Ann Pediatr Endocrinol Metab Search

CLOSE


Ann Pediatr Endocrinol Metab > Volume 29(2); 2024 > Article
DOI: https://doi.org/10.6065/apem.2346050.025    Published online January 24, 2024.
Clinical validation of a deep-learning-based bone age software in healthy Korean children
Hyo-Kyoung Nam1  , Winnah Wu-In Lea2  , Zepa Yang3,4  , Eunjin Noh3  , Young-Jun Rhie1  , Kee-Hyoung Lee1  , Suk-Joo Hong2,4 
1Department of Pediatrics, Korea University College of Medicine, Seoul, Korea
2Department of Radiology, Korea University College of Medicine, Seoul, Korea
3Smart Health Care Center, Korea University Guro Hospital, Seoul, Korea
4Korea University Guro Hospital-Medical Image Data Center (KUGH-MIDC), Seoul, Korea
Address for correspondence:  Suk-Joo Hong
Email: hongsj@korea.ac.kr
Received: February 23, 2023   Revised: April 19, 2023   Accepted: April 28, 2023
Abstract
Purpose
Bone age (BA) is needed to assess developmental status and growth disorders. We evaluated the clinical performance of a deep-learning-based BA software to estimate the chronological age (CA) of healthy Korean children.
Methods
This retrospective study included 371 healthy children (217 boys, 154 girls), aged between 4 and 17 years, who visited the Department of Pediatrics for health check-ups between January 2017 and December 2018. A total of 553 left-hand radiographs from 371 healthy Korean children were evaluated using a commercial deep-learning-based BA software (BoneAge, Vuno, Seoul, Korea). The clinical performance of the deep learning (DL) software was determined using the concordance rate and Bland-Altman analysis via comparison with the CA.
Results
A 2-sample t-test (P<0.001) and Fisher exact test (P=0.011) showed a significant difference between the normal CA and the BA estimated by the DL software. There was good correlation between the 2 variables (r=0.96, P<0.001); however, the root mean square error was 15.4 months. With a 12-month cutoff, the concordance rate was 58.8%. The Bland-Altman plot showed that the DL software tended to underestimate the BA compared with the CA, especially in children under the age of 8.3 years.
Conclusion
The DL-based BA software showed a low concordance rate and a tendency to underestimate the BA in healthy Korean children.
Keywords: Age determination by skeleton, Child, Child health, Deep learning, Software


ABOUT
ARTICLE CATEGORY

Browse all articles >

BROWSE ARTICLES
AUTHOR INFORMATION
Editorial Office
501-107, 30 Seocho-daero 74-gil, Seocho-gu, Seoul 06622, Republic of Korea
Tel: +82-2-3471-4268    Fax: +82-2-3471-4269    E-mail: editor@e-apem.org                

Copyright © 2024 by Korean Society of Pediatric Endocrinology.

Developed in M2PI

Close layer
prev next