Terufumi Kokabu1, Satoshi Kanai2, Noriaki Kawakami3, Koki Uno4, Toshiaki Kotani5, Teppei Suzuki4, Hiroyuki Tachi1, Yuichiro Abe6, Norimasa Iwasaki7, Hideki Sudo8. 1. Department of Orthopedic Surgery, Hokkaido University Hospital, Nishi 5 Chome Kita 14 Jo, Kita Ward, Sapporo, Hokkaido 060-8648, Japan; Department of Orthopedic Surgery, Eniwa Hospital, Koganechuo 2-1-1, Eniwa, Hokkaido 061-1449, Japan. 2. Division of Systems Science and Informatics, Hokkaido University Graduate School of Information Science and Technology, Nishi 9 Chome Kita 13 Jo, Kita Ward, Sapporo, Hokkaido 060-0813, Japan. 3. Department of Orthopedic Surgery, Ichinomiyanishi Hospital, Ichinomiya, Kaimei, Aza Hira 1, 494-0001 Aichi, Japan. 4. Department of Orthopedic Surgery, National Hospital Organization, Kobe Medical Center, 3 Chome-1-1 Nishiochiai, Suma Ward, Kobe, Hyogo 654-0155, Japan. 5. Department of Orthopedic Surgery, Seirei Sakura Citizen Hospital, 2 Chome-36-2 Ebaradai, Sakura, Chiba 285-8765, Japan. 6. Department of Orthopedic Surgery, Eniwa Hospital, Koganechuo 2-1-1, Eniwa, Hokkaido 061-1449, Japan. 7. Department of Orthopedic Surgery, Hokkaido University Hospital, Nishi 5 Chome Kita 14 Jo, Kita Ward, Sapporo, Hokkaido 060-8648, Japan. 8. Department of Orthopedic Surgery, Hokkaido University Hospital, Nishi 5 Chome Kita 14 Jo, Kita Ward, Sapporo, Hokkaido 060-8648, Japan; Department of Advanced Medicine for Spine and Spinal Cord Disorders, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, N15W7, Sapporo, Hokkaido 060-8638, Japan. Electronic address: hidekisudo@yahoo.co.jp.
Abstract
BACKGROUND CONTEXT: Timely 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. PURPOSE: This 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 DESIGN: Retrospective analysis of prospectively collected, consecutive, nonrandomized series of patients at five scoliosis centers in Japan. PATIENT SAMPLE: One hundred and-sixty human subjects suspected to have AIS were included. OUTCOME MEASURES: Patient demographics, radiographic measurements, and predicted Cobb angle derived from the deep learning algorithm were the outcome measures for this study. METHODS: One 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. RESULTS: The 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°. CONCLUSIONS: The 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.
BACKGROUND CONTEXT: Timely 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. PURPOSE: This 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 DESIGN: Retrospective analysis of prospectively collected, consecutive, nonrandomized series of patients at five scoliosis centers in Japan. PATIENT SAMPLE: One hundred and-sixty human subjects suspected to have AIS were included. OUTCOME MEASURES: Patient demographics, radiographic measurements, and predicted Cobb angle derived from the deep learning algorithm were the outcome measures for this study. METHODS: One 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. RESULTS: The 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°. CONCLUSIONS: The 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.
Authors: Nan Meng; Jason P Y Cheung; Kwan-Yee K Wong; Socrates Dokos; Sofia Li; Richard W Choy; Samuel To; Ricardo J Li; Teng Zhang Journal: EClinicalMedicine Date: 2022-01-04
Authors: Benjamin N Groisser; Howard J Hillstrom; Ankush Thakur; Kyle W Morse; Matthew Cunningham; M Timothy Hresko; Ron Kimmel; Alon Wolf; Roger F Widmann Journal: Spine Deform Date: 2022-05-08