Automated Bone Age Estimation From Noncontrast Abdominal CT Using Deep Learning

Peking University People's Hospital3,000 enrolled

Overview

This study is a retrospective analysis that uses abdominal CT scans, which were originally taken for other medical reasons, to estimate bone age. By applying advanced deep learning methods, the investigators aim to develop a tool that can evaluate bone health and detect early signs of osteoporosis without requiring additional scans or radiation. This approach may help doctors better understand bone aging, improve screening for bone weakness, and provide patients with more personalized information about their bone health.

Study Type

OBSERVATIONAL

Enrollment

3,000

Conditions

Bone Aging Osteoporosis Diagnosis

Eligibility

Sex: ALLMin age: 18 YearsHealthy volunteers:

Medical Language ↔ Plain English

Inclusion Criteria: * Adults aged over 18 years. * Underwent routine noncontrast abdominal CT scans. * CT scans fully included the proximal femur. * Scans were performed for non-orthopedic clinical indications. * Provided necessary demographic information (e.g., age, sex). Exclusion Criteria: * CT scans with poor image quality or severe artifacts that precluded accurate analysis. * History of hip surgery or presence of internal fixation devices. * Presence of bone tumors in the proximal femur. * Severe hip deformity or prior fractures affecting the proximal femur. * Pediatric patients or pregnant individuals (if applicable).

Locations (1)

Outcomes

Primary Outcomes

Radiomics-Based Bone Age Prediction Model

Extraction of radiomics features from abdominal CT images of the proximal femur and development of a machine learning model to estimate biological bone age. The performance of the model will be evaluated by comparing predicted bone age with chronological age.

Time frame: Retrospective analysis of CT scans acquired between Sep 01.2024 to Oct 01.2025