Deep learning-based automatic measurement of the femoral head ossification center in healthy Korean children: development of a novel radiographic growth chart - Takeaways - MDSpire

Deep learning-based automatic measurement of the femoral head ossification center in healthy Korean children: development of a novel radiographic growth chart

  • By

  • Byoung-Dai Lee

  • Ki-Ryum Moon

  • Jin Young Kim

  • Mu Sook Lee

  • January 13, 2026

  • 0 min

Share

  • 1

    A deep learning algorithm was developed to measure the femoral head ossification center (FHOC) size in healthy Korean children using pelvic radiographs.

  • 2

    The study aimed to enhance pediatric hip joint assessments by providing standardized reference values for diagnosing hip joint diseases.

  • 3

    Manual measurements of FHOC are limited by variability and inefficiency, highlighting the need for automated measurement approaches.

  • 4

    The dataset included 1705 pelvic radiographs, with a strict patient-level split for training, validation, and testing of the deep learning model.

  • 5

    The proposed algorithm demonstrated accurate segmentation and measurement of FHOC, potentially improving clinical workflows in pediatric imaging.

Original Source(s)

Deep learning-based automatic measurement of the femoral head ossification center in healthy Korean children: development of a novel radiographic growth chart

  • by Byoung-Dai Lee, Ki-Ryum Moon, Jin Young Kim, Mu Sook Lee

  • January 13, 2026

Related Content

Hybrid deep feature and machine learning framework for classification of thyroid nodules in ultrasound images

The Impact of Physical Activity Levels on Sexual Function in Breast Cancer Survivors: An Integrative Review

Sexual dysfunction is a lasting effect of treatment and can impact the quality of life of breast cancer survivors. This review examined the impact of different levels (none/low, moderate, and high) of physical activity on sexual outcomes in breast cancer survivors.

Fabricated Citations Are Reaching Medical Journals

A large audit of biomedical publications suggests fabricated references are increasingly appearing in peer-reviewed papers — often in ways that are difficult for reviewers and readers to detect.