Research map / Detection and segmentation / Weakly supervised detection and segmentation
HistoSegNet: Semantic Segmentation of Histological Tissue Type in Whole Slide Images
Lyndon Chan, Mahdi S. Hosseini, Corwyn Rowsell, Konstantinos N. Plataniotis, Savvas Damaskinos
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 HistoSegNet instead of DSRG | WSSS on ADP · ADP tuning set, functional types | mIoU: 0.4732 -> 0.5505 | Improved |
| use HistoSegNet instead of SEC | WSSS on ADP · ADP tuning set, functional types | mIoU: 0.3225 -> 0.5505 | Improved |
| use HistoSegNet instead of DSRG | WSSS on ADP · ADP tuning set, morphological types | mIoU: 0.1375 -> 0.2206 | Improved |
| use HistoSegNet instead of SEC | WSSS on ADP · ADP tuning set, morphological types | mIoU: 0.1628 -> 0.2206 | Improved |
| add inter-HTT adjustments after pixel-level segmentation (ablation) | HistoSegNet · ADP tuning set, functional types | mIoU: 0.2059 -> 0.5174 | Improved |
| add inter-HTT adjustments after pixel-level segmentation (ablation) | HistoSegNet · ADP tuning set, morphological types | mIoU: 0.2549 -> 0.2067 | Hurt |
| add segmentation post-processing (fully-connected CRF) (ablation) | HistoSegNet · ADP tuning set, morphological types | mIoU: 0.2067 -> 0.2206 | Improved |
| add segmentation post-processing (fully-connected CRF) (ablation) | HistoSegNet · ADP tuning set, functional types | mIoU: 0.5174 -> 0.5505 | Improved |
| use functional types instead of morphological types | HistoSegNet · ADP tuning set | mIoU: 0.2206 -> 0.5505 | Improved |
| increase tumor grade from healthy to poorly differentiated | HistoSegNet · GlaS Challenge | average G.O confidence score: 0.9750 -> 0.6628 | Hurt |
| increase tumor grade from healthy to poorly differentiated | HistoSegNet · GlaS Challenge, single gland mode | mean Dice: 0.5970 -> 0.4102 | Hurt |
| increase tumor grade from healthy to poorly differentiated | HistoSegNet · GlaS Challenge, single gland mode | mean Hausdorff distance: 130.48 -> 170.20 | Hurt |
Closest papers by meaning
- Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis (CVPR 2024 · similarity 0.86)
- Rotation-Agnostic Image Representation Learning for Digital Pathology (CVPR 2024 · similarity 0.86)
- Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation (CVPR 2025 · similarity 0.86)
- Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology (NeurIPS 2025 · similarity 0.86)
- HistoFS: Non-IID Histopathologic Whole Slide Image Classification via Federated Style Transfer with RoI-Preserving (CVPR 2025 · similarity 0.86)
- PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization (NeurIPS 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.
