Research map / 3D vision / Depth and stereo
Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation
Read the paperCheck 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 deep-architecture BDC-LSTM RNN on top of FCN (ablation) | kU-Net FCN · In-house fungus | pixel error: 0.0242 -> 0.0215 | Helped |
| add deep-architecture BDC-LSTM RNN on top of FCN (ablation) | kU-Net FCN · ISBI neuron | V_rand: 0.9749 -> 0.9753 | Helped |
| add deep-architecture BDC-LSTM RNN on top of FCN (ablation) | kU-Net FCN · ISBI neuron | V_info: 0.9869 -> 0.9870 | No clear effect |
| add simple stacked BDC-LSTM RNN on top of FCN (ablation) | kU-Net FCN · ISBI neuron | V_rand: 0.9749 -> 0.9742 | No clear effect |
| add simple stacked BDC-LSTM RNN on top of FCN (ablation) | kU-Net FCN · In-house fungus | pixel error: 0.0242 -> 0.0241 | No clear effect |
| deep RNN with subsampling instead of simply stacking BDC-LSTMs (ablation) | FCN+RNN · In-house fungus | pixel error: 0.0241 -> 0.0215 | Helped |
| deep RNN with subsampling instead of simply stacking BDC-LSTMs (ablation) | FCN+RNN · ISBI neuron | V_rand: 0.9742 -> 0.9753 | Helped |
| use kU-Net FCN instead of U-Net | segmentation FCN · ISBI neuron | V_rand: 0.9728 -> 0.9749 | Helped |
| use kU-Net FCN instead of U-Net | segmentation FCN · In-house fungus | pixel error: 0.0263 -> 0.0242 | Helped |
| anisotropy-aware FCN+RNN vs 3D convolution | segmentation · In-house fungus | pixel error: 0.0630 -> 0.0215 | Helped |
| anisotropy-aware FCN+RNN vs Tri-Planar | segmentation · ISBI neuron | V_rand: 0.8462 -> 0.9753 | Helped |
| FCN+deep RNN vs Pyramid-LSTM | segmentation · ISBI neuron | V_rand: 0.9677 -> 0.9753 | Helped |
Closest papers by meaning
- Upping the Game: How 2D U-Net Skip Connections Flip 3D Segmentation (NeurIPS 2024 · similarity 0.90)
- A New Ensemble Learning Framework for 3D Biomedical Image Segmentation (AAAI 2019 · similarity 0.89)
- nnWNet: Rethinking the Use of Transformers in Biomedical Image Segmentation and Calling for a Unified Evaluation Benchmark (CVPR 2025 · similarity 0.87)
- E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation (NeurIPS 2024 · similarity 0.87)
- Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation (NeurIPS 2024 · similarity 0.86)
- UniPro: Unified Multi-Mode Medical Image Segmentation from 2D Images to 3D Volumes via Propagation (NeurIPS 2026 · similarity 0.85)
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.