Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation

By Micah J. Sheller, G. Reina, Brandon Edwards, Jason Martin, S. Bakas. 2018

583 citations recorded by the source corpus.

Deep learning models for semantic segmentation of images require large amounts of data. In the medical imaging domain, acquiring sufficient data is a significant challenge. Labeling medical image data requires expert knowledge. Collaboration between institutions could address this challenge, but sharing medical data to a centralized location faces various legal, privacy, technical, and data-ownership challenges, especially among international institutions. In this study, we introduce the first use of federated learning for multi-institutional collaboration, enabling deep learning modeling without sharing patient data. Our quantitative results demonstrate that the performance of federated semantic segmentation models (Dice=0.852) on multimodal brain scans is similar to that of models trained by sharing data (Dice=0.862). We compare federated learning with two alternative collaborative learning methods and find that they fail to match the performance of federated learning.

How researchers see this paper

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

Citations in the corpus

FedML: A Research Library and Benchmark for Federated Machine Learning (2020, background): “…computer vision [77, 78], natural language processing [79, 80, 81, 82, 83], ﬁnance [74, 35, 84], transportation [85, 86, 87, 88, 89, 90, 91, 92, 93, 94], digital health [95, 96, 97, 98, 99, 100, 101], recommendation [102, 103, 104, 105, 106, 107], robotics [108, 109], and smart cities [110, 111].”
A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond (2021, methodology): “Sheller et al. [69] and Li et al. [70] focused on medical image prediction for brain tumor segmentation while considering FL.”
BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning (2019, methodology): “The traditional FL concept has recently been applied to medical image analysis for 2-class segmentation of brain tumors [9], demonstrating its feasibility.”
FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space (2021, background): “Although FL has witnessed some pilot progress on medical image segmentation tasks [4, 44, 49], all existing works only focus on improving model performance on the internal clients, while neglecting model generalizability onto unseen domains outside the federation.”
Model Aggregation via Good-Enough Model Spaces (2018, background): “This scenario can face many of the challenges described above, as hospitals operate under strict privacy practices, and may face legal, administrative, or ethical constraints prohibiting a shared connected network for training [3, 16, 23, 28].”
Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results (2020, background): “In the medical imaging ﬁeld, multi-institutional deep learning without sharing patient data was ﬁrstly investigated in [15].”
End-to-end privacy preserving deep learning on multi-institutional medical imaging (2021, methodology): “We selected the hub-and-spoke system topology due to its reported improved final model performance over techniques such as incremental or cyclical training 5,43 and its higher flexibility with respect to node availability and asynchronous training 53 .”
A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, methodology): “[84] present the first use of FL for multi-institutional DL model without sharing patient data and report similar brain lesion segmentation performances between the models trained in a federated or centralized way.”
Federated learning enables big data for rare cancer boundary detection (2022, methodology): “The exact 49 site IDs are: 1, 2, 3, 4, 5, 6, 7, 9, 10, 12, 13, 14, 15, 16, 17, 18, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 44, 45, 46, 48, 49, 50, 52, 53, 54, 56, 59, 60.”
Shifting machine learning for healthcare from development to deployment and from models to data (2022, background): “…focused on empirically evaluating model-design parameters, and on logistical decisions to optimize model performance and overcome the unique implementation challenges of federated learning, such as bottlenecks in protecting privacy and in tackling the statistical heterogeneity of the data 75,76 .”
Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data (2020, methodology): “For epochs per institution per cycle during CIIL, we used 1, as this value produced the best results in previous work 14,15 .”
Privacy Preserving Machine Learning with Homomorphic Encryption and Federated Learning (2021, background): “In the medical field, patients’ medical data are sensitive, thus federated learning is very useful [40,41].”