HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Medicine / Faculty of Medicine >
Peer-reviewed Journal Articles, etc >

Prediction of Cobb Angle Using Deep Learning Algorithm with Three-Dimensional Depth Sensor Considering the Influence of Garment in Idiopathic Scoliosis

Files in This Item:

The file(s) associated with this item can be obtained from the following URL:

Title: Prediction of Cobb Angle Using Deep Learning Algorithm with Three-Dimensional Depth Sensor Considering the Influence of Garment in Idiopathic Scoliosis
Authors: Ishikawa, Yoko Browse this author
Kokabu, Terufumi Browse this author
Yamada, Katsuhisa Browse this author
Abe, Yuichiro Browse this author
Tachi, Hiroyuki Browse this author
Suzuki, Hisataka Browse this author
Ohnishi, Takashi Browse this author
Endo, Tsutomu Browse this author
Ukeba, Daisuke Browse this author
Ura, Katsuro Browse this author
Takahata, Masahiko Browse this author
Iwasaki, Norimasa Browse this author →KAKEN DB
Sudo, Hideki Browse this author →KAKEN DB
Keywords: adolescent idiopathic scoliosis
deep learning algorithm
three-dimensional depth sensor
Issue Date: 7-Jan-2023
Publisher: MDPI
Journal Title: Journal of clinical medicine
Volume: 12
Issue: 2
Start Page: 499
Publisher DOI: 10.3390/jcm12020499
Abstract: Adolescent idiopathic scoliosis (AIS) is the most common pediatric spinal deformity. Early detection of deformity and timely intervention, such as brace treatment, can help inhibit progressive changes. A three-dimensional (3D) depth-sensor imaging system with a convolutional neural network was previously developed to predict the Cobb angle. The purpose of the present study was to (1) evaluate the performance of the deep learning algorithm (DLA) in predicting the Cobb angle and (2) assess the predictive ability depending on the presence or absence of clothing in a prospective analysis. We included 100 subjects with suspected AIS. The correlation coefficient between the actual and predicted Cobb angles was 0.87, and the mean absolute error and root mean square error were 4.7 degrees and 6.0 degrees, respectively, for Adam's forward bending without underwear. There were no significant differences in the correlation coefficients between the groups with and without underwear in the forward-bending posture. The performance of the DLA with a 3D depth sensor was validated using an independent external validation dataset. Because the psychological burden of children and adolescents on naked body imaging is an unignorable problem, scoliosis examination with underwear is a valuable alternative in clinics or schools.
Type: article
Appears in Collections:医学院・医学研究院 (Graduate School of Medicine / Faculty of Medicine) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Export metadata:

OAI-PMH ( junii2 , jpcoar_1.0 )

MathJax is now OFF:


 - Hokkaido University