Research map / Detection and segmentation / 3D detection and driving
Joint Sequence Learning and Cross-Modality Convolution for 3D Biomedical Segmentation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 multi-modal encoding and cross-modality convolution (ablation) | Encoder-decoder segmentation · BRATS-2015 test | MeanIU: 44.14 -> 45.80 | Helped |
| Add multi-resolution fusion (ablation) | Encoder-decoder segmentation · BRATS-2015 test | MeanIU: 44.14 -> 55.37 | Helped |
| Add multi-modal encoding and CMC to the MRF model (ablation) | Encoder-Decoder + MRF · BRATS-2015 test | MeanIU: 55.37 -> 61.83 | Helped |
| Add two-phase training (ablation) | MME + CMC + MRF · BRATS-2015 test | MeanIU: 61.83 -> 64.02 | Helped |
| Add convLSTM without two-phase training (ablation) | MME + CMC + MRF · BRATS-2015 test | MeanIU: 61.83 -> 62.15 | Helped |
| Combine convLSTM and two-phase training (ablation) | MME + CMC + MRF · BRATS-2015 test | MeanIU: 62.15 -> 73.52 | Helped |
| Add convLSTM (ablation) | Encoder-Decoder · CamVid test | MeanIU: 47.85 -> 48.16 | Helped |
| Add MRF (ablation) | Encoder-Decoder · CamVid test | MeanIU: 47.85 -> 49.91 | Helped |
| Add convLSTM and MRF (ablation) | Encoder-Decoder · CamVid test | MeanIU: 47.85 -> 52.13 | Helped |
| Use two-phase training (ablation) | U-Net · BRATS-2015 test | MeanIU: 54.2 -> 59.3 | Helped |
| Use two-phase training (ablation) | MME + MRF + CMC + convLSTM · BRATS-2015 test | MeanIU: 62.5 -> 73.5 | Helped |
| Use convolutional LSTM with two-phase training | U-Net on BRATS-2015 online evaluation · BRATS-2015 online evaluation, five-fold | Dice Core: 0.6174 -> 0.6835 | Helped |
Closest papers by meaning
- Multi-modal Vision Pre-training for Medical Image Analysis (CVPR 2025 · similarity 0.87)
- E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation (NeurIPS 2024 · similarity 0.85)
- Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention (CVPR 2024 · similarity 0.85)
- Learning Generalized Medical Image Segmentation from Decoupled Feature Queries (AAAI 2024 · similarity 0.84)
- Combinatorial CNN-Transformer Learning with Manifold Constraints for Semi-supervised Medical Image Segmentation (AAAI 2024 · similarity 0.84)
- Upping the Game: How 2D U-Net Skip Connections Flip 3D Segmentation (NeurIPS 2024 · similarity 0.84)
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.