Research map / Label-efficient and robust learning / Domain adaptation and generalization
On Transferability of Histological Tissue Labels in Computational Pathology
Mahdi S. Hosseini, Lyndon Chan, Weimin Huang, Yichen Wang, Danial Hasan, Corwyn Rowsell, Savvas Damaskinos, Konstantinos N. Plataniotis
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 YCbCr-Strong color augmentation (ablation) | HistoNet · ADP HTT classification, 1um | AUC: 0.9594 -> 0.9645 | Improved |
| Add YCbCr-Strong color augmentation (ablation) | HistoNet · ADP HTT classification, 4um | AUC: 0.9136 -> 0.9277 | Improved |
| Add HSV-Light color augmentation (ablation) | HistoNet · ADP HTT classification, 1um | F1: 0.8378 -> 0.8534 | Improved |
| Use YCbCr-Strong instead of HSV-Strong augmentation (ablation) | HistoNet · ADP HTT classification, 1um | AUC: 0.9638 vs 0.9645 | No clear effect |
| Use YCbCr instead of HSV augmentation (training cost) (ablation) | HistoNet · ADP HTT classification, 1um | sec/epoch: 937 -> 569 | Improved |
| Decrease pixel size from 4um to 1um (finer resolution) (ablation) | HistoNet, no color aug · ADP HTT classification | AUC: 0.9136 -> 0.9594 | Improved |
| Decrease pixel size from 4um to 1um (finer resolution) (ablation) | HistoNet, no color aug · ADP HTT classification | sec/epoch: 72 -> 567 | Hurt |
| Use HistoNet architecture instead of ResNet18 | YCbCr-augmented ADP training · ADP HTT classification, 1um | AUC: 0.9521 -> 0.9645 | Improved |
| Add color augmentation (HSV or YCbCr) to Xception-1 (ablation) | Xception-1 · ADP HTT classification, 1um | AUC: 0.9576 -> 0.9567 | No clear effect |
| Add color augmentation to ResNet18 (ablation) | ResNet18 · ADP HTT classification, 1um | AUC: 0.9533 -> 0.9511 | Hurt |
| Use lighter color augmentation (ablation) | HistoNet · CRC tissue classification (zero-shot) | ROC | Improved |
| Add YCbCr-Strong color augmentation (ablation) | HistoNet · HMT tissue classification (zero-shot) | ROC | Improved |
Closest papers by meaning
- Sequential Attention-based Sampling for Histopathological Analysis (NeurIPS 2025 · similarity 0.86)
- Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation (CVPR 2025 · similarity 0.86)
- Dynamic Entity-Masked Graph Diffusion Model for Histopathology Image Representation Learning (AAAI 2025 · similarity 0.85)
- HistoFS: Non-IID Histopathologic Whole Slide Image Classification via Federated Style Transfer with RoI-Preserving (CVPR 2025 · similarity 0.85)
- Memory-Efficient Prompt Tuning for Incremental Histopathology Classification (AAAI 2024 · similarity 0.85)
- Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction (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.
