Rethinking Greulich and Pyle: A Deep Learning Approach to Pediatric Bone Age Assessment Using Pediatric Trauma Hand Radiographs.
Journal
Radiology. Artificial intelligence
ISSN: 2638-6100
Titre abrégé: Radiol Artif Intell
Pays: United States
ID NLM: 101746556
Informations de publication
Date de publication:
Jul 2020
Jul 2020
Historique:
received:
12
11
2019
revised:
19
05
2020
accepted:
29
05
2020
entrez:
3
5
2021
pubmed:
4
5
2021
medline:
4
5
2021
Statut:
epublish
Résumé
To develop a deep learning approach to bone age assessment based on a training set of developmentally normal pediatric hand radiographs and to compare this approach with automated and manual bone age assessment methods based on Greulich and Pyle (GP). In this retrospective study, a convolutional neural network (trauma hand radiograph-trained deep learning bone age assessment method [TDL-BAAM]) was trained on 15 129 frontal view pediatric trauma hand radiographs obtained between December 14, 2009, and May 31, 2017, from Children's Hospital of New York, to predict chronological age. A total of 214 trauma hand radiographs from Hasbro Children's Hospital were used as an independent test set. The test set was rated by the TDL-BAAM model as well as a GP-based deep learning model (GPDL-BAAM) and two pediatric radiologists (radiologists 1 and 2) using the GP method. All ratings were compared with chronological age using mean absolute error (MAE), and standard concordance analyses were performed. The MAE of the TDL-BAAM model was 11.1 months, compared with 12.9 months for GPDL-BAAM ( A deep learning model trained on pediatric trauma hand radiographs is on par with automated and manual GP-based methods for bone age assessment and provides a foundation for developing population-specific deep learning algorithms for bone age assessment in modern pediatric populations.
Identifiants
pubmed: 33937834
doi: 10.1148/ryai.2020190198
pmc: PMC8082327
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e190198Commentaires et corrections
Type : CommentIn
Informations de copyright
2020 by the Radiological Society of North America, Inc.
Déclaration de conflit d'intérêts
Disclosures of Conflicts of Interest: I.P. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: disclosed no relevant relationships. Other relationships: author is a consultant for MD.ai. G.L.B. disclosed no relevant relationships. S.M. disclosed no relevant relationships. D.M. disclosed no relevant relationships. C.R. disclosed no relevant relationships. D.W.S. disclosed no relevant relationships. R.S.A. disclosed no relevant relationships.
Références
AJR Am J Roentgenol. 2017 Dec;209(6):1374-1380
pubmed: 28898126
PLoS One. 2019 Jul 25;14(7):e0220242
pubmed: 31344143
J Digit Imaging. 2017 Aug;30(4):427-441
pubmed: 28275919
Am J Roentgenol Radium Ther Nucl Med. 1973 Jun;118(2):320-7
pubmed: 4351412
IEEE Trans Med Imaging. 2009 Jan;28(1):52-66
pubmed: 19116188
Pediatr Radiol. 2016 Aug;46(9):1269-74
pubmed: 27173981
Acad Radiol. 2010 Nov;17(11):1425-32
pubmed: 20691616
AJR Am J Roentgenol. 2001 Feb;176(2):507-10
pubmed: 11159105
J Pharm Bioallied Sci. 2015 Jul-Sep;7(3):218-25
pubmed: 26229357
Radiology. 2018 Apr;287(1):313-322
pubmed: 29095675
J Med Syst. 2018 Nov 3;42(12):249
pubmed: 30390162
J Digit Imaging. 2018 Aug;31(4):513-519
pubmed: 29404850
Horm Res Paediatr. 2011;76(1):1-9
pubmed: 21691054
Arch Dis Child. 1999 Aug;81(2):172-3
pubmed: 10490531
IEEE Trans Pattern Anal Mach Intell. 2020 Feb;42(2):318-327
pubmed: 30040631
Med Image Anal. 2017 Feb;36:41-51
pubmed: 27816861
Horm Res Paediatr. 2011;76(1):10-6
pubmed: 21691055
Ethiop J Health Sci. 2017 Nov;27(6):631-640
pubmed: 29487472
Skeletal Radiol. 2019 Feb;48(2):275-283
pubmed: 30069585
Eur Radiol. 2019 Jun;29(6):2910-2923
pubmed: 30617474
Radiology. 2009 Jan;250(1):228-35
pubmed: 18955510
Radiology. 2019 Feb;290(2):498-503
pubmed: 30480490