mlsanityData to 7 Oct 2026

FedDis: Disentangled Federated Learning for Unsupervised Brain Pathology Segmentation

arXiv 2103.03705 ↗First posted 5 Mar 2021eess.IV cs.CV cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

In recent years, data-driven machine learning (ML) methods have revolutionized the computer vision community by providing novel efficient solutions to many unsolved (medical) image analysis problems. However, due to the increasing privacy concerns and data fragmentation on many different sites, existing medical data are not fully utilized, thus limiting the potential of ML. Federated learning (FL) enables multiple parties to collaboratively train a ML model without exchanging local data. However, data heterogeneity (non-IID) among the distributed clients is yet a challenge. To this end, we propose a novel federated method, denoted Federated Disentanglement (FedDis), to disentangle the parameter space into shape and appearance, and only share the shape parameter with the clients. FedDis is based on the assumption that the anatomical structure in brain MRI images is similar across multiple institutions, and sharing the shape knowledge would be beneficial in anomaly detection. In this paper, we leverage healthy brain scans of 623 subjects from multiple sites with real data (OASIS, ADNI) in a privacy-preserving fashion to learn a model of normal anatomy, that allows to segment abnormal structures. We demonstrate a superior performance of FedDis on real pathological databases containing 109 subjects; two publicly available MS Lesions (MSLUB, MSISBI), and an in-house database with MS and Glioblastoma (MSI and GBI). FedDis achieved an average dice performance of 0.38, outperforming the state-of-the-art (SOTA) auto-encoder by 42% and the SOTA federated method by 11%. Further, we illustrate that FedDis learns a shape embedding that is orthogonal to the appearance and consistent under different intensity augmentations.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 5 Mar 2021.

Builds on

18 of 32 references.

References · 18

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  4. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  5. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  6. 2020The Future of Digital Health with Federated Learningcited by 625
  7. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  8. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 303
  9. 2019Privacy-preserving Federated Brain Tumour Segmentationcited by 169
  10. 2018Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentationcited by 148
  11. 2020Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Studycited by 146
  12. 2020Federated Visual Classification with Real-World Data Distributioncited by 126
6 more
  1. 2020Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Resultscited by 122
  2. 2020Fairness by Learning Orthogonal Disentangled Representationscited by 76
  3. 2019Disentangled Representation Learning in Cardiac Image Analysiscited by 69
  4. 2020Siloed Federated Learning for Multi-Centric Histopathology Datasetscited by 61
  5. 2018Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearancecited by 58
  6. 2019Unsupervised Deformable Registration for Multi-Modal Images via Disentangled Representationscited by 52

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 8; 2023: 1; 2024: 5; 2025: 1.

19 papers.

Sort:

  1. 2022Improving Generalization in Federated Learning by Seeking Flat Minimacited by 98
  2. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  3. 2022FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Drivingcited by 41
  4. 2022Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learningcited by 35
  5. 2022One Model to Unite Them All: Personalized Federated Learning of Multi-Contrast MRI Synthesiscited by 22
  6. 2023Federated Learning for Computer Visioncited by 22
  7. 2021Algorithm Fairness in AI for Medicine and Healthcarecited by 21
  8. 2021Memory-aware curriculum federated learning for breast cancer classificationcited by 20
  9. 2022Federated Cycling (FedCy): Semi-supervised Federated Learning of Surgical Phasescited by 18
  10. 2022Distributed Contrastive Learning for Medical Image Segmentationcited by 16
  11. 2024From Challenges and Pitfalls to Recommendations and Opportunities: Implementing Federated Learning in Healthcarecited by 16
  12. 2024Federated Modality-specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentationcited by 8
7 more
  1. 2022MouseGAN++: Unsupervised Disentanglement and Contrastive Representation for Multiple MRI Modalities Synthesis and Structural Segmentation of Mouse Braincited by 6
  2. 2025Advanced Deep Learning and Large Language Models: Comprehensive Insights for Cancer Detectioncited by 4
  3. 2022Enhancing Fairness of Visual Attribute Predictorscited by 3
  4. 2024FedGS: Federated Gradient Scaling for Heterogeneous Medical Image Segmentationcited by 1
  5. 2024FeDETR: a Federated Approach for Stenosis Detection in Coronary Angiographycited by 1
  6. 2021Segmentation of Brain MRI using an Altruistic Harris Hawks' Optimization algorithmcited by 0
  7. 2024Unsupervised Federated Optimization at the Edge: D2D-Enabled Learning without Labelscited by 0