FedDropoutAvg: Generalizable federated learning for histopathology image classification

Abstract

Federated learning (FL) enables collaborative learning of a deep learning model without sharing the data of participating sites. FL in medical image analysis tasks is relatively new and open for enhancements. In this study, we propose FedDropoutAvg, a new federated learning approach for training a generalizable model. The proposed method takes advantage of randomness, both in client selection and also in federated averaging process. We compare FedDropoutAvg to several algorithms in an FL scenario for real-world multi-site histopathology image classification task. We show that with FedDropoutAvg, the final model can achieve performance better than other FL approaches and closer to a classical deep learning model that requires all data to be shared for centralized training. We test the trained models on a large dataset consisting of 1.2 million image tiles from 21 different centers. To evaluate the generalization ability of the proposed approach, we use held-out test sets from centers whose data was used in the FL and for unseen data from other independent centers whose data was not used in the federated training. We show that the proposed approach is more generalizable than other state-of-the-art federated training approaches. To the best of our knowledge, ours is the first study to use a randomized client and local model parameter selection procedure in a federated setting for a medical image analysis task.

A Comprehensive Survey on Federated Learning in the Healthcare Area: Concept and Applications

“…Differentially private federated learning is proposed as a potential technique for learning from distributed medical data, such as histopathology scans [112][113][114]. Federated learning enables the training of models without openly disclosing patient information, reducing privacy and confidentiality concerns related to healthcare data [115].…”

Federated Learning for Computer-Aided Diagnosis of Glaucoma Using Retinal Fundus Images

“…The first two strategies are part of one of the initial studies done on FL and serve as the standard baseline for FL strategies. The remaining three were chosen as they have often been mentioned and used as benchmarks for multiple studies [29][30][31][32]. FedAvg aggregates the clients' weights by performing a weighted average to generate the new global model.…”

Collaborative Colorectal Cancer Classification on Highly Class Imbalanced Data Setting via Federated Neural Style Transfer Based Data Augmentation

“…They also prevent data leakage by not sharing the statistics of the collaborator-specific layer activations and benchmarked the model on Camelyon 16 and Camelyon 17 breast cancer datasets [11]. Gunesli et al [12] proposed FedDropoutAvg which is a novel FL model aggregation method inspired from the well-known DL regularization DropOut method and benchmarked this proposed method on the CRC dataset of TCGA portal. It is reported that the FedDropOutAvg method reached to the closest level of centralized training compared to the FedProx and FedAvg [12].…”

“…Gunesli et al [12] proposed FedDropoutAvg which is a novel FL model aggregation method inspired from the well-known DL regularization DropOut method and benchmarked this proposed method on the CRC dataset of TCGA portal. It is reported that the FedDropOutAvg method reached to the closest level of centralized training compared to the FedProx and FedAvg [12].…”