Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Multicenter Study
. 2025 Jul 1;25(1):235.
doi: 10.1186/s12880-025-01743-9.

Radiomics and machine learning for osteoporosis detection using abdominal computed tomography: a retrospective multicenter study

Zhai Liu  1 , Yongjun Li  2 , Chenguang Zhang  1 , Hui Xu  1 , Junlu Zhao  1 , Chencui Huang  3 , Xingzhi Chen  3 , Qingyun Ren  4
Affiliations
Multicenter Study

Radiomics and machine learning for osteoporosis detection using abdominal computed tomography: a retrospective multicenter study

Zhai Liu et al. BMC Med Imaging. .

Abstract

Objective: This study aimed to develop and validate a predictive model to detect osteoporosis using radiomic features and machine learning (ML) approaches from lumbar spine computed tomography (CT) images during an abdominal CT examination.

Methods: A total of 509 patients who underwent both quantitative CT (QCT) and abdominal CT examinations (training group, n = 279; internal validation group, n = 120; external validation group, n = 110) were analyzed in this retrospective study from two centers. Radiomic features were extracted from the lumbar spine CT images. Seven radiomic-based ML models, including logistic regression (LR), Bernoulli, Gaussian NB, SGD, decision tree, support vector machine (SVM), and K-nearest neighbor (KNN) models, were constructed. The performance of the models was assessed using the area under the curve (AUC) of receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA).

Results: The radiomic model based on LR in the internal validation group and external validation group had excellent performance, with an AUC of 0.960 and 0.786 for differentiating osteoporosis from normal BMD and osteopenia, respectively. The radiomic model based on LR in the internal validation group and Gaussian NB model in the external validation group yielded the highest performance, with an AUC of 0.905 and 0.839 for discriminating normal BMD from osteopenia and osteoporosis, respectively. DCA in the internal validation group revealed that the LR model had greater net benefit than the other models in differentiating osteoporosis from normal BMD and osteopenia.

Conclusion: Radiomic-based ML approaches may be used to predict osteoporosis from abdominal CT images and as a tool for opportunistic osteoporosis screening.

Keywords: Computed tomography; Machine learning; Osteoporosis; Radiomics; Vertebral body.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: The study was conducted in accordance with the 1964 Declaration of Helsinki and later amendments. This study was approved by the Ethics Committee of the First Hospital of Hebei Medical University (approval no. 20220104). The requirement for individual informed consent was waived because of the retrospective nature of the study. Consent for publication: The requirement for written informed consent was waived because of the retrospective nature of the study. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Overall workflow of this study
Fig. 2
Fig. 2
Feature correlation heatmap of osteoporosis vs. normal BMD and osteopenia model
Fig. 3
Fig. 3
Feature correlation heatmap of normal BMD vs. osteopenia and osteoporosis model
Fig. 4
Fig. 4
Receiver operating characteristic curves for the two classification tasks: (a) to (c), osteoporosis vs. normal and osteopenia; (a) training group; (b) internal validation group; (c) external validation group; (d) to (f), normal vs. osteopenia and osteoporosis; (d) training group; (e) internal validation group; (f) external validation group
Fig. 5
Fig. 5
DCA for the two classification tasks. (a) Osteoporosis vs. normal and osteopenia: DCA revealed that the LR model (red line) was more advantageous than the other models. (b) Normal vs. osteopenia and osteoporosis: DCA revealed that the LR model (red line) was more advantageous than the other models
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. NIH Consensus Development Panel on Osteoporosis Prevention, Diagnosis, and Therapy, March 7-29, 2000: highlights of the conference. South Med J. 2001;94(6):569–73.. - PubMed
    1. Siris ES, Adler R, Bilezikian J, et al. The clinical diagnosis of osteoporosis: a position statement from the National Bone Health Alliance Working Group. Osteoporos Int. 2014;25:1439–43. - PMC - PubMed
    1. Kanis JA, Johnell O, Oden A, et al. Risk of hip fracture according to the World Health Organization criteria for osteopenia and osteoporosis. Bone. 2000;27(5):585–90. - PubMed
    1. Gao C, Xu Y, Li L, et al. Prevalence of osteoporotic vertebral fracture among community-dwelling elderly in Shanghai. Chin Med J (Engl). 2019;132(14):1749–51. - PMC - PubMed
    1. Kanis JA. Diagnosis of osteoporosis and assessment of fracture risk. Lancet. 2002;359(9321):1929–36. - PubMed

Publication types