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

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.

[1]  Min Chen,et al.  Privacy Protection and Intrusion Avoidance for Cloudlet-Based Medical Data Sharing , 2020, IEEE Transactions on Cloud Computing.

[2]  Ian Goodfellow,et al.  Deep Learning with Differential Privacy , 2016, CCS.

[3]  Bradley J. Erickson,et al.  Residual Deep Convolutional Neural Network Predicts MGMT Methylation Status , 2017, Journal of Digital Imaging.

[4]  G. Biros,et al.  Imaging Surrogates of Infiltration Obtained Via Multiparametric Imaging Pattern Analysis Predict Subsequent Location of Recurrence of Glioblastoma. , 2016, Neurosurgery.

[5]  Blaise Agüera y Arcas,et al.  Communication-Efficient Learning of Deep Networks from Decentralized Data , 2016, AISTATS.

[6]  Christos Davatzikos,et al.  Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features , 2017, Scientific Data.

[7]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[8]  Christos Davatzikos,et al.  In Vivo Detection of EGFRvIII in Glioblastoma via Perfusion Magnetic Resonance Imaging Signature Consistent with Deep Peritumoral Infiltration: The ϕ-Index , 2017, Clinical Cancer Research.

[9]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[10]  Yong Fan,et al.  A deep learning model integrating FCNNs and CRFs for brain tumor segmentation , 2017, Medical Image Anal..

[11]  Vitaly Shmatikov,et al.  Privacy-preserving deep learning , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[12]  Luke Macyszyn,et al.  Imaging patterns predict patient survival and molecular subtype in glioblastoma via machine learning techniques. , 2016, Neuro-oncology.

[13]  Tassilo Klein,et al.  Differentially Private Federated Learning: A Client Level Perspective , 2017, ArXiv.

[14]  Raymond Y Huang,et al.  Residual Convolutional Neural Network for the Determination of IDH Status in Low- and High-Grade Gliomas from MR Imaging , 2017, Clinical Cancer Research.

[15]  H. Brendan McMahan,et al.  Learning Differentially Private Recurrent Language Models , 2017, ICLR.

[16]  Bruce R. Rosen,et al.  Distributed deep learning networks among institutions for medical imaging , 2018, J. Am. Medical Informatics Assoc..

[17]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[18]  J. Marc Overhage,et al.  Going Digital: A Survey on Digitalization and Large-Scale Data Analytics in Healthcare , 2016, Proceedings of the IEEE.

[19]  Christos Davatzikos,et al.  Epidermal Growth Factor Receptor Extracellular Domain Mutations in Glioblastoma Present Opportunities for Clinical Imaging and Therapeutic Development. , 2018, Cancer cell.

[20]  Yue Zhao,et al.  Federated Learning with Non-IID Data , 2018, ArXiv.

[21]  Vitaly Shmatikov,et al.  How To Backdoor Federated Learning , 2018, AISTATS.

[22]  R. French Catastrophic forgetting in connectionist networks , 1999, Trends in Cognitive Sciences.