Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and Forearm
<b>Background</b>: We investigated whether opportunistic screening for osteoporosis can be done from computed tomography (CT) scans of the wrist/forearm using machine learning. <b>Methods:</b> A retrospective study of 196 patients aged 50 years or greater who underwent CT sca...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/3/691 |
| _version_ | 1827649402391494656 |
|---|---|
| author | Ronnie Sebro Cynthia De la Garza-Ramos |
| author_facet | Ronnie Sebro Cynthia De la Garza-Ramos |
| author_sort | Ronnie Sebro |
| collection | DOAJ |
| description | <b>Background</b>: We investigated whether opportunistic screening for osteoporosis can be done from computed tomography (CT) scans of the wrist/forearm using machine learning. <b>Methods:</b> A retrospective study of 196 patients aged 50 years or greater who underwent CT scans of the wrist/forearm and dual-energy X-ray absorptiometry (DEXA) scans within 12 months of each other was performed. Volumetric segmentation of the forearm, carpal, and metacarpal bones was performed to obtain the mean CT attenuation of each bone. The correlations of the CT attenuations of each of the wrist/forearm bones and their correlations to the DEXA measurements were calculated. The study was divided into training/validation (n = 96) and test (n = 100) datasets. The performance of multivariable support vector machines (SVMs) was evaluated in the test dataset and compared to the CT attenuation of the distal third of the radial shaft (radius 33%). <b>Results:</b> There were positive correlations between each of the CT attenuations of the wrist/forearm bones, and with DEXA measurements. A threshold hamate CT attenuation of 170.2 Hounsfield units had a sensitivity of 69.2% and a specificity of 77.1% for identifying patients with osteoporosis. The radial-basis-function (RBF) kernel SVM (AUC = 0.818) was the best for predicting osteoporosis with a higher AUC than other models and better than the radius 33% (AUC = 0.576) (<i>p</i> = 0.020). <b>Conclusions:</b> Opportunistic screening for osteoporosis could be performed using CT scans of the wrist/forearm. Multivariable machine learning techniques, such as SVM with RBF kernels, that use data from multiple bones were more accurate than using the CT attenuation of a single bone. |
| first_indexed | 2024-03-09T19:56:33Z |
| format | Article |
| id | doaj.art-b20406a3e6c94b0a8504e53912c9f767 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T19:56:33Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-b20406a3e6c94b0a8504e53912c9f7672023-11-24T00:55:46ZengMDPI AGDiagnostics2075-44182022-03-0112369110.3390/diagnostics12030691Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and ForearmRonnie Sebro0Cynthia De la Garza-Ramos1Mayo Clinic Florida, Department of Radiology, Jacksonville, FL 32224, USAMayo Clinic Florida, Department of Radiology, Jacksonville, FL 32224, USA<b>Background</b>: We investigated whether opportunistic screening for osteoporosis can be done from computed tomography (CT) scans of the wrist/forearm using machine learning. <b>Methods:</b> A retrospective study of 196 patients aged 50 years or greater who underwent CT scans of the wrist/forearm and dual-energy X-ray absorptiometry (DEXA) scans within 12 months of each other was performed. Volumetric segmentation of the forearm, carpal, and metacarpal bones was performed to obtain the mean CT attenuation of each bone. The correlations of the CT attenuations of each of the wrist/forearm bones and their correlations to the DEXA measurements were calculated. The study was divided into training/validation (n = 96) and test (n = 100) datasets. The performance of multivariable support vector machines (SVMs) was evaluated in the test dataset and compared to the CT attenuation of the distal third of the radial shaft (radius 33%). <b>Results:</b> There were positive correlations between each of the CT attenuations of the wrist/forearm bones, and with DEXA measurements. A threshold hamate CT attenuation of 170.2 Hounsfield units had a sensitivity of 69.2% and a specificity of 77.1% for identifying patients with osteoporosis. The radial-basis-function (RBF) kernel SVM (AUC = 0.818) was the best for predicting osteoporosis with a higher AUC than other models and better than the radius 33% (AUC = 0.576) (<i>p</i> = 0.020). <b>Conclusions:</b> Opportunistic screening for osteoporosis could be performed using CT scans of the wrist/forearm. Multivariable machine learning techniques, such as SVM with RBF kernels, that use data from multiple bones were more accurate than using the CT attenuation of a single bone.https://www.mdpi.com/2075-4418/12/3/691computed tomographyCT attenuationmetacarpalradiusulnascaphoid |
| spellingShingle | Ronnie Sebro Cynthia De la Garza-Ramos Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and Forearm Diagnostics computed tomography CT attenuation metacarpal radius ulna scaphoid |
| title | Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and Forearm |
| title_full | Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and Forearm |
| title_fullStr | Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and Forearm |
| title_full_unstemmed | Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and Forearm |
| title_short | Machine Learning for Opportunistic Screening for Osteoporosis from CT Scans of the Wrist and Forearm |
| title_sort | machine learning for opportunistic screening for osteoporosis from ct scans of the wrist and forearm |
| topic | computed tomography CT attenuation metacarpal radius ulna scaphoid |
| url | https://www.mdpi.com/2075-4418/12/3/691 |
| work_keys_str_mv | AT ronniesebro machinelearningforopportunisticscreeningforosteoporosisfromctscansofthewristandforearm AT cynthiadelagarzaramos machinelearningforopportunisticscreeningforosteoporosisfromctscansofthewristandforearm |