Deep Learning for Bone Mineral Density and T-Score Prediction from Chest X-rays: A Multicenter Study
Although the number of patients with osteoporosis is increasing worldwide, diagnosis and treatment are presently inadequate. In this study, we developed a deep learning model to predict bone mineral density (BMD) and T-score from chest X-rays, which are one of the most common, easily accessible, and...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Biomedicines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9059/10/9/2323 |
| _version_ | 1797490808504451072 |
|---|---|
| author | Yoichi Sato Norio Yamamoto Naoya Inagaki Yusuke Iesaki Takamune Asamoto Tomohiro Suzuki Shunsuke Takahara |
| author_facet | Yoichi Sato Norio Yamamoto Naoya Inagaki Yusuke Iesaki Takamune Asamoto Tomohiro Suzuki Shunsuke Takahara |
| author_sort | Yoichi Sato |
| collection | DOAJ |
| description | Although the number of patients with osteoporosis is increasing worldwide, diagnosis and treatment are presently inadequate. In this study, we developed a deep learning model to predict bone mineral density (BMD) and T-score from chest X-rays, which are one of the most common, easily accessible, and low-cost medical imaging examination methods. The dataset used in this study contained patients who underwent dual-energy X-ray absorptiometry (DXA) and chest radiography at six hospitals between 2010 and 2021. We trained the deep learning model through ensemble learning of chest X-rays, age, and sex to predict BMD using regression and T-score for multiclass classification. We assessed the following two metrics to evaluate the performance of the deep learning model: (1) correlation between the predicted and true BMDs and (2) consistency in the T-score between the predicted class and true class. The correlation coefficients for BMD prediction were hip = 0.75 and lumbar spine = 0.63. The areas under the curves for the T-score predictions of normal, osteopenia, and osteoporosis diagnoses were 0.89, 0.70, and 0.84, respectively. These results suggest that the proposed deep learning model may be suitable for screening patients with osteoporosis by predicting BMD and T-score from chest X-rays. |
| first_indexed | 2024-03-10T00:38:22Z |
| format | Article |
| id | doaj.art-6f5859fbaa5742e59913b63f56325f96 |
| institution | Directory Open Access Journal |
| issn | 2227-9059 |
| language | English |
| last_indexed | 2024-03-10T00:38:22Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomedicines |
| spelling | doaj.art-6f5859fbaa5742e59913b63f56325f962023-11-23T15:12:53ZengMDPI AGBiomedicines2227-90592022-09-01109232310.3390/biomedicines10092323Deep Learning for Bone Mineral Density and T-Score Prediction from Chest X-rays: A Multicenter StudyYoichi Sato0Norio Yamamoto1Naoya Inagaki2Yusuke Iesaki3Takamune Asamoto4Tomohiro Suzuki5Shunsuke Takahara6Department of Orthopedics Surgery, Japan Community Healthcare Organization (JCHO) Tokyo Shinjuku Medical Center, Tokyo 162-8543, JapanDepartment of Orthopedics Surgery, Miyamoto Orthopaedic Hospital, Okayama 703-8236, JapanDepartment of Orthopedics Surgery, The Jikei University Kashiwa Hospital, Chiba 277-8567, JapanDepartment of Orthopedics Surgery, The National Hospital Organization Nagoya Medical Center, Nagoya 460-0001, JapanDepartment of Orthopedics Surgery, Gamagori City Hospital, Gamagori 443-8501, JapaniSurgery Co., Ltd., Tokyo 103-0012, JapanDepartment of Orthopaedics Surgery, Hyogo Prefectural Kakogawa Medical Center, Kakogawa 675-0003, JapanAlthough the number of patients with osteoporosis is increasing worldwide, diagnosis and treatment are presently inadequate. In this study, we developed a deep learning model to predict bone mineral density (BMD) and T-score from chest X-rays, which are one of the most common, easily accessible, and low-cost medical imaging examination methods. The dataset used in this study contained patients who underwent dual-energy X-ray absorptiometry (DXA) and chest radiography at six hospitals between 2010 and 2021. We trained the deep learning model through ensemble learning of chest X-rays, age, and sex to predict BMD using regression and T-score for multiclass classification. We assessed the following two metrics to evaluate the performance of the deep learning model: (1) correlation between the predicted and true BMDs and (2) consistency in the T-score between the predicted class and true class. The correlation coefficients for BMD prediction were hip = 0.75 and lumbar spine = 0.63. The areas under the curves for the T-score predictions of normal, osteopenia, and osteoporosis diagnoses were 0.89, 0.70, and 0.84, respectively. These results suggest that the proposed deep learning model may be suitable for screening patients with osteoporosis by predicting BMD and T-score from chest X-rays.https://www.mdpi.com/2227-9059/10/9/2323osteoporosisscreeningDXABMDchest X-raydeep learning |
| spellingShingle | Yoichi Sato Norio Yamamoto Naoya Inagaki Yusuke Iesaki Takamune Asamoto Tomohiro Suzuki Shunsuke Takahara Deep Learning for Bone Mineral Density and T-Score Prediction from Chest X-rays: A Multicenter Study Biomedicines osteoporosis screening DXA BMD chest X-ray deep learning |
| title | Deep Learning for Bone Mineral Density and T-Score Prediction from Chest X-rays: A Multicenter Study |
| title_full | Deep Learning for Bone Mineral Density and T-Score Prediction from Chest X-rays: A Multicenter Study |
| title_fullStr | Deep Learning for Bone Mineral Density and T-Score Prediction from Chest X-rays: A Multicenter Study |
| title_full_unstemmed | Deep Learning for Bone Mineral Density and T-Score Prediction from Chest X-rays: A Multicenter Study |
| title_short | Deep Learning for Bone Mineral Density and T-Score Prediction from Chest X-rays: A Multicenter Study |
| title_sort | deep learning for bone mineral density and t score prediction from chest x rays a multicenter study |
| topic | osteoporosis screening DXA BMD chest X-ray deep learning |
| url | https://www.mdpi.com/2227-9059/10/9/2323 |
| work_keys_str_mv | AT yoichisato deeplearningforbonemineraldensityandtscorepredictionfromchestxraysamulticenterstudy AT norioyamamoto deeplearningforbonemineraldensityandtscorepredictionfromchestxraysamulticenterstudy AT naoyainagaki deeplearningforbonemineraldensityandtscorepredictionfromchestxraysamulticenterstudy AT yusukeiesaki deeplearningforbonemineraldensityandtscorepredictionfromchestxraysamulticenterstudy AT takamuneasamoto deeplearningforbonemineraldensityandtscorepredictionfromchestxraysamulticenterstudy AT tomohirosuzuki deeplearningforbonemineraldensityandtscorepredictionfromchestxraysamulticenterstudy AT shunsuketakahara deeplearningforbonemineraldensityandtscorepredictionfromchestxraysamulticenterstudy |