Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN model

Abstract

Abstract Objective To develop and evaluate a chest CT deep learning model that achieves favorable performance on opportunistic osteoporosis screening using the lumbar 1 + lumbar 2 vertebral body fusion feature images, and explore the feasibility and effectiveness of the model based on the lumbar 1 vertebral alone. Materials and methods The chest CT images of 1048 physical examination subjects from January 2021 to June wereretrospectively collected as the internal dataset (548 for training, 100 for tuning and 400 for test for the segmentation model and 530 for training, 100 for validation and 418 for test set for the classification model). The subjects were divided into three categories according to the quantitative CT measurements, namely, normal, osteopenia and osteoporosis. First, a deep learning-based segmentation model was constructed, and the Dice similarity coefficient was used to compare the consistency between the model and manual labelling. Then, 2 classification models were established, namely, 1) model 1 (fusion feature construction of lumbar vertebral bodies 1 and 2) and 2) model 2 (feature construction of lumbar 1 alone). Receiver operating characteristic curves were used to evaluate the diagnostic efficacy of the models, and the Delong test was used to compare the areas under the curve. Results When the number of images in the training set was 300, the DSC value was 0.951±0.030 in the test set. The results showed that the model 1 diagnosing osteopenia achieved an AUC of 0.952; The model 1 diagnosing osteoporosis achieved an AUC of 0.980; the model 2 diagnosing osteopenia achieved an AUC of 0.940; the model 2 diagnosing osteoporosis achieved an AUC of 0.978. The Delong test showed that there was no significant difference in AUC values between the osteopenia group and osteoporosis group (P=0.210, 0.546), while the AUC value of normal model 2 was higher than that of model 1 (0.990 vs. 0.983) (P=0.033). Conclusion This study proposed a chest CT deep learning model that achieves favorable performance on opportunistic osteoporosis screening using the lumbar 1 + lumbar 2 vertebral body fusion feature images.. we further constructed the comparable model based on the lumbar 1 vertebra alone which can shorten the scan length, reduce the radiation dose received by patients, and reduce the training cost of technicians.