A Federated Learning Framework for Breast Cancer Histopathological Image Classification

Quantities and diversities of datasets are vital to model training in a variety of medical image diagnosis applications. However, there are the following problems in real scenes: the required data may not be available in a single institution due to the number of patients or the type of pathology, and it is often not feasible to share patient data due to medical data privacy regulations. This means keeping private data safe is required and has become an obstacle in fusing data from multi-party to train a medical model. To solve the problems, we propose a federated learning framework, which allows knowledge fusion achieved by sharing the model parameters of each client through federated training rather than sharing data. Based on breast cancer histopathological dataset (BreakHis), our federated learning experiments achieve the expected results which are similar to the performances of the centralized learning and verify the feasibility and efficiency of the proposed framework.

Automated summary

Quantities and diversities of datasets are essential for training models in medical image diagnosis. However, problems arise in real scenes due to insufficient availability of required data in a single institution and the inability to share patient data due to privacy regulations. To address these issues, we propose a federated learning framework that allows knowledge fusion by sharing model parameters rather than data. Experimental results based on the BreakHis dataset demonstrate the feasibility and efficiency of the proposed framework.