Cargando…

Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment

BACKGROUND: Federated learning is a decentralized approach to machine learning; it is a training strategy that overcomes medical data privacy regulations and generalizes deep learning algorithms. Federated learning mitigates many systemic privacy risks by sharing only the model and parameters for tr...

Descripción completa

Detalles Bibliográficos
Autores principales: Lee, Haeyun, Chai, Young Jun, Joo, Hyunjin, Lee, Kyungsu, Hwang, Jae Youn, Kim, Seok-Mo, Kim, Kwangsoon, Nam, Inn-Chul, Choi, June Young, Yu, Hyeong Won, Lee, Myung-Chul, Masuoka, Hiroo, Miyauchi, Akira, Lee, Kyu Eun, Kim, Sungwan, Kong, Hyoun-Joong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: JMIR Publications 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8170555/
https://www.ncbi.nlm.nih.gov/pubmed/33858817
http://dx.doi.org/10.2196/25869
_version_ 1783702268383592448
author Lee, Haeyun
Chai, Young Jun
Joo, Hyunjin
Lee, Kyungsu
Hwang, Jae Youn
Kim, Seok-Mo
Kim, Kwangsoon
Nam, Inn-Chul
Choi, June Young
Yu, Hyeong Won
Lee, Myung-Chul
Masuoka, Hiroo
Miyauchi, Akira
Lee, Kyu Eun
Kim, Sungwan
Kong, Hyoun-Joong
author_facet Lee, Haeyun
Chai, Young Jun
Joo, Hyunjin
Lee, Kyungsu
Hwang, Jae Youn
Kim, Seok-Mo
Kim, Kwangsoon
Nam, Inn-Chul
Choi, June Young
Yu, Hyeong Won
Lee, Myung-Chul
Masuoka, Hiroo
Miyauchi, Akira
Lee, Kyu Eun
Kim, Sungwan
Kong, Hyoun-Joong
author_sort Lee, Haeyun
collection PubMed
description BACKGROUND: Federated learning is a decentralized approach to machine learning; it is a training strategy that overcomes medical data privacy regulations and generalizes deep learning algorithms. Federated learning mitigates many systemic privacy risks by sharing only the model and parameters for training, without the need to export existing medical data sets. In this study, we performed ultrasound image analysis using federated learning to predict whether thyroid nodules were benign or malignant. OBJECTIVE: The goal of this study was to evaluate whether the performance of federated learning was comparable with that of conventional deep learning. METHODS: A total of 8457 (5375 malignant, 3082 benign) ultrasound images were collected from 6 institutions and used for federated learning and conventional deep learning. Five deep learning networks (VGG19, ResNet50, ResNext50, SE-ResNet50, and SE-ResNext50) were used. Using stratified random sampling, we selected 20% (1075 malignant, 616 benign) of the total images for internal validation. For external validation, we used 100 ultrasound images (50 malignant, 50 benign) from another institution. RESULTS: For internal validation, the area under the receiver operating characteristic (AUROC) curve for federated learning was between 78.88% and 87.56%, and the AUROC for conventional deep learning was between 82.61% and 91.57%. For external validation, the AUROC for federated learning was between 75.20% and 86.72%, and the AUROC curve for conventional deep learning was between 73.04% and 91.04%. CONCLUSIONS: We demonstrated that the performance of federated learning using decentralized data was comparable to that of conventional deep learning using pooled data. Federated learning might be potentially useful for analyzing medical images while protecting patients’ personal information.
format Online
Article
Text
id pubmed-8170555
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher JMIR Publications
record_format MEDLINE/PubMed
spelling pubmed-81705552021-06-11 Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment Lee, Haeyun Chai, Young Jun Joo, Hyunjin Lee, Kyungsu Hwang, Jae Youn Kim, Seok-Mo Kim, Kwangsoon Nam, Inn-Chul Choi, June Young Yu, Hyeong Won Lee, Myung-Chul Masuoka, Hiroo Miyauchi, Akira Lee, Kyu Eun Kim, Sungwan Kong, Hyoun-Joong JMIR Med Inform Original Paper BACKGROUND: Federated learning is a decentralized approach to machine learning; it is a training strategy that overcomes medical data privacy regulations and generalizes deep learning algorithms. Federated learning mitigates many systemic privacy risks by sharing only the model and parameters for training, without the need to export existing medical data sets. In this study, we performed ultrasound image analysis using federated learning to predict whether thyroid nodules were benign or malignant. OBJECTIVE: The goal of this study was to evaluate whether the performance of federated learning was comparable with that of conventional deep learning. METHODS: A total of 8457 (5375 malignant, 3082 benign) ultrasound images were collected from 6 institutions and used for federated learning and conventional deep learning. Five deep learning networks (VGG19, ResNet50, ResNext50, SE-ResNet50, and SE-ResNext50) were used. Using stratified random sampling, we selected 20% (1075 malignant, 616 benign) of the total images for internal validation. For external validation, we used 100 ultrasound images (50 malignant, 50 benign) from another institution. RESULTS: For internal validation, the area under the receiver operating characteristic (AUROC) curve for federated learning was between 78.88% and 87.56%, and the AUROC for conventional deep learning was between 82.61% and 91.57%. For external validation, the AUROC for federated learning was between 75.20% and 86.72%, and the AUROC curve for conventional deep learning was between 73.04% and 91.04%. CONCLUSIONS: We demonstrated that the performance of federated learning using decentralized data was comparable to that of conventional deep learning using pooled data. Federated learning might be potentially useful for analyzing medical images while protecting patients’ personal information. JMIR Publications 2021-05-18 /pmc/articles/PMC8170555/ /pubmed/33858817 http://dx.doi.org/10.2196/25869 Text en ©Haeyun Lee, Young Jun Chai, Hyunjin Joo, Kyungsu Lee, Jae Youn Hwang, Seok-Mo Kim, Kwangsoon Kim, Inn-Chul Nam, June Young Choi, Hyeong Won Yu, Myung-Chul Lee, Hiroo Masuoka, Akira Miyauchi, Kyu Eun Lee, Sungwan Kim, Hyoun-Joong Kong. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 18.05.2021. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on https://medinform.jmir.org/, as well as this copyright and license information must be included.
spellingShingle Original Paper
Lee, Haeyun
Chai, Young Jun
Joo, Hyunjin
Lee, Kyungsu
Hwang, Jae Youn
Kim, Seok-Mo
Kim, Kwangsoon
Nam, Inn-Chul
Choi, June Young
Yu, Hyeong Won
Lee, Myung-Chul
Masuoka, Hiroo
Miyauchi, Akira
Lee, Kyu Eun
Kim, Sungwan
Kong, Hyoun-Joong
Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment
title Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment
title_full Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment
title_fullStr Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment
title_full_unstemmed Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment
title_short Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment
title_sort federated learning for thyroid ultrasound image analysis to protect personal information: validation study in a real health care environment
topic Original Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8170555/
https://www.ncbi.nlm.nih.gov/pubmed/33858817
http://dx.doi.org/10.2196/25869
work_keys_str_mv AT leehaeyun federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT chaiyoungjun federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT joohyunjin federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT leekyungsu federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT hwangjaeyoun federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT kimseokmo federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT kimkwangsoon federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT naminnchul federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT choijuneyoung federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT yuhyeongwon federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT leemyungchul federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT masuokahiroo federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT miyauchiakira federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT leekyueun federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT kimsungwan federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment
AT konghyounjoong federatedlearningforthyroidultrasoundimageanalysistoprotectpersonalinformationvalidationstudyinarealhealthcareenvironment