Go, G.; Ariga, K.; Tanaka, N.; Oda, K.; Haro, H.; Ohba, T. Clinical Significance of Pose Estimation Methods Compared to Radiographic Parameters in Adolescent Idiopathic Scoliosis Patients. Preprints2023, 2023061370. https://doi.org/10.20944/preprints202306.1370.v1
APA Style
Go, G., Ariga, K., Tanaka, N., Oda, K., Haro, H., & Ohba, T. (2023). Clinical Significance of Pose Estimation Methods Compared to Radiographic Parameters in Adolescent Idiopathic Scoliosis Patients. Preprints. https://doi.org/10.20944/preprints202306.1370.v1
Chicago/Turabian Style
Go, G., Hirotaka Haro and Tetsuro Ohba. 2023 "Clinical Significance of Pose Estimation Methods Compared to Radiographic Parameters in Adolescent Idiopathic Scoliosis Patients" Preprints. https://doi.org/10.20944/preprints202306.1370.v1
Abstract
Background. Pose estimation based on deep learning has been expected to be a breakthrough method to increase the accuracy of clinical photographic evaluation and to decrease interobserver errors. The purpose is to quantify pose estimation from photography of patients with adolescent idiopathic scoliosis (AIS) using open-source software packages and determine correlations between parameters obtained by radiography and photography. Methods. We included 12 consecutive patients with AIS treated with spinal correction surgery. Photographs were taken preoperatively using a tripod-mounted camera (iPhone 13Pro) on an X-ray tube head. To assess photographic parameters obtained by photography, we defined 17 points to analyze posture and define parameters. Results. In the sagittal plane, there was a significant correlation between the radiographic trunk tilt angle and the photographic sagittal trunk tilt angle of the shoulder–hip and ear–hip. In the coronal plane, there was a significant correlation between the radiographic clavicle angle and the photographic shoulder height angle, and the radiographic C7–CSVL and the photographic coronal trunk tilt angle. Conclusions. Posture analysis by photography using popular mobile devices has clinical utility for improving and promoting the screening and early detection of AIS because it is simple, without patient exposure to X-ray radiation.
Keywords
adolescent idiopathic scoliosis; pose estimation; posture parameters; mobile devices; deep learning; clinical photography; mobile applications; MoveNet, convolutional neural network; kinematics; posture; reliability; validity
Subject
Physical Sciences, Radiation and Radiography
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.