scholarly journals Application of Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in Real Healthcare Environment (Preprint)

10.2196/25869 ◽  
2020 ◽  
Author(s):  
Haeyun Lee ◽  
Young Jun Chai ◽  
Hyunjin Joo ◽  
Kyungsu Lee ◽  
Jae Youn Hwang ◽  
...  
Keyword(s):  
Image Analysis ◽  
Validation Study ◽  
Personal Information ◽  
Ultrasound Image ◽  
Thyroid Ultrasound ◽  
Healthcare Environment

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

2020 ◽  
Author(s):  
Haeyun Lee ◽  
Young Jun Chai ◽  
Hyunjin Joo ◽  
Kyungsu Lee ◽  
Jae Youn Hwang ◽  
...  
Keyword(s):  
Image Analysis ◽  
Deep Learning ◽  
Data Privacy ◽  
Personal Information ◽  
External Validation ◽  
Ultrasound Image ◽  
Medical Data ◽  
Ultrasound Images ◽  
Health Care Environment ◽  
Internal Validation

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.

scholarly journals Evaluation of Digestive Activation Level of a Small Intestine by Abdominal Ultrasound Image Analysis

2011 ◽  
Vol 12 (3) ◽  
pp. 81-89 ◽  
Author(s):  
Osamu SAKATA ◽  
Yutaka SUZUKI ◽  
Ken-ichi MATSUDA ◽  
Takaaki SATAKE
Keyword(s):  
Image Analysis ◽  
Small Intestine ◽  
Ultrasound Image ◽  
Abdominal Ultrasound ◽  
Activation Level

scholarly journals Assessment of Stroke Risk Based on Morphological Ultrasound Image Analysis with Conformal Prediction

2010 ◽  
pp. 146-153 ◽  
Author(s):  
Antonis Lambrou ◽  
Harris Papadopoulos ◽  
Efthyvoulos Kyriacou ◽  
Constantinos S. Pattichis ◽  
Marios S. Pattichis ◽  
...  
Keyword(s):  
Image Analysis ◽  
Stroke Risk ◽  
Ultrasound Image ◽  
Conformal Prediction
Sign in / Sign up

Export Citation Format

Share Document