Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data

By Micah J. Sheller, Brandon Edwards, G. Reina, Jason Martin, Sarthak Pati, Aikaterini Kotrotsou, Mikhail Milchenko, Weilin Xu, Daniel Marcus, R. Colen and 1 more. Scientific Reports, 2020

1,493 citations recorded by the source corpus.

Several studies underscore the potential of deep learning in identifying complex patterns, leading to diagnostic and prognostic biomarkers. Identifying sufficiently large and diverse datasets, required for training, is a significant challenge in medicine and can rarely be found in individual institutions. Multi-institutional collaborations based on centrally-shared patient data face privacy and ownership challenges. Federated learning is a novel paradigm for data-private multi-institutional collaborations, where model-learning leverages all available data without sharing data between institutions, by distributing the model-training to the data-owners and aggregating their results. We show that federated learning among 10 institutions results in models reaching 99% of the model quality achieved with centralized data, and evaluate generalizability on data from institutions outside the federation. We further investigate the effects of data distribution across collaborating institutions on model quality and learning patterns, indicating that increased access to data through data private multi-institutional collaborations can benefit model quality more than the errors introduced by the collaborative method. Finally, we compare with other collaborative-learning approaches demonstrating the superiority of federated learning, and discuss practical implementation considerations. Clinical adoption of federated learning is expected to lead to models trained on datasets of unprecedented size, hence have a catalytic impact towards precision/personalized medicine.

Subfields: Artificial Intelligence, Cancer Research, Health Informatics

View Paper: https://www.semanticscholar.org/paper/ee6da0ca07fe062968a66887edddfc8a0034a409

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qiang Yang
2. Philip S. Yu
3. Lichao Sun
4. Dusist Niyato
5. Zehui Xiong
6. Jiawen Kang
7. Jiayu Zhou
8. Chunyan Miao

In Cancer Research

1. Philip S. Yu
2. Qiang Yang
3. Chunyan Miao
4. Barret Zoph
5. Quoc V. Le
6. Ekin Dogus Cubuk

In Health Informatics

1. Leo Anthony Celi
2. Philip S. Yu
3. Angela Zhang
4. James Y. Zou
5. Qiang Yang
6. Lichao Sun

Citations in the corpus

• A Full Dive Into Realizing the Edge-Enabled Metaverse: Visions, Enabling Technologies, and Challenges (2022, background): “, in healthcare [241], data privacy laws may”
• Shifting machine learning for healthcare from development to deployment and from models to data (2022, background): “…learning were found to achieve 99% of the performance of traditional centralized training even with imbalanced datasets or with relatively few samples per institution, thus showing that federated learning can be realistically implemented without sacrificing performance or generalization 77,78 .”
• The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification (2021, methodology): “…approach, which would enable researchers to access potentially unprecedented size of data and hence design more robust and generalizable algorithms [39,45–47]. views of the NIH or of the RSNA R&E Foundation, or the views or policies of the Department of Health and Human Services, nor does mention…”
• Decentralized Federated Learning: A Survey and Perspective (2023, methodology): “The line variant is frequently used as a baseline for comparison due to its ease of implementation, intuitiveness, and efficiency [163], [164], [165], [166].”
• Clinical artificial intelligence quality improvement: towards continual monitoring and updating of AI algorithms in healthcare (2022, background): “The advantage of this option is that it minimizes the burden on the AI-QI team and the model vendor can leverage data from multiple institutions to improve model monitoring and maintenance 97,98 .”
• Federated learning and differential privacy for medical image analysis (2021, methodology): “The steps involved in creations of a mosaic are: (1) removal of non-tissue regions using colour thresholding; (2) grouping the remaining tissue-containing patches into a pre-set number of categories through a clustering algorithm; and (3) randomly selecting a portion of all clustered patches (e.”