Abstract
Highlights
•Understanding the causes of spinal curve progression is hampered by lack of prospective population-based studies
•We have developed an automated method of identification of scoliosis from total body DXA scans based on machine learning
•We have now developed an extension of this automation to quantify size of spinal curve which appears clinically valid
•This new automation may revolutionise scoliosis research by facilitating exploitation of large population-based research cohorts
Abstract
Background
Scoliosis is spinal curvature that may progress to require surgical stabilisation. Risk factors for progression are little understood due to lack of population-based research, since radiographs cannot be performed on entire populations due to high levels of radiation. To help address this, we have previously developed and validated a method for quantification of spinal curvature from total body dual energy X-ray absorptiometry (DXA) scans. The purpose of this study was to automate this quantification of spinal curve size from DXA scans using machine learning techniques.
Methods
To develop the automation of curve size, we utilised manually annotated scans from 7298 participants from the Avon Longitudinal Study of Parents and Children (ALSPAC) at age 9 and 5122 at age 15. To validate the automation we assessed (1) agreement between manual vs automation using the Bland-Altman limits of agreement, (2) reliability by calculating the coefficient of variation, and (3) clinical validity by running the automation on 4969 non-annotated scans at age 18 to assess the associations with physical activity, body composition, adipocyte function and backpain compared to previous literature.
Results
The mean difference between manual vs automated readings was less than one degree, and 90.4 % of manual vs automated readings fell within 10°. The coefficient of variation was 25.4 %. Clinical validation showed the expected relationships between curve size and physical activity, adipocyte function, height and weight.
Conclusion
We have developed a reasonably accurate and valid automated method for quantifying spinal curvature from DXA scans for research purposes.
•Understanding the causes of spinal curve progression is hampered by lack of prospective population-based studies
•We have developed an automated method of identification of scoliosis from total body DXA scans based on machine learning
•We have now developed an extension of this automation to quantify size of spinal curve which appears clinically valid
•This new automation may revolutionise scoliosis research by facilitating exploitation of large population-based research cohorts
Abstract
Background
Scoliosis is spinal curvature that may progress to require surgical stabilisation. Risk factors for progression are little understood due to lack of population-based research, since radiographs cannot be performed on entire populations due to high levels of radiation. To help address this, we have previously developed and validated a method for quantification of spinal curvature from total body dual energy X-ray absorptiometry (DXA) scans. The purpose of this study was to automate this quantification of spinal curve size from DXA scans using machine learning techniques.
Methods
To develop the automation of curve size, we utilised manually annotated scans from 7298 participants from the Avon Longitudinal Study of Parents and Children (ALSPAC) at age 9 and 5122 at age 15. To validate the automation we assessed (1) agreement between manual vs automation using the Bland-Altman limits of agreement, (2) reliability by calculating the coefficient of variation, and (3) clinical validity by running the automation on 4969 non-annotated scans at age 18 to assess the associations with physical activity, body composition, adipocyte function and backpain compared to previous literature.
Results
The mean difference between manual vs automated readings was less than one degree, and 90.4 % of manual vs automated readings fell within 10°. The coefficient of variation was 25.4 %. Clinical validation showed the expected relationships between curve size and physical activity, adipocyte function, height and weight.
Conclusion
We have developed a reasonably accurate and valid automated method for quantifying spinal curvature from DXA scans for research purposes.
Original language | English |
---|---|
Article number | 116775 |
Number of pages | 7 |
Journal | Bone |
Volume | 172 |
Early online date | 18 Apr 2023 |
DOIs | |
Publication status | Published - 1 Jul 2023 |
Bibliographical note
Funding Information:The UK Medical Research Council and Wellcome (Grant ref.: 217065/Z/19/Z ) and the University of Bristol provide core support for ALSPAC. A comprehensive list of grants funding is available on the ALSPAC website http://www.bristol.ac.uk/alspac/external/documents/grant-acknowledgements.pdf . This research was specifically funded by the British Scoliosis Research Foundation . Funding for authors based at the University of Oxford was via an EPSRC Programme Grant Seebibyte ( EP/M013774/1 ).
Publisher Copyright:
© 2023 Elsevier Inc.