Federated learning for privacy-preserving medical diagnostics
Abstract
The rapid healthcare system digitization has resulted in the creation of huge volumes of sensitive healthcare information, which allows developing Diagnostics based on artificial intelligence (AI). Nonetheless, the issue of data privacy, security and regulatory compliance has constrained the distribution of medical datasets between institutions. Federated Learning (FL) has become a potentially promising paradigm that enables collaborative model training and eliminates the necessity to centralize data, thus maintaining patient privacy and utilizing distributed sources of data.
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.