FedHisto-PAST: Parameter-Efficient Stain-Aware Federated Learning for Cross-Site Lung Histopathology Classification
Not on the map. Why?
Abstract (arXiv)
Cross-site lung histopathology classification must account for stain variation, non-IID client data, missing classes, and the cost of adapting large pathology encoders. This study evaluates FedHisto-PAST v2 for three-way classification of adenocarcinoma (ACA), Normal, and squamous cell carcinoma (SCC). FedHisto-PAST v2 combines a frozen HIBOU-B foundation model with parameter-efficient adaptation, stain-conditioned paired-view prediction and feature consistency, reliability-aware prototype learning, and adaptive federated aggregation. Experiments used a five-client, non-IID, raw-data-local simulation with fixed internal evaluation, client-level analysis, component ablations, communication accounting, and a development-influenced exploratory LungHist700 cohort. All principal methods achieved near- ceiling internal performance, which limited discrimination on the fixed split. On LungHist700, FedHisto- PAST v2 achieved a Macro-F1 of 0.728560 and a balanced accuracy of 0.730454. Higher recognition of Normal and SCC was accompanied by lower ACA recall, and calibration remained imperfect. Prediction-level consistency was the only component with a clearly supported independent contribution in the external ablation analysis. Feature consistency and prototype regularization showed no conclusive independent overall gains in Macro-F1. The framework updated 1.253841% of the model parameters. The results provide exploratory cross-dataset evidence for stain-aware, parameter-efficient federation; they do not establish formal privacy, patient-level independence, prospective deployment, or clinical validation.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 42 references that are in the map. First posted on arXiv 25 Sep 2026.
Builds on
21 of 42 references.
References · 21
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
- 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
- 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
- 2024Multimodal Whole Slide Foundation Model for Pathologycited by 162
- 2020Siloed Federated Learning for Multi-Centric Histopathology Datasetscited by 61
- 2024Hibou: A Family of Foundational Vision Transformers for Pathologycited by 57
- 2020Federated Learning for Computational Pathology on Gigapixel Whole Slide Imagescited by 54
- 2024Benchmarking foundation models as feature extractors for weakly-supervised computational pathologycited by 49
- 2022WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinomacited by 36
9 more
- 2022Nuclei instance segmentation and classification in histopathology images with StarDistcited by 31
- 2022Federated Stain Normalization for Computational Pathologycited by 11
- 2025HistoViT: Vision Transformer for Accurate and Scalable Histopathological Cancer Diagnosiscited by 9
- 2023FedSODA: Federated Cross-assessment and Dynamic Aggregation for Histopathology Segmentationcited by 3
- 2024FMDNN: A Fuzzy-guided Multi-granular Deep Neural Network for Histopathological Image Classificationcited by 3
- 2024FedDP: Privacy-preserving method based on federated learning for histopathology image segmentationcited by 3
- 2025FedWSIDD: Federated Whole Slide Image Classification via Dataset Distillationcited by 3
- 2025FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classificationcited by 2
- 2026FedStain: Modeling Higher-Order Stain Statistics for Federated Domain Generalization in Computational Pathologycited by 1
Built on by
Not cited yet.