41 145

Cited 0 times in

Bone Age Estimation and Prediction of Final Adult Height Using Deep Learning

Authors
 Junghwan Suh  ;  Jinkyoung Heo  ;  Su Jin Kim  ;  Soyeong Park  ;  Mo Kyung Jung  ;  Han Saem Choi  ;  Youngha Choi  ;  Jun Suk Oh  ;  Hae In Lee  ;  Myeongseob Lee  ;  Kyungchul Song  ;  Ahreum Kwon  ;  Hyun Wook Chae  ;  Ho-Seong Kim 
Citation
 YONSEI MEDICAL JOURNAL, Vol.64(11) : 679-686, 2023-11 
Journal Title
YONSEI MEDICAL JOURNAL
ISSN
 0513-5796 
Issue Date
2023-11
Keywords
Bone age ; artificial intelligence ; convolutional neural network ; deep learning ; final height
Abstract
Purpose: The appropriate evaluation of height and accurate estimation of bone age are crucial for proper assessment of the growth status of a child. We developed a bone age estimation program using a deep learning algorithm and established a model to predict the final adult height of Korean children.

Materials and Methods: A total of 1678 radiographs from 866 children, for which the interpretation results were consistent be tween two pediatric endocrinologists, were used to train and validate the deep learning model. The bone age estimation algorithm was based on the convolutional neural network of the deep learning system. The test set simulation was performed by a deep learning program and two raters using 150 radiographs and final height data for 100 adults.

Results: There was a statistically significant correlation between bone age interpreted by the artificial intelligence (AI) program and the reference bone age in the test set simulation (r=0.99, p<0.001). In the test set simulation, the AI program showed a mean absolute error (MAE) of 0.59 years and a root mean squared error (RMSE) of 0.55 years, compared with reference bone age, and showed similar accuracy to that of an experienced pediatric endocrinologist (rater 1). Prediction of final adult height by the AI program showed an MAE of 4.62 cm, compared with the actual final adult height.

Conclusion: We developed a bone age estimation program based on a deep learning algorithm. The AI-derived program demon strated high accuracy in estimating bone age and predicting the final adult height of Korean children and adolescents.
Files in This Item:
T202400447.pdf Download
DOI
10.3349/ymj.2023.0244
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Pediatrics (소아과학교실) > 1. Journal Papers
Yonsei Authors
Kwon, Ah Reum(권아름) ORCID logo https://orcid.org/0000-0002-9692-2135
Kim, Su Jin(김수진) ORCID logo https://orcid.org/0000-0003-0907-9213
Kim, Ho Seong(김호성) ORCID logo https://orcid.org/0000-0003-1135-099X
Suh, Junghwan(서정환) ORCID logo https://orcid.org/0000-0002-2092-2585
Song, Kyungchul(송경철) ORCID logo https://orcid.org/0000-0002-8497-5934
Lee, Myeongseob(이명섭) ORCID logo https://orcid.org/0000-0001-7055-3100
Chae, Hyun Wook(채현욱) ORCID logo https://orcid.org/0000-0001-5016-8539
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/197912
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links