Research map / Detection and segmentation / Open-set and few-shot detection
Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation
Adrian V. Dalca, John Guttag, Mert R. Sabuncu
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 |
|---|---|---|---|
| Use an anatomical prior learned from unpaired segmentation images | CNN-based unsupervised brain MRI segmentation · T1w brain MRI | segmentation quality | Improved |
| Use an anatomical prior learned from T1w segmentations on a different modality | CNN-based unsupervised brain MRI segmentation · T2-FLAIR brain MRI | segmentation plausibility | Improved |
| Use a 3D architecture instead of the 2D architecture (ablation) | Proposed segmentation model · Brain MRI segmentation | segmentation performance | No clear effect |
| Use a standard U-Net with image MSE or mutual information loss instead of the proposed prior-based model | Unsupervised brain MRI segmentation · T1w brain MRI | segmentation quality | Hurt |
Closest papers by meaning
- Teaching AI the Anatomy Behind the Scan: Addressing Anatomical Flaws in Medical Image Segmentation with Learnable Prior (ICCV 2025 · similarity 0.89)
- Mine yOur owN Anatomy: Revisiting Medical Image Segmentation With Extremely Limited Labels (TPAMI 2024 · similarity 0.89)
- Learning Conditional Deformable Templates with Convolutional Networks (NeurIPS 2019 · similarity 0.87)
- Class-Aware Adversarial Transformers for Medical Image Segmentation (NeurIPS 2022 · similarity 0.87)
- Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation (CVPR 2024 · similarity 0.85)
- Generative Medical Segmentation (AAAI 2025 · 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.
