Pediatric skeletal age: Determination with neural networks

G. W. Gross, John M Boone, D. M. Bishop

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

PURPOSE: To develop a neural network to calculate skeletal age based on measurements taken from digitized hand radiographs. MATERIALS AND METHODS: From a database of 521 hand radiographs obtained in healthy patients, four parameters were calculated from seven linear measurements and were used to train a neural network, with use of the jackknife method, to calculate skeletal age. The results were compared with those of an experienced pediatric radiologist using a standard pediatric skeletal atlas. RESULTS: The mean difference from biologic age for the neural network was -0.261 years ± 1.82 (standard deviation) and for the radiologist, -0.232 years ± 1.54; this difference was not significantly different (P = .67, Wilcoxon signed rank test). Skeletal age determined by the neural network was closer to the biologic age than that assigned by the radiologist in 243 of 521 cases (47%). CONCLUSION: A simple neural network may assist radiologists in the assessment of skeletal age.

Original languageEnglish (US)
Pages (from-to)689-695
Number of pages7
JournalRadiology
Volume195
Issue number3
StatePublished - 1995

Fingerprint

Pediatrics
Hand
Atlases
Nonparametric Statistics
Databases
Radiologists

Keywords

  • Bones, growth and development
  • Children, skeletal system
  • Computers, neural network

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology

Cite this

Gross, G. W., Boone, J. M., & Bishop, D. M. (1995). Pediatric skeletal age: Determination with neural networks. Radiology, 195(3), 689-695.

Pediatric skeletal age : Determination with neural networks. / Gross, G. W.; Boone, John M; Bishop, D. M.

In: Radiology, Vol. 195, No. 3, 1995, p. 689-695.

Research output: Contribution to journalArticle

Gross, GW, Boone, JM & Bishop, DM 1995, 'Pediatric skeletal age: Determination with neural networks', Radiology, vol. 195, no. 3, pp. 689-695.
Gross, G. W. ; Boone, John M ; Bishop, D. M. / Pediatric skeletal age : Determination with neural networks. In: Radiology. 1995 ; Vol. 195, No. 3. pp. 689-695.
@article{a70f2777de7f4fe392768ea6b3ca7409,
title = "Pediatric skeletal age: Determination with neural networks",
abstract = "PURPOSE: To develop a neural network to calculate skeletal age based on measurements taken from digitized hand radiographs. MATERIALS AND METHODS: From a database of 521 hand radiographs obtained in healthy patients, four parameters were calculated from seven linear measurements and were used to train a neural network, with use of the jackknife method, to calculate skeletal age. The results were compared with those of an experienced pediatric radiologist using a standard pediatric skeletal atlas. RESULTS: The mean difference from biologic age for the neural network was -0.261 years ± 1.82 (standard deviation) and for the radiologist, -0.232 years ± 1.54; this difference was not significantly different (P = .67, Wilcoxon signed rank test). Skeletal age determined by the neural network was closer to the biologic age than that assigned by the radiologist in 243 of 521 cases (47{\%}). CONCLUSION: A simple neural network may assist radiologists in the assessment of skeletal age.",
keywords = "Bones, growth and development, Children, skeletal system, Computers, neural network",
author = "Gross, {G. W.} and Boone, {John M} and Bishop, {D. M.}",
year = "1995",
language = "English (US)",
volume = "195",
pages = "689--695",
journal = "Radiology",
issn = "0033-8419",
publisher = "Radiological Society of North America Inc.",
number = "3",

}

TY - JOUR

T1 - Pediatric skeletal age

T2 - Determination with neural networks

AU - Gross, G. W.

AU - Boone, John M

AU - Bishop, D. M.

PY - 1995

Y1 - 1995

N2 - PURPOSE: To develop a neural network to calculate skeletal age based on measurements taken from digitized hand radiographs. MATERIALS AND METHODS: From a database of 521 hand radiographs obtained in healthy patients, four parameters were calculated from seven linear measurements and were used to train a neural network, with use of the jackknife method, to calculate skeletal age. The results were compared with those of an experienced pediatric radiologist using a standard pediatric skeletal atlas. RESULTS: The mean difference from biologic age for the neural network was -0.261 years ± 1.82 (standard deviation) and for the radiologist, -0.232 years ± 1.54; this difference was not significantly different (P = .67, Wilcoxon signed rank test). Skeletal age determined by the neural network was closer to the biologic age than that assigned by the radiologist in 243 of 521 cases (47%). CONCLUSION: A simple neural network may assist radiologists in the assessment of skeletal age.

AB - PURPOSE: To develop a neural network to calculate skeletal age based on measurements taken from digitized hand radiographs. MATERIALS AND METHODS: From a database of 521 hand radiographs obtained in healthy patients, four parameters were calculated from seven linear measurements and were used to train a neural network, with use of the jackknife method, to calculate skeletal age. The results were compared with those of an experienced pediatric radiologist using a standard pediatric skeletal atlas. RESULTS: The mean difference from biologic age for the neural network was -0.261 years ± 1.82 (standard deviation) and for the radiologist, -0.232 years ± 1.54; this difference was not significantly different (P = .67, Wilcoxon signed rank test). Skeletal age determined by the neural network was closer to the biologic age than that assigned by the radiologist in 243 of 521 cases (47%). CONCLUSION: A simple neural network may assist radiologists in the assessment of skeletal age.

KW - Bones, growth and development

KW - Children, skeletal system

KW - Computers, neural network

UR - http://www.scopus.com/inward/record.url?scp=0029057501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029057501&partnerID=8YFLogxK

M3 - Article

C2 - 7753995

AN - SCOPUS:0029057501

VL - 195

SP - 689

EP - 695

JO - Radiology

JF - Radiology

SN - 0033-8419

IS - 3

ER -