Minty Radhiya, Mahomed Nasreen, van Wyk Nicole, Mndebele Gopolang, Lockhat Zarina, Ranchod Ashesh
Department of Radiology, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa.
Department of Paediatrics and Child Health, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa.
SA J Radiol. 2025 Apr 11;29(1):3033. doi: 10.4102/sajr.v29i1.3033. eCollection 2025.
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.
To compare the manual GP method with the automated BoneXpert method in performing bone age assessment of children with various paediatric endocrinology diagnoses.
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.
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.
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.
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.
格-派（GP）方法是最常用的手动骨龄评估方法，但存在评估者间差异。BoneXpert方法是完全自动化的，消除了评估者间差异，并且已在不同人群中得到验证。
比较手动GP方法与自动化BoneXpert方法在对患有各种儿科内分泌疾病的儿童进行骨龄评估时的效果。
三名手动阅片者对手腕部X线片进行手动骨龄评估，BoneXpert软件对260张左手腕部X线片进行自动化骨龄评估。当三名手动阅片者的平均评估结果（手动骨龄）与BoneXpert评估结果相差超过1.5岁时，由一名外部阅片者重新阅片，得出参考骨龄。将手动骨龄与软件生成的腕骨骨龄进行比较。定义了软件的综合骨龄（Comp BA），以估计腕骨和管状骨的权重，从而与手动骨龄达成最佳一致性。
各手动阅片者之间的组内相关系数（ICC）>0.9，表明具有高度正相关性。手动骨龄与BoneXpert骨龄之间的ICC为0.982。与手动骨龄最匹配的BoneXpert综合骨龄，对腕骨骨龄和管状骨骨龄的权重均为50%。
BoneXpert方法高效、经过充分验证，且与手动GP方法呈正相关。腕骨和管状骨各占50%的估计权重，使得自动化综合骨龄与手动骨龄达成了最佳一致性。
这篇原创研究文章比较了手动和自动化骨龄评估方法，以评估人工智能工具在南非背景下的应用。
