Research map / 3D vision / 3D generation
M3T: Three-Dimensional Medical Image Classifier Using Multi-Plane and Multi-Slice Transformer
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 |
|---|---|---|---|
| Combine 3D CNN, 2D CNN, and Transformer in M3T | AD classification from 3D MRI · ADNI | AUC: 0.9530 -> 0.9634 | Helped |
| Combine 3D CNN, 2D CNN, and Transformer in M3T | AD classification from 3D MRI · AIBL | AUC: 0.9179 -> 0.9258 | Helped |
| Combine 3D CNN, 2D CNN, and Transformer in M3T | AD classification from 3D MRI · OASIS | accuracy: 0.8261 -> 0.8526 | Helped |
| Add the initial 3D CNN block (ablation) | M3T · ADNI | AUC: 0.9515 -> 0.9634 | Helped |
| Add the initial 3D CNN block (ablation) | M3T · AIBL | AUC: 0.8896 -> 0.9258 | Helped |
| Add the 2D CNN block (ablation) | M3T · ADNI | AUC: 0.9236 -> 0.9634 | Helped |
| Add the 2D CNN block (ablation) | M3T · OASIS | AUC: 0.8340 -> 0.8961 | Helped |
| Add the Transformer block (ablation) | M3T · ADNI | AUC: 0.9445 -> 0.9634 | Helped |
| Add the Transformer block (ablation) | M3T · OASIS | AUC: 0.8727 -> 0.8961 | Helped |
| Use multi-slice extraction instead of single-slice extraction (ablation) | M3T · ADNI | AUC: 0.9086 -> 0.9634 | Helped |
| Use all three planes rather than only coronal slices (ablation) | M3T · AIBL | AUC: 0.9101 -> 0.9258 | Helped |
| Use all three planes rather than only sagittal slices (ablation) | M3T · OASIS | AUC: 0.8691 -> 0.8961 | Helped |
Closest papers by meaning
- Revisiting MAE Pre-training for 3D Medical Image Segmentation (CVPR 2025 · similarity 0.86)
- E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation (NeurIPS 2024 · similarity 0.84)
- Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification (NeurIPS 2024 · similarity 0.84)
- Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation (NeurIPS 2024 · similarity 0.84)
- Autoregressive Sequence Modeling for 3D Medical Image Representation (AAAI 2025 · similarity 0.84)
- Enhancing vision-language models for medical imaging: bridging the 3D gap with innovative slice selection (NeurIPS 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.