mlsanityData to 14 Oct 2026

Federated Medical Image Segmentation under Real-World Label Noise: A Benchmark Suite for Noisy Label Learning Method Selection

arXiv 2606.16868 ↗First posted 15 Jun 2026cs.CV cs.AI cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

While federated learning (FL) enables collaborative medical image segmentation without centralizing sensitive data, real-world deployment is frequently complicated by cross-site label imperfections such as contour disagreement, missing or additional structures, and confused labels. Federated noisy label learning (FNLL) aims to mitigate these effects, yet remains underused in practice as existing evidence is largely based on synthetic noise, simplified settings, and limited real-world noisy evaluation. We address this gap by introducing a benchmark suite that combines diverse real-world noisy datasets, deployment-relevant client-noise scenarios, and label-noise-targeted evaluation to support systematic FNLL assessment and informed method selection. The suite combines curated real-world noisy medical image segmentation datasets from diverse sources with a comprehensive federated segmentation framework including various client-noise scenarios and noise-targeted evaluation. The presented suite provides a realistic and discriminative basis for FNLL evaluation in medical image segmentation and establishes a reusable foundation for fair benchmarking, dataset-specific label-noise characterization, and future method development under realistic federated settings. Code is available at https://github.com/MIC-DKFZ/FedSegNoiseBench.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 37 of its 69 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

37 of 69 references.

References · 37

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2020The Future of Digital Health with Federated Learningcited by 633
  3. 2021The Medical Segmentation Decathloncited by 628
  4. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
  5. 2024nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentationcited by 240
  6. 2022Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learntcited by 236
  7. 2023Segment Anything in Medical Imagescited by 227
  8. 2019Deep learning with noisy labels: exploring techniques and remedies in medical image analysiscited by 173
  9. 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 125
  10. 2019Meta Label Correction for Noisy Label Learningcited by 108
  11. 2021MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluationcited by 88
  12. 2022Federated Learning Enables Big Data for Rare Cancer Boundary Detectioncited by 84
25 more
  1. 2021FINE Samples for Learning with Noisy Labelscited by 82
  2. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  3. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  4. 2020Interpreting Chest X-rays via CNNs that Exploit Hierarchical Disease Dependencies and Uncertainty Labelscited by 56
  5. 2022FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clientscited by 46
  6. 2020Robust Federated Learning with Noisy Labelscited by 40
  7. 2024A large-scale multicenter breast cancer DCE-MRI benchmark dataset with expert segmentationscited by 40
  8. 2023FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneitycited by 33
  9. 2019Learning to Segment Skin Lesions from Noisy Annotationscited by 25
  10. 2022IOP-FL: Inside-Outside Personalization for Federated Medical Image Segmentationcited by 22
  11. 2022Industry-Scale Orchestrated Federated Learning for Drug Discoverycited by 19
  12. 2023FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noisecited by 14
  13. 2021Modeling Annotator Preference and Stochastic Annotation Error for Medical Image Segmentationcited by 12
  14. 2024Tackling Noisy Clients in Federated Learning with End-to-end Label Correctioncited by 12
  15. 2023FedNoisy: Federated Noisy Label Learning Benchmarkcited by 11
  16. 2024Deep learning with noisy labels in medical prediction problems: a scoping reviewcited by 10
  17. 2020Less is More: Sample Selection and Label Conditioning Improve Skin Lesion Segmentationcited by 8
  18. 2025Adaptive Label Correction for Robust Medical Image Segmentation with Noisy Labelscited by 8
  19. 2018Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classificationcited by 7
  20. 2025FNBench: Benchmarking Robust Federated Learning against Noisy Labelscited by 6
  21. 2024Real-World Federated Learning in Radiology: Hurdles to overcome and Benefits to gaincited by 5
  22. 2023Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Trainingcited by 4
  23. 2021Pathological Image Segmentation with Noisy Labelscited by 3
  24. 2025Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlookcited by 3
  25. 2024FedIA: Federated Medical Image Segmentation with Heterogeneous Annotation Completenesscited by 2

Built on by

Not cited yet.