Abstract
BACKGROUND CONTEXTTimely intervention in growing individuals, such as brace treatment, relies on early detection of adolescent idiopathic scoliosis (AIS). To this end, several screening methods have been implemented. However, these methods have limitations in predicting the Cobb angle. PURPOSEThis study aimed to evaluate the performance of a three-dimensional depth sensor imaging system with a deep learning algorithm, in predicting the Cobb angle in AIS. STUDY DESIGNRetrospective analysis of prospectively collected, consecutive, nonrandomized series of patients at five scoliosis centers in Japan. PATIENT SAMPLEOne hundred and-sixty human subjects suspected to have AIS were included. OUTCOME MEASURESPatient demographics, radiographic measurements, and predicted Cobb angle derived from the deep learning algorithm were the outcome measures for this study. METHODSOne hundred and sixty data files were shuffled into five datasets with 32 data files at random (dataset 1, 2, 3, 4, and 5) and five-fold cross validation was performed. The relationships between the actual and predicted Cobb angles were calculated using Pearson's correlation coefficient analyses. The prediction performances of the network models were evaluated using mean absolute error and root mean square error between the actual and predicted Cobb angles. The shuffling into five datasets and five-fold cross validation was conducted ten times. There were no study-specific biases related to conflicts of interest. RESULTSThe correlation between the actual and the mean predicted Cobb angles was 0.91. The mean absolute error and root mean square error were 4.0° and 5.4°, respectively. The accuracy of the mean predicted Cobb angle was 94% for identifying a Cobb angle of ≥10° and 89% for that of ≥20°. CONCLUSIONSThe three-dimensional depth sensor imaging system with its newly innovated convolutional neural network for regression is objective and has significant ability to predict the Cobb angle in children and adolescents. This system is expected to be used for screening scoliosis in clinics or physical examination at schools.
Highlights
Adolescent idiopathic scoliosis (AIS) is most the common musculoskeletal disease in children of school-going age
We evaluated whether the deep learning algorithms (DLAs)/neural network could identify the location of the curve
We evaluated whether the DLA/neural network identified the location of the curve based on location/apex of the curves (Table 4)
Summary
Adolescent idiopathic scoliosis (AIS) is most the common musculoskeletal disease in children of school-going age. Intervention in growing individuals, such as brace treatment, relies on early detection of AIS To this end, several screening methods have been implemented. The direction of the light source should be vertical to the back [4] and is not designed to be shot with a forward bend of the trunk, resulting in high false positive rates (32%−60%) [6−9] To overcome these limitations, we developed a system consisting of a threedimensional (3D) depth sensor and an algorithm installed in a laptop computer [4, 10]. Intervention in growing individuals, such as brace treatment, relies on early detection of adolescent idiopathic scoliosis (AIS). The accuracy of the mean predicted Cobb angle was 94% for identifying a Cobb angle of ≥10 ̊ and 89% for that of ≥20 ̊
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
