Development of a system for measuring the bone mineal density of the proximal femur from hip x-rays

2023 Fiscal Year Final Research Report

• Project/Area Number: 21K16655
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 56020:Orthopedics-related
• Research Institution: Osaka University
• Principal Investigator: Uemura Keisuke 大阪大学, 大学院医学系研究科, 寄附講座講師 (70871367)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Keywords: 骨粗鬆症 / 人工知能 / X線画像

Outline of Final Research Achievements

Dual-energy X-ray absorptiometry (DXA) is the gold standard for measuring bone mineral density (BMD). However, as access to DXA is limited, we aimed to develop and verify a system that measures BMD of the proximal femur from hip X-rays. Using 315 cases of hip anteroposterior X-rays, hip CT, and proximal femur BMD measured using DXA (DXA-BMD, a deep-learning model called “BMD-GAN” that could measure the BMD from hip X-rays was developed and validated on 1426 cases. In the validation,the correlation coefficient between Xp-aBMD and DXA-BMD was > 0.9, which indicated that the developed system could be applied for clinical investigation in the future.

Free Research Field

骨粗鬆症

Academic Significance and Societal Importance of the Research Achievements

人工知能を用い、股関節X線画像から大腿骨近位部の骨密度を正確に計測し、骨粗鬆症の診断を行うシステムの構築を行った。今後本システムが普及すれば、二重エネルギーX線吸収測定法が導入されていない施設でもX線画像を用いて骨粗鬆症の診断および治療介入が可能となり、骨粗鬆症に続発する脆弱性骨折およびそれに伴う活動性の低下を防ぐことが期待できる。