Saved in:
Bibliographic Details
Main Authors: Wang, Pochuan, Shen, Chen, Oda, Masahiro, Fuh, Chiou-Shann, Mori, Kensaku, Wang, Weichung, Roth, Holger R.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.18833
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915580461711360
author Wang, Pochuan
Shen, Chen
Oda, Masahiro
Fuh, Chiou-Shann
Mori, Kensaku
Wang, Weichung
Roth, Holger R.
author_facet Wang, Pochuan
Shen, Chen
Oda, Masahiro
Fuh, Chiou-Shann
Mori, Kensaku
Wang, Weichung
Roth, Holger R.
contents In medical imaging, developing generalized segmentation models that can handle multiple organs and lesions is crucial. However, the scarcity of fully annotated datasets and strict privacy regulations present significant barriers to data sharing. Federated Learning (FL) allows decentralized model training, but existing FL methods often struggle with partial labeling, leading to model divergence and catastrophic forgetting. We propose ConDistFL, a novel FL framework incorporating conditional distillation to address these challenges. ConDistFL enables effective learning from partially labeled datasets, significantly improving segmentation accuracy across distributed and non-uniform datasets. In addition to its superior segmentation performance, ConDistFL maintains computational and communication efficiency, ensuring its scalability for real-world applications. Furthermore, ConDistFL demonstrates remarkable generalizability, significantly outperforming existing FL methods in out-of-federation tests, even adapting to unseen contrast phases (e.g., non-contrast CT images) in our experiments. Extensive evaluations on 3D CT and 2D chest X-ray datasets show that ConDistFL is an efficient, adaptable solution for collaborative medical image segmentation in privacy-constrained settings.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18833
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Federated Learning with Partially Labeled Data: A Conditional Distillation Approach
Wang, Pochuan
Shen, Chen
Oda, Masahiro
Fuh, Chiou-Shann
Mori, Kensaku
Wang, Weichung
Roth, Holger R.
Computer Vision and Pattern Recognition
In medical imaging, developing generalized segmentation models that can handle multiple organs and lesions is crucial. However, the scarcity of fully annotated datasets and strict privacy regulations present significant barriers to data sharing. Federated Learning (FL) allows decentralized model training, but existing FL methods often struggle with partial labeling, leading to model divergence and catastrophic forgetting. We propose ConDistFL, a novel FL framework incorporating conditional distillation to address these challenges. ConDistFL enables effective learning from partially labeled datasets, significantly improving segmentation accuracy across distributed and non-uniform datasets. In addition to its superior segmentation performance, ConDistFL maintains computational and communication efficiency, ensuring its scalability for real-world applications. Furthermore, ConDistFL demonstrates remarkable generalizability, significantly outperforming existing FL methods in out-of-federation tests, even adapting to unseen contrast phases (e.g., non-contrast CT images) in our experiments. Extensive evaluations on 3D CT and 2D chest X-ray datasets show that ConDistFL is an efficient, adaptable solution for collaborative medical image segmentation in privacy-constrained settings.
title Federated Learning with Partially Labeled Data: A Conditional Distillation Approach
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.18833