Federated Cross Learning for Medical Image Segmentation

Abstract

Federated learning (FL) can collaboratively train deep learning models using isolated patient data owned by different hospitals for various clinical applications, including medical image segmentation. However, a major problem of FL is its performance degradation when dealing with the data that are not independently and identically distributed (non-iid), which is often the case in medical images. In this paper, we first conduct a theoretical analysis on the FL algorithm to reveal the problem of model aggregation during training on non-iid data. With the insights gained through the analysis, we propose a simple and yet effective method, federated cross learning (FedCross), to tackle this challenging problem. Unlike the conventional FL methods that combine multiple individually trained local models on a server node, our FedCross sequentially trains the global model across different clients in a roundrobin manner, and thus the entire training procedure does not involve any model aggregation steps. To further improve its performance to be comparable with the centralized learning method, we combine the FedCross with an ensemble learning mechanism to compose a federated cross ensemble learning (FedCrossEns) method. Finally, we conduct extensive experiments using a set of public datasets. The experimental results show that the proposed FedCross training strategy outperforms the mainstream FL methods on non-iid data. In addition to improving the segmentation performance, our FedCrossEns can further provide a quantitative estimation of the model uncertainty, demonstrating the effectiveness and clinical significance of our designs. Source code will be made publicly available after paper publication.

Current and Emerging Trends in Medical Image Segmentation With Deep Learning

“…12 More and more research works in medical image segmentation involve an FL scheme [211]. Recently, Xu et al [212] introduced in a new federated cross-learning segmentation approach that handles data that are not independently and identically distributed. Unlike the conventional FL methods that combine multiple individually trained local models on a server node, the proposed method named FedCross consecutively trained the global model across multiple clients in a roundrobin fashion.…”

Regularized Weight Aggregation in Networked Federated Learning for Glioblastoma Segmentation

“…The challenge of data heterogeneity and domain shifting was recently tackled in novel ways by, for example, federated disentanglement learning via disentangling the parameter space into shape and appearance [6] and automated federated averaging based on Dirichlet distribution [22]. Dynamic Re-Weighting mechanisms [12], federated cross ensemble learning [24], and label-agnostic (mixed labels) unified FL formed by a mixture of the client distributions [21] have been recently proposed to relax an unrealistic assumption that each client's training set will be annotated similarly and therefore follows the same image supervision level during the training of an image segmentation model. Although extensive research has been carried out on FL, there is still a need for methods to enable the development of more generalized FL models for clinical use which can effectively deal with statistical heterogeneity in weight aggregation, communication efficiency, and privacy with security.…”

Decentralized Learning in Healthcare: A Review of Emerging Techniques

“…It was demonstrated to enhance the local models' performance following adaptation. The authors in [104] applied a Federated Cross Learning (FedCross) algorithm on prostate cancer MRI segmentation using the same datasets as in [99].…”