Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN model
Abstract Objective To develop and evaluate a deep learning model based on chest CT that achieves favorable performance on opportunistic osteoporosis screening using the lumbar 1 + lumbar 2 vertebral bodies fusion feature images, and explore the feasibility and effectiveness of the model based on the...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-02-01
|
| Series: | BMC Musculoskeletal Disorders |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12891-024-07297-1 |
| _version_ | 1827328916413480960 |
|---|---|
| author | Jing Pan Peng-cheng Lin Shen-chu Gong Ze Wang Rui Cao Yuan Lv Kun Zhang Lin Wang |
| author_facet | Jing Pan Peng-cheng Lin Shen-chu Gong Ze Wang Rui Cao Yuan Lv Kun Zhang Lin Wang |
| author_sort | Jing Pan |
| collection | DOAJ |
| description | Abstract Objective To develop and evaluate a deep learning model based on chest CT that achieves favorable performance on opportunistic osteoporosis screening using the lumbar 1 + lumbar 2 vertebral bodies fusion feature images, and explore the feasibility and effectiveness of the model based on the lumbar 1 vertebral body alone. Materials and methods The chest CT images of 1048 health check subjects from January 2021 to June were retrospectively collected as the internal dataset (the segmentation model: 548 for training, 100 for tuning and 400 for test. The classification model: 530 for training, 100 for validation and 418 for test set). 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(DSC) was used to compare the consistency between the model and manual labelling. Then, two classification models were established, namely, (i) model 1 (fusion feature construction of lumbar vertebral bodies 1 and 2) and (ii) 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 normal, osteopenia and osteoporosis achieved an AUC of 0.990, 0.952 and 0.980; the model 2 diagnosing normal, osteopenia and osteoporosis achieved an AUC of 0.983, 0.940 and 0.978. The Delong test showed that there was no significant difference in area under the curve (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 bodies 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 technologists. |
| first_indexed | 2024-03-07T15:25:18Z |
| format | Article |
| id | doaj.art-eb51213d06ed45ce86e9e417ba01419c |
| institution | Directory Open Access Journal |
| issn | 1471-2474 |
| language | English |
| last_indexed | 2024-03-07T15:25:18Z |
| publishDate | 2024-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Musculoskeletal Disorders |
| spelling | doaj.art-eb51213d06ed45ce86e9e417ba01419c2024-03-05T17:23:59ZengBMCBMC Musculoskeletal Disorders1471-24742024-02-0125111310.1186/s12891-024-07297-1Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN modelJing Pan0Peng-cheng Lin1Shen-chu Gong2Ze Wang3Rui Cao4Yuan Lv5Kun Zhang6Lin Wang7Department of Radiology, Nanjing Hospital of Chinese Medicine Affiliated to Nanjing University of Chinese MedicineSchool of Electrical Engineering, Nantong UniversityDepartment of Radiology, The First People’s Hospital of Nantong/The Second Affiliated Hospital of Nantong UniversityDepartment of Radiology, The First People’s Hospital of Nantong/The Second Affiliated Hospital of Nantong UniversityDepartment of Radiology, The First People’s Hospital of Nantong/The Second Affiliated Hospital of Nantong UniversityDepartment of Radiology, The First People’s Hospital of Nantong/The Second Affiliated Hospital of Nantong UniversitySchool of Electrical Engineering, Nantong UniversityDepartment of Radiology, The First People’s Hospital of Nantong/The Second Affiliated Hospital of Nantong UniversityAbstract Objective To develop and evaluate a deep learning model based on chest CT that achieves favorable performance on opportunistic osteoporosis screening using the lumbar 1 + lumbar 2 vertebral bodies fusion feature images, and explore the feasibility and effectiveness of the model based on the lumbar 1 vertebral body alone. Materials and methods The chest CT images of 1048 health check subjects from January 2021 to June were retrospectively collected as the internal dataset (the segmentation model: 548 for training, 100 for tuning and 400 for test. The classification model: 530 for training, 100 for validation and 418 for test set). 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(DSC) was used to compare the consistency between the model and manual labelling. Then, two classification models were established, namely, (i) model 1 (fusion feature construction of lumbar vertebral bodies 1 and 2) and (ii) 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 normal, osteopenia and osteoporosis achieved an AUC of 0.990, 0.952 and 0.980; the model 2 diagnosing normal, osteopenia and osteoporosis achieved an AUC of 0.983, 0.940 and 0.978. The Delong test showed that there was no significant difference in area under the curve (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 bodies 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 technologists.https://doi.org/10.1186/s12891-024-07297-1OsteoporosisQuantitative CTDeep learningBone mineral densityChest CT |
| spellingShingle | Jing Pan Peng-cheng Lin Shen-chu Gong Ze Wang Rui Cao Yuan Lv Kun Zhang Lin Wang Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN model BMC Musculoskeletal Disorders Osteoporosis Quantitative CT Deep learning Bone mineral density Chest CT |
| title | Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN model |
| title_full | Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN model |
| title_fullStr | Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN model |
| title_full_unstemmed | Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN model |
| title_short | Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN model |
| title_sort | effectiveness of opportunistic osteoporosis screening on chest ct using the dcnn model |
| topic | Osteoporosis Quantitative CT Deep learning Bone mineral density Chest CT |
| url | https://doi.org/10.1186/s12891-024-07297-1 |
| work_keys_str_mv | AT jingpan effectivenessofopportunisticosteoporosisscreeningonchestctusingthedcnnmodel AT pengchenglin effectivenessofopportunisticosteoporosisscreeningonchestctusingthedcnnmodel AT shenchugong effectivenessofopportunisticosteoporosisscreeningonchestctusingthedcnnmodel AT zewang effectivenessofopportunisticosteoporosisscreeningonchestctusingthedcnnmodel AT ruicao effectivenessofopportunisticosteoporosisscreeningonchestctusingthedcnnmodel AT yuanlv effectivenessofopportunisticosteoporosisscreeningonchestctusingthedcnnmodel AT kunzhang effectivenessofopportunisticosteoporosisscreeningonchestctusingthedcnnmodel AT linwang effectivenessofopportunisticosteoporosisscreeningonchestctusingthedcnnmodel |