeling (T) to channel modeling (T+C) (ablation) | Mesh-Cast · BraTS 2019 | Dice TC (%): 89.28 -> 90.21 | Improved |
| add second ordered phase to shuffled-only training (ablation) | M-Net T+C · BraTS 2019 | Dice WT (%): 88.07 -> 88.38 | Improved |
| add shuffled first phase to ordered-only training (ablation) | M-Net T+C · BraTS 2019 | Dice ET (%): 90.65 -> 91.43 | Improved |
| shuffle first then order, instead of order then shuffle (ablation) | M-Net T+C · BraTS 2019 | Dice ET (%): 91.29 -> 91.43 | Improved |
| shuffled training on backbone without sequential module (ablation) | Backbone · BraTS 2019 | Dice WT (%): 87.17 -> 88.21 | Improved |
| add shuffled training and Mesh-Cast to backbone (ablation) | Backbone shuffled · BraTS 2019 | Dice WT (%): 88.21 -> 88.07 | No clear effect |
Later papers that compared with this method
2 later accepted papers report M-Net as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- SPHERE: From MRI Sampling Mechanisms to Spatial Priors for Generalizable Brain Tumor Segmentation (ECCV 2026 · better on 6 of 6 shared results)
- PGR-Net: Prior-Guided ROI Reasoning Network for Brain Tumor MRI Segmentation (CVPR 2026 · better on 3 of 3 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Incomplete Multi-modal Brain Tumor Segmentation via Learnable Sorting State Space Model (CVPR 2025 · similarity 0.87)
- Upping the Game: How 2D U-Net Skip Connections Flip 3D Segmentation (NeurIPS 2024 · similarity 0.86)
- Semantic-guided Masked Mutual Learning for Multi-modal Brain Tumor Segmentation with Arbitrary Missing Modalities (AAAI 2025 · similarity 0.86)
- SuperLightNet: Lightweight Parameter Aggregation Network for Multimodal Brain Tumor Segmentation (CVPR 2025 · similarity 0.86)
- UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation (NeurIPS 2026 · similarity 0.86)
- E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation (NeurIPS 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.
