Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment.
Haeyun LeeYoung Jun ChaiHyunjin JooKyungsu LeeJae Youn HwangSeok-Mo KimKwangsoon KimInn-Chul NamJune Young ChoiHyeong Won YuMyung-Chul LeeHiroo MasuokaAkira MiyauchiKyu Eun LeeSungwan KimHyoun-Joong KongPublished in: JMIR medical informatics (2021)
We demonstrated that the performance of federated learning using decentralized data was comparable to that of conventional deep learning using pooled data. Federated learning might be potentially useful for analyzing medical images while protecting patients' personal information.
Keyphrases
- deep learning
- healthcare
- end stage renal disease
- electronic health record
- ejection fraction
- newly diagnosed
- big data
- chronic kidney disease
- convolutional neural network
- health information
- magnetic resonance imaging
- peritoneal dialysis
- artificial intelligence
- machine learning
- randomized controlled trial
- computed tomography
- clinical trial
- social media