Research map / Detection and segmentation / Open-set and few-shot detection
Focus, Segment and Erase: An Efficient Network for Multi-Label Brain Tumor Segmentation
Xuan Chen, Jun Hao Liew, Wei Xiong, Chee-Kong Chui, Sim-Heng Ong
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 tumor region pooling (ablation) | Res-UNet baseline · BraTS 2015 (54-case validation split) | Dice, whole tumor: 0.744 -> 0.751 | Improved |
| add tumor region pooling (ablation) | Res-UNet baseline · BraTS 2015 (54-case validation split) | Dice, tumor core: 0.686 -> 0.735 | Improved |
| add tumor region pooling (ablation) | Res-UNet baseline · BraTS 2015 (54-case validation split) | Dice, active tumor: 0.721 -> 0.688 | Hurt |
| add tumor region pooling (ablation) | Res-UNet baseline · BraTS 2015 (54-case validation split) | mean IoU, non-enhancing core (%): 22.1 -> 24.6 | Improved |
| replace one-stage multi-label with cascaded binary classifiers (ablation) | Model 2 · BraTS 2015 (54-case validation split) | Dice, whole tumor: 0.751 -> 0.890 | Improved |
| replace one-stage multi-label with cascaded binary classifiers (ablation) | Model 2 · BraTS 2015 (54-case validation split) | Dice, tumor core: 0.735 -> 0.776 | Improved |
| replace one-stage multi-label with cascaded binary classifiers (ablation) | Model 2 · BraTS 2015 (54-case validation split) | mean IoU, non-enhancing core (%): 24.6 -> 28.1 | Improved |
| add erasing between binary classifiers (no context) (ablation) | Model 3 · BraTS 2015 (54-case validation split) | Dice, whole tumor: 0.890 -> 0.891 | No clear effect |
| add context branch to erasing cascade (ablation) | Model 4 · BraTS 2015 (54-case validation split) | Dice, active tumor: 0.711 -> 0.734 | Improved |
| add context branch to erasing cascade (ablation) | Model 4 · BraTS 2015 (54-case validation split) | Dice, tumor core: 0.775 -> 0.782 | Improved |
| add erasing and context to cascaded binary classifiers (ablation) | Model 3 · BraTS 2015 (54-case validation split) | Dice, active tumor: 0.708 -> 0.734 | Improved |
| add erasing and context to cascaded binary classifiers (ablation) | Model 3 · BraTS 2015 (54-case validation split) | sensitivity, active tumor: 0.677 -> 0.745 | Improved |
Closest papers by meaning
- SuperLightNet: Lightweight Parameter Aggregation Network for Multimodal Brain Tumor Segmentation (CVPR 2025 · similarity 0.85)
- Semantic-guided Masked Mutual Learning for Multi-modal Brain Tumor Segmentation with Arbitrary Missing Modalities (AAAI 2025 · similarity 0.85)
- Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains (NeurIPS 2025 · similarity 0.84)
- ZePT: Zero-Shot Pan-Tumor Segmentation via Query-Disentangling and Self-Prompting (CVPR 2024 · similarity 0.84)
- Incomplete Multi-modal Brain Tumor Segmentation via Learnable Sorting State Space Model (CVPR 2025 · similarity 0.84)
- Federated Modality-Specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation (AAAI 2024 · similarity 0.83)
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.
