Endocrinology and Metabolism

Original Article

Mineral, Bone & Muscle
End-to-End Semi-Supervised Opportunistic Osteoporosis Screening Using Computed Tomography: Jieun Oh, Boah Kim, Gyutaek Oh, Yul Hwangbo, Jong Chul Ye; Endocrinol Metab. 2024;39(3):500-510. Published online May 9, 2024; DOI: https://doi.org/10.3803/EnM.2023.1860

5,424 View
98 Download
6 Web of Science
8 Crossref

Abstract PDF Supplementary Material PubReader ePub

Background
Osteoporosis is the most common metabolic bone disease and can cause fragility fractures. Despite this, screening utilization rates for osteoporosis remain low among populations at risk. Automated bone mineral density (BMD) estimation using computed tomography (CT) can help bridge this gap and serve as an alternative screening method to dual-energy X-ray absorptiometry (DXA).
Methods
The feasibility of an opportunistic and population agnostic screening method for osteoporosis using abdominal CT scans without bone densitometry phantom-based calibration was investigated in this retrospective study. A total of 268 abdominal CT-DXA pairs and 99 abdominal CT studies without DXA scores were obtained from an oncology specialty clinic in the Republic of Korea. The center axial CT slices from the L1, L2, L3, and L4 lumbar vertebrae were annotated with the CT slice level and spine segmentation labels for each subject. Deep learning models were trained to localize the center axial slice from the CT scan of the torso, segment the vertebral bone, and estimate BMD for the top four lumbar vertebrae.
Results
Automated vertebra-level DXA measurements showed a mean absolute error (MAE) of 0.079, Pearson’s r of 0.852 (P<0.001), and R² of 0.714. Subject-level predictions on the held-out test set had a MAE of 0.066, Pearson’s r of 0.907 (P<0.001), and R² of 0.781.
Conclusion
CT scans collected during routine examinations without bone densitometry calibration can be used to generate DXA BMD predictions.

Citations

Citations to this article as recorded by

Artificial Intelligence in Rheumatology: From Algorithms to Clinical Impact in Osteoporosis and Chronic Inflammatory Rheumatic Diseases
Marie Doussiere, Ahlem Aboud, Gilles Dequen, Vincent Goëb
Journal of Clinical Medicine.2026; 15(2): 491. CrossRef
The Diagnostic Value of Image-Based Machine Learning for Osteoporosis: Systematic Review and Meta-Analysis
Rui Zhao, Haolin Yang, Yangbo Li, Xiaoyun Li, Zhijie Yang, Yanping Lin, Jiachun Huang, Lei Wan, Hongxing Huang
Journal of Medical Internet Research.2026; 28: e75965. CrossRef
Phantomless estimation of bone mineral density on computed tomography: a scoping review
Aleena Waqar, Alberto Bazzocchi, Maria Pilar Aparisi Gómez
RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren.2025; 197(11): 1262. CrossRef
Diagnostic accuracy of axial and sagittal CT measurements for osteoporosis: A multi-vertebra evaluation
Sevde Nur Emir, Ahmet Kürşat Soydan, Safiye Sanem Dereli Bulut
Journal of Clinical Densitometry.2025; 28(4): 101596. CrossRef
Artificial intelligence in spine surgery
Cheng Zhang, Shanshan Liu, Jialin Shi, Xingyu Zhou, Peter Passias, Nanfang Xu, Weishi Li
Spine Research.2025; 1(1): 13. CrossRef
Deep Learning–Assisted Automated Diagnosis of Osteoporosis Based on Computed Tomography Scans: Systematic Review and Meta-Analysis
Aobo Wang, Ziqian Ma, Tianyi Wang, Ruiyuan Chen, Yu Xi, Qichao Wu, Shuo Yuan, Ning Fan, Peng Du, Lei Zang
Journal of Medical Internet Research.2025; 27: e77155. CrossRef
Changes of bone, adipose, and muscle-related body compositions in gastric cancers after gastrectomy using deep learning based automatic segmentation
Mengying Xu, Dan Liu, Mengze Zhang, Song Liu, Zhengyang Zhou
BMC Gastroenterology.2025;[Epub] CrossRef
Unaccounted Variations Can Surreptitiously Spoil the Validity of “Good” Biostatistical Models
Abhaya Indrayan
Journal of the Epidemiology Foundation of India.2024; 2(4): 205. CrossRef

First
Prev
Page of 1
Next
Last

Search