Federated Learning for Privacy Preserving Intelligent Healthcare Application to Breast Cancer Detection
Abstract
Health data used in building intelligent medical care systems contain sensitive personal information of the patients. Distributed storage, processing and sharing of data poses threats to the data privacy and security. Federated learning (FL) is an emerging approach that allows multiple entities to collaboratively train a model without sharing their data, thus preserving data privacy. This paper explores the implementation of federated learning techniques for deep learning-based breast cancer detection using the publicly available BRCA dataset. The efficacy of both centralized and federated approaches has been examined through various performance metrics. This work is an effort to reduce the gap between privacy-preserving techniques and practical healthcare applications, offering insights into the trade-offs between data privacy and model performance.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.