Age-Dependent Generalizability of Lumbar Spine Detection and Segmentation Models: A Comparative Study in Pediatric Populations

Jemyoung Lee, Changmin Park, Minkyoung Cho, Young Hun Choi, Jong Hyo Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

This study assessed automated bone density measurement technologies in pediatric groups, focusing on lumbar spine localization and spine segmentation models initially trained on adult data. The research involved three phases: training models using YOLOv5 and U-Net on adult images, adapting these models with pediatric data via transfer learning, and external validation categorized by age to account for anatomical variances. The adult-trained model showed decreased sensitivity in younger ages, with the lowest performance in the youngest group. Conversely, the pediatric-trained model achieved high sensitivity, over 90% in children under 10, and perfect scores in the 10-12 group, demonstrating improved accuracy. Qualitative analysis for segmentation indicated better performance in the pediatric model across all age groups, particularly in those under 13. The study concludes that transfer learning enhances the performance and generalizability of models for pediatric spine analysis, suggesting a potential for more accurate diagnostics.

Original languageEnglish
Title of host publicationMedical Imaging 2024
Subtitle of host publicationImage Processing
EditorsOlivier Colliot, Jhimli Mitra
PublisherSPIE
ISBN (Electronic)9781510671560
DOIs
StatePublished - 2024
EventMedical Imaging 2024: Image Processing - San Diego, United States
Duration: 19 Feb 202422 Feb 2024

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume12926
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2024: Image Processing
Country/TerritoryUnited States
CitySan Diego
Period19/02/2422/02/24

Bibliographical note

Publisher Copyright:
© 2024 SPIE.

Keywords

  • Age-Dependent Generalizability
  • Pediatric
  • Spine Localization
  • Spine Segmentation
  • Transfer Learning

Fingerprint

Dive into the research topics of 'Age-Dependent Generalizability of Lumbar Spine Detection and Segmentation Models: A Comparative Study in Pediatric Populations'. Together they form a unique fingerprint.

Cite this