Multi-Site Assessment of Pediatric Bone Age Using Deep Learning

Aly A. Valliani, John T. Schwartz, Varun Arvind, Amir Taree, Jun S. Kim, Samuel K. Cho

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

3 Scopus citations

Abstract

Pediatric bone age assessment is clinically valuable for the evaluation of a variety of pediatric endocrine and orthopedic conditions. Recent studies have explored automated methods for bone age assessment using machine learning techniques, yielding impressive results. However, many state-of-The-Art methods rely on manual, fine-grained segmentation of phalanges and have not been validated on an external hospital site. The purpose of this study was to examine the efficacy of a deep learning algorithm for pediatric bone age assessment without the need for time-intensive segmentation. We utilize a novel training regime to achieve results on par with existing approaches, present a systematic analysis of experimental findings via an ablation study, and evaluate generalizability on an external dataset as a function of training data size. The final optimized model achieves mean absolute error of 7.59 months upon internal validation and 11.02 upon validation with data from an external hospital site.

Original languageEnglish
Title of host publicationProceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2020
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450379649
DOIs
StatePublished - 21 Sep 2020
Event11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2020 - Virtual, Online, United States
Duration: 21 Sep 202024 Sep 2020

Publication series

NameProceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2020

Conference

Conference11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2020
Country/TerritoryUnited States
CityVirtual, Online
Period21/09/2024/09/20

Keywords

  • artificial intelligence bone age computer vision
  • deep learning
  • endocrinology
  • machine learning
  • orthopedics
  • pediatrics

Fingerprint

Dive into the research topics of 'Multi-Site Assessment of Pediatric Bone Age Using Deep Learning'. Together they form a unique fingerprint.

Cite this