Using federated data sources and Varian Learning Portal framework to train a neural network model for automatic organ segmentation |
| |
| Institution: | 1. Varian Medical Systems Finland Oy, Paciuksenkatu 21, FI-00270 Helsinki, Finland;2. Varian Medical Systems Deutschland GmbH, Alsfelder Straße 6, 64289 Darmstadt, Germany;3. Varian Medical Systems, Inc., 3100 Hansen Way, Palo Alto, CA 94304, USA;1. Department of Ophthalmology, Oregon Health & Science University, Portland, Oregon;2. Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, Massachusetts;3. Center for Clinical Data Science, Massachusetts General Hospital and Brigham and Women’s Hospital, Boston, Massachusetts;4. School of Computer Science, University of Lincoln, Lincoln, United Kingdom;5. Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, Illinois;6. Center for Biomedical Informatics Research, Stanford University School of Medicine, Stanford, California;7. National Eye Institute, National Institutes of Health, Bethesda, Maryland;1. Associate Professor of Radiology, Northwestern University Feinberg School of Medicine, Chicago, Illinois;2. Vice-Chair of Imaging Informatics, Ann & Robert H. Lurie Children’s Hospital of Chicago, Illinois;1. Facultad de Enfermería. Grupo Perspectivas del Cuidado. Fundación Universitaria de Ciencias de la Salud, Bogotá, Colombia;2. Facultad de Enfermería, programa de Enfermería en cuidado crítico del adulto. Fundación Universitaria de Ciencias de la Salud, Bogotá, Colombia;3. Servicio de Medicina Crítica y Cuidado Intensivo. Centro de Investigación en Medicina Crítica y Aguda. Fundación Universitaria de Ciencias de la Salud FUCS–Hospital de San José, Hospital Infantil de San José, Bogotá, Colombia;1. Center for Ethics, Emory University, Atlanta, Georgia;2. Director of the Institutional Review Board, Emory University, Atlanta, Georgia;3. Vice Chair of Health Policy and Practice, Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, Georgia;4. Vice Chair for Imaging Infomatics, Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, Georgia;5. Department of Computational Mathematics, Science and Engineering, Department of Biomedical Engineering and Radiology, Michigan State University, East Lansing, Michigan |
| |
| Abstract: | PurposeIn this study we trained a deep neural network model for female pelvis organ segmentation using data from several sites without any personal data sharing. The goal was to assess its prediction power compared with the model trained in a centralized manner.MethodsVarian Learning Portal (VLP) is a distributed machine learning (ML) infrastructure enabling privacy-preserving research across hospitals from different regions or countries, within the framework of a trusted consortium. Such a framework is relevant in the case when there is a high level of trust among the participating sites, but there are legal restrictions which do not allow the actual data sharing between them. We trained an organ segmentation model for the female pelvic region using the synchronous data distributed framework provided by the VLP.ResultsThe prediction performance of the model trained using the federated framework offered by VLP was on the same level as the performance of the model trained in a centralized manner where all training data was pulled together in one centre.ConclusionsVLP infrastructure can be used for GPU-based training of a deep neural network for organ segmentation for the female pelvic region. This organ segmentation instance is particularly difficult due to the high variation in the organs’ shape and size. Being able to train the model using data from several clinics can help, for instance, by exposing the model to a larger range of data variations. VLP framework enables such a distributed training approach without sharing protected health information. |
| |
| Keywords: | Federated Data Sources Varian Learning Portal Distributed Training Convolutional Neural Network Female Pelvis Organ Segmentation |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
