EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Determination of Skeletal Age From Hand Radiographs Using Deep Learning

Joshua T Bram, Ayoosh Pareek, Samuel A Beber, Ruth H Jones, M Moein Shariatnia, Amir Daliliyazdi, Olivia C Tracey, Daniel W Green, Peter D Fabricant iD

The American Journal of Sports Medicine · 2025-09 · 53 (11) · 2715-2725

DOI: 10.1177/03635465251359618 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The American Journal of Sports Medicine, online erschienen am 15.08.2025. Verfasst von Joshua T Bram und 8 weiteren Autor:innen. Beteiligte Einrichtung: Lerner Children's Pavilion, Hospital for Special Surgery, New York, New York, USA. Hauptthemen laut MEDLINE: Deep Learning, Age Determination by Skeleton, Hand, Radiography. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Surgeons treating skeletally immature patients use skeletal age to determine appropriate surgical strategies. Traditional bone age estimation methods utilizing hand radiographs are time-consuming.

Purpose

To develop highly accurate/reliable deep learning (DL) models for determination of accurate skeletal age from hand radiographs. Study Design: Cohort Study.

Methods

The authors utilized 3 publicly available hand radiograph data sets for model development/validation from (1) the Radiological Society of North America (RSNA), (2) the Radiological Hand Pose Estimation (RHPE) data set, and (3) the Digital Hand Atlas (DHA). All 3 data sets report corresponding sex and skeletal age. The RHPE and DHA also contain chronological age. After image preprocessing, a ConvNeXt model was trained first on the RSNA data set using sex/skeletal age as inputs using 5-fold cross-validation, with subsequent training on the RHPE with addition of chronological age. Final model validation was performed on the DHA and an institutional data set of 200 images.

Results

The first model, trained on the RSNA, achieved a mean absolute error (MAE) of 3.68 months on the RSNA test set and 5.66 months on the DHA. This outperformed the 4.2 months achieved on the RSNA test set by the best model from previous work (12.4% improvement) and 3.9 months by the open-source software Deeplasia (5.6% improvement). After incorporation of chronological age from the RHPE in model 2, this error improved to an MAE of 4.65 months on the DHA, again surpassing the best previously published models (19.8% improvement).

Conclusion

Leveraging newer DL technologies trained on >20,000 hand radiographs across 3 distinct, diverse data sets, this study developed a robust model for predicting bone age. Utilizing features extracted from an RSNA model, combined with chronological age inputs, this model outperforms previous state-of-the-art models when applied to validation data sets. These results indicate that the models provide a highly accurate/reliable platform for clinical use to improve confidence about appropriate surgical selection (eg, physeal-sparing procedures) and time savings for orthopaedic surgeons/radiologists evaluating skeletal age. Clinical Relevance: Development of an accurate DL model for determination of bone age from the hand reduces the time required for age estimation. Additionally, streamlined skeletal age estimation can aid practitioners in determining optimal treatment strategies and may be useful in research settings to decrease workload and improve reporting.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAge Determination by SkeletonHandRadiographyHand BonesHumansMaleFemaleCohort StudiesChildChild, PreschoolAdolescentInfant

Stichwörter der Autor:innen

artificial intelligencebone agedeep learninghandskeletal age

Autor:innen und Institutionen

  • Lerner Children's Pavilion, Hospital for Special Surgery, New York, New York, USA.
  • Sports Medicine Institute, Hospital for Special Surgery, New York, New York, USA.
  • School of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
  • Department of Computer Engineering, Sharif University of Technology, Tehran, Iran.

ORCID-Profile: Peter D Fabricant

Zitieren

APA

Bram, J. T., Pareek, A., Beber, S. A., Jones, R. H., Shariatnia, M. M., Daliliyazdi, A., Tracey, O. C., Green, D. W., & Fabricant, P. D. (2025). Determination of Skeletal Age From Hand Radiographs Using Deep Learning. The American Journal of Sports Medicine, 53(11), 2715-2725. https://doi.org/10.1177/03635465251359618

Vancouver

Bram JT, Pareek A, Beber SA, Jones RH, Shariatnia MM, Daliliyazdi A, et al. Determination of Skeletal Age From Hand Radiographs Using Deep Learning. The American Journal of Sports Medicine. 2025;53(11):2715-2725. doi:10.1177/03635465251359618

BibTeX
@article{Bram2025,
  author = {Bram, Joshua T and Pareek, Ayoosh and Beber, Samuel A and Jones, Ruth H and Shariatnia, M Moein and Daliliyazdi, Amir and Tracey, Olivia C and Green, Daniel W and Fabricant, Peter D},
  title = {Determination of Skeletal Age From Hand Radiographs Using Deep Learning},
  journal = {The American Journal of Sports Medicine},
  year = {2025},
  volume = {53},
  number = {11},
  pages = {2715--2725},
  doi = {10.1177/03635465251359618}
}
Kostenlos starten →