Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification
Cheng-Chang Tsai, Kai-Wen Cheng, Chun-Shien Lu
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 FedSDA stain alignment | FedAvg · CAMELYON17 | AUROC: 90.97 -> 93.84 | Improved |
| add FedSDA stain alignment | FedAvg · AGGC22 | AUROC: 78.99 -> 90.38 | Improved |
| add FedSDA stain alignment | FedAvg · AGGC22 | AUPRC: 46.60 -> 64.20 | Improved |
| add FedSDA stain alignment | FedSAM · CAMELYON17 | AUROC: 90.87 -> 93.04 | Improved |
| add FedSDA stain alignment | FedLESAM · CAMELYON17 | AUROC: 90.17 -> 92.68 | Improved |
| add FedSDA stain alignment | FedFA · AGGC22 | AUROC: 82.62 -> 91.79 | Improved |
| replace FedSDA with CCST cross-client style transfer | FedAvg · CAMELYON17 | AUROC: 93.84 -> 71.89 | Hurt |
| replace FedSDA with amp-norm | FedAvg · CAMELYON17 | AUROC: 93.84 -> 77.49 | Hurt |
| use CCST on AGGC22 versus plain FedAvg | FedAvg · AGGC22 | AUROC: 78.99 -> 80.09 | Mixed |
| use CCST instead of FedSDA for structure preservation | FedAvg · MA14+C17+A22 (avg) | SSIM: 0.9969 -> 0.2462 | Hurt |
| use single-layer transformer instead of MLP for stain diffusion (ablation) | FedSDA diffusion model · Stain matrices | Frechet distance: 18.91 -> 0.40 | Improved |
| increase local epochs for diffusion training from 1-4 to 300 (ablation) | FedSDA diffusion model · CAMELYON17 stain matrices | communication rounds to converge | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FedFA — FedFA: Federated Feature Augmentation (ICLR 2023) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- HistoFS: Non-IID Histopathologic Whole Slide Image Classification via Federated Style Transfer with RoI-Preserving (CVPR 2025 · similarity 0.87)
- Point Transformer with Federated Learning for Predicting Breast Cancer HER2 Status from Hematoxylin and Eosin-Stained Whole Slide Images (AAAI 2024 · similarity 0.86)
- FedVCK: Non-IID Robust and Communication-Efficient Federated Learning via Valuable Condensed Knowledge for Medical Image Analysis (AAAI 2025 · similarity 0.86)
- Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation (NeurIPS 2026 · similarity 0.85)
- FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noise (AAAI 2024 · similarity 0.85)
- Federated Modality-Specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation (AAAI 2024 · 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.
