Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentation

• URL: http://arxiv.org/abs/2203.10144v1
• Date: Fri, 18 Mar 2022 19:50:07 GMT
• Title: Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentation
• Authors: An Xu, Wenqi Li, Pengfei Guo, Dong Yang, Holger Roth, Ali Hatamizadeh, Can Zhao, Daguang Xu, Heng Huang, and Ziyue Xu
• Abstract summary: Cross-silo federated learning (FL) has attracted much attention in medical imaging analysis with deep learning in recent years. There can be a gap between the model trained from FL and one from centralized training. We propose a novel training framework FedSM to avoid client issue and successfully close the drift gap.
• Score: 66.44449514373746
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cross-silo federated learning (FL) has attracted much attention in medical imaging analysis with deep learning in recent years as it can resolve the critical issues of insufficient data, data privacy, and training efficiency. However, there can be a generalization gap between the model trained from FL and the one from centralized training. This important issue comes from the non-iid data distribution of the local data in the participating clients and is well-known as client drift. In this work, we propose a novel training framework FedSM to avoid the client drift issue and successfully close the generalization gap compared with the centralized training for medical image segmentation tasks for the first time. We also propose a novel personalized FL objective formulation and a new method SoftPull to solve it in our proposed framework FedSM. We conduct rigorous theoretical analysis to guarantee its convergence for optimizing the non-convex smooth objective function. Real-world medical image segmentation experiments using deep FL validate the motivations and effectiveness of our proposed method.

Related papers

• Federated Semi-supervised Learning for Medical Image Segmentation with intra-client and inter-client Consistency [10.16245019262119]
  Federated learning aims to train a shared model of isolated clients without local data exchange. In this work, we propose a novel federated semi-supervised learning framework for medical image segmentation.
  arXiv  Detail & Related papers  (2024-03-19T12:52:38Z)
• Benchmarking Collaborative Learning Methods Cost-Effectiveness for Prostate Segmentation [39.19170617818745]
  We address a prostate segmentation problem from MRI in a collaborative scenario. To the best of our knowledge, this is the first work in which consensus-based methods (CBM) are used to solve a problem of collaborative learning.
  arXiv  Detail & Related papers  (2023-09-29T09:47:18Z)
• MS Lesion Segmentation: Revisiting Weighting Mechanisms for Federated Learning [92.91544082745196]
  Federated learning (FL) has been widely employed for medical image analysis. FL's performance is limited for multiple sclerosis (MS) lesion segmentation tasks. We propose the first FL MS lesion segmentation framework via two effective re-weighting mechanisms.
  arXiv  Detail & Related papers  (2022-05-03T14:06:03Z)
• Federated Cross Learning for Medical Image Segmentation [23.075410916203005]
  Federated learning (FL) can collaboratively train deep learning models using isolated patient data owned by different hospitals for various clinical applications. A major problem of FL is its performance degradation when dealing with data that are not independently and identically distributed (non-iid)
  arXiv  Detail & Related papers  (2022-04-05T18:55:02Z)
• FedDropoutAvg: Generalizable federated learning for histopathology image classification [11.509801043891837]
  Federated learning (FL) enables collaborative learning of a deep learning model without sharing the data of participating sites. We propose FedDropoutAvg, a new federated learning approach for training a generalizable model. We show that the proposed approach is more generalizable than other state-of-the-art federated training approaches.
  arXiv  Detail & Related papers  (2021-11-25T19:30:37Z)
• Differentially private federated deep learning for multi-site medical image segmentation [56.30543374146002]
  Collaborative machine learning techniques such as federated learning (FL) enable the training of models on effectively larger datasets without data transfer. Recent initiatives have demonstrated that segmentation models trained with FL can achieve performance similar to locally trained models. However, FL is not a fully privacy-preserving technique and privacy-centred attacks can disclose confidential patient data.
  arXiv  Detail & Related papers  (2021-07-06T12:57:32Z)
• Federated Semi-supervised Medical Image Classification via Inter-client Relation Matching [58.26619456972598]
  Federated learning (FL) has emerged with increasing popularity to collaborate distributed medical institutions for training deep networks. This paper studies a practical yet challenging FL problem, named textitFederated Semi-supervised Learning (FSSL) We present a novel approach for this problem, which improves over traditional consistency regularization mechanism with a new inter-client relation matching scheme.
  arXiv  Detail & Related papers  (2021-06-16T07:58:00Z)
• FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space [63.43592895652803]
  Federated learning allows distributed medical institutions to collaboratively learn a shared prediction model with privacy protection. While at clinical deployment, the models trained in federated learning can still suffer from performance drop when applied to completely unseen hospitals outside the federation. We present a novel approach, named as Episodic Learning in Continuous Frequency Space (ELCFS), for this problem. The effectiveness of our method is demonstrated with superior performance over state-of-the-arts and in-depth ablation experiments on two medical image segmentation tasks.
  arXiv  Detail & Related papers  (2021-03-10T13:05:23Z)
• Inverse Distance Aggregation for Federated Learning with Non-IID Data [48.48922416867067]
  Federated learning (FL) has been a promising approach in the field of medical imaging in recent years. A critical problem in FL, specifically in medical scenarios is to have a more accurate shared model which is robust to noisy and out-of distribution clients. We propose IDA, a novel adaptive weighting approach for clients based on meta-information which handles unbalanced and non-iid data.
  arXiv  Detail & Related papers  (2020-08-17T23:20:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.