Using federated data sources and Varian Learning Portal framework to train a neural network model for automatic organ segmentation. (April 2020)

• Record Type: Journal Article
• Authors: Czeizler, Elena; Wiessler, Wolfgang; Koester, Thorben; Hakala, Mikko; Basiri, Shahab; Jordan, Petr; Kuusela, Esa
• Is Part Of: Physica medica. Volume 72(2020)
• Page Start: 39
• Page End: 45
• Publication Date: 2020-04
• Subjects: Federated Data Sources -- Varian Learning Portal -- Distributed Training -- Convolutional Neural Network -- Female Pelvis Organ Segmentation; Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2020.03.011
• Languages: English
• ISSNs: 1120-1797

Abstract

Graphical abstract: Highlights: We did a distributed training of a segmentation model for female pelvic region, with high variations in the organ contours. Varian Learning Portal (VLP) infrastructure enables distributed training within a trusted consortium framework. In trusted consortia the partners trust each other but there are legal restrictions regarding data sharing. OAR segmentation model trained with VLP reached the same level of performance as the model trained in centralized manner. Abstract: Purpose: In 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. Methods: Varian 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. Results: The 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. Conclusions: VLP 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.