Feasibility study of opportunistic osteoporosis screening on chest CT using a multi-feature fusion DCNN model

• Published in: Archives of osteoporosis Vol. 19; no. 1; p. 98
• Main Authors: Pan, Jing, Lin, Peng-cheng, Gong, Shen-chu, Wang, Ze, Cao, Rui, Lv, Yuan, Zhang, Kun, Wang, Lin
• Format: Journal Article
• Language: English
• Published: London Springer London 17.10.2024; Springer Nature B.V
• Subjects: Adult; Aged; automation; Bone Density; Bone Diseases, Metabolic - diagnostic imaging; bone fractures; chest; computed tomography; data collection; Datasets; Deep Learning; Endocrinology; Feasibility Studies; Female; Fractures; Humans; Lumbar Vertebrae - diagnostic imaging; Male; Medical screening; Medicine; Medicine & Public Health; Middle Aged; Neural networks; Original; Original Article; Orthopedics; osteopenia; Osteoporosis; Osteoporosis - diagnostic imaging; prediction; Radiography, Thoracic - methods; Radiomics; regression analysis; Retrospective Studies; risk; Risk factors; Tomography, X-Ray Computed - methods; Vertebrae; Deep learning; Osteoporosis; Bone mineral density; Feature fusion; Quantitative CT
• ISSN: 1862-3514; 1862-3522; 1862-3514
• DOI: 10.1007/s11657-024-01455-7

Summary A multi-feature fusion DCNN model for automated evaluation of lumbar vertebrae L1 on chest combined with clinical information and radiomics permits estimation of volumetric bone mineral density for evaluation of osteoporosis. Purpose To develop a multi-feature deep learning model based on chest CT, combined with clinical information and radiomics to explore the feasibility in screening for osteoporosis based on estimation of volumetric bone mineral density. Methods The chest CT images of 1048 health check subjects were retrospectively collected as the master dataset, and the images of 637 subjects obtained from a different CT scanner were used for the external validation cohort. The subjects were divided into three categories according to the quantitative CT (QCT) examination, namely, normal group, osteopenia group, and osteoporosis group. Firstly, a deep learning–based segmentation model was constructed. Then, classification models were established and selected, and then, an optimal model to build bone density value prediction regression model was chosen. Results The DSC value was 0.951 ± 0.030 in the testing dataset and 0.947 ± 0.060 in the external validation cohort. The multi-feature fusion model based on the lumbar 1 vertebra had the best performance in the diagnosis. The area under the curve (AUC) of diagnosing normal, osteopenia, and osteoporosis was 0.992, 0.973, and 0.989. The mean absolute errors (MAEs) of the bone density prediction regression model in the test set and external testing dataset are 8.20 mg/cm 3 and 9.23 mg/cm 3 , respectively, and the root mean square errors (RMSEs) are 10.25 mg/cm 3 and 11.91 mg/cm 3 , respectively. The R -squared values are 0.942 and 0.923, respectively. The Pearson correlation coefficients are 0.972 and 0.965. Conclusion The multi-feature fusion DCNN model based on only the lumbar 1 vertebrae and clinical variables can perform bone density three-classification diagnosis and estimate volumetric bone mineral density. If confirmed in independent populations, this automated opportunistic chest CT evaluation can help clinical screening of large-sample populations to identify subjects at high risk of osteoporotic fracture.