Research map / Detection and segmentation / Weakly supervised detection and segmentation
Semantic Segmentation for Histopathology using Learned Regularization based on Global Proportions
Yangping Li, Thomas Pinetz, Michael Hölzel, Marieta Toma, Alexander Effland
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 second-stage variational refinement to the first-stage posterior | VSLP_Diff. · RINGS | Dice: 0.775 -> 0.819 | Improved |
| add second-stage variational refinement to the first-stage posterior | VSLP_GMM · BCSS | Dice: 0.763 -> 0.786 | Improved |
| add second-stage refinement on in-house three-class data | VSLP_Diff. · In-house renal CD31 (3 classes) | F1: 0.934 -> 0.934 | No clear effect |
| use VSLP_ULA instead of first stage on BCSS | VSLP_ULA · BCSS | Dice: 0.763 -> 0.69 | Hurt |
| use overlapping patches 224 stride 150 instead of stride 224 (ablation) | VSLP_Diff. · RINGS | Dice: 0.7712 -> 0.8195 | Improved |
| use patch 224 stride 150 instead of patch 384 stride 250 (ablation) | VSLP_Diff. · RINGS | Dice: 0.7936 -> 0.8195 | Improved |
| increase TTA rotations from 24 to 360 (ablation) | VSLP_GMM · RINGS | Dice: 0.7664 -> 0.8013 | Improved |
| increase TTA rotations from 24 to 360 (ablation) | VSLP_Diff. · RINGS | Dice: 0.7665 -> 0.8195 | Improved |
| increase TTA rotations from 180 to 360 (ablation) | VSLP_Diff. · RINGS | Dice: 0.8310 -> 0.8195 | No clear effect |
| use true global proportions instead of random values (ablation) | VSLP_Diff. · RINGS | Dice: 0.5518 -> 0.819 | Improved |
| add the learned regularizer (ablation) | VSLP_ULA · RINGS | Dice: 0.3041 -> 0.829 | Improved |
| add the learned regularizer (ablation) | VSLP_GMM · RINGS | Dice: 0.0600 -> 0.801 | Improved |
Closest papers by meaning
- MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation (NeurIPS 2025 · similarity 0.87)
- Weakly Supervised Gland Segmentation with Class Semantic Consistency and Purified Labels Filtration (AAAI 2025 · similarity 0.87)
- Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology (NeurIPS 2025 · similarity 0.87)
- Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation (CVPR 2025 · similarity 0.86)
- Neighbor Does Matter: Density-Aware Contrastive Learning for Medical Semi-supervised Segmentation (AAAI 2025 · similarity 0.86)
- GapMatch: Bridging Instance and Model Perturbations for Enhanced Semi-Supervised Medical Image 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.
