Original Research

Comparison of bone age assessment using manual Greulich and Pyle method versus automated BoneXpert method in South African children

Radhiya Minty, Nasreen Mahomed, Nicole van Wyk, Gopolang Mndebele, Zarina Lockhat, Ashesh Ranchod
South African Journal of Radiology | Vol 29, No 1 | a3033 | DOI: https://doi.org/10.4102/sajr.v29i1.3033 | © 2025 Radhiya Minty, Nasreen Mahomed, Nicole van Wyk, Gopolang Mndebele, Zarina Lockhat, Ashesh Ranchod | This work is licensed under CC Attribution 4.0
Submitted: 14 September 2024 | Published: 11 April 2025

About the author(s)

Radhiya Minty, Department of Radiology, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa
Nasreen Mahomed, Department of Radiology, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa
Nicole van Wyk, Department of Paediatrics and Child Health, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa
Gopolang Mndebele, Department of Radiology, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa
Zarina Lockhat, Department of Radiology, Faculty of Health Sciences, University of Pretoria, Pretoria, South Africa
Ashesh Ranchod, Department of Radiology, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa

Abstract

Background: The Greulich and Pyle (GP) method is the most commonly used manual bone age assessment method but it is associated with interrater variability. The BoneXpert method is fully automated, eliminates interrater variability and has been validated for use in various populations.

Objectives: To compare the manual GP method with the automated BoneXpert method in performing bone age assessment of children with various paediatric endocrinology diagnoses.

Method: Three manual readers performed manual bone age assessment, and BoneXpert software performed automated bone age assessment on 260 left hand-wrist radiographs. Images where the average of three manual readers (Manual BA) deviated from BoneXpert BA by > 1.5 years, were re-read by an external reader, producing a Reference BA. Manual BA was compared to Carpal BA that was produced by the software. A composite bone age (Comp BA) for the software was defined to estimate the weighting on carpal and tubular bones to achieve the best agreement with Manual BA.

Results: The interclass correlation (ICC) between each manual reader was > 0.9, indicating a high positive correlation. The ICC between Manual BA and BoneXpert BA was 0.982. The Comp BA for BoneXpert that would achieve the best fit with Manual BA, places a 50% weighting on Carpal BA and 50% weighting on Tubular BA.

Conclusion: The BoneXpert method is efficient, well-validated and shows a positive correlation with the manual GP method. An estimated weightage of 50% to carpal bones and 50% to tubular bones resulted in an automated Comp BA with the best agreement with Manual BA.

Contribution: This original research article compares manual and automated bone age assessment methods to evaluate the use of artificial intelligence tools in the South African context.


Keywords

bone age assessment; Greulich and Pyle; BoneXpert; artificial intelligence; skeletal maturity

Sustainable Development Goal

Goal 3: Good health and well-being

Metrics

Total abstract views: 13
Total article views: 40


Crossref Citations

No related citations found.