Scoliosis screening system based on improved optical photogrammetry using a Kinect sensor

Abstract Background Scoliosis has become an important factor affecting human health, and there is a trend of younger age, so it is necessary to carry out scoliosis screening in communities and schools. However, common methods of scoliosis screening, such as manual physical examination and X-ray, require the experience of a professional physician and the procedure is complex, so they cannot meet requirements of fast, convenient and low cost. This paper presents a scoliosis screening system based on improved optical photogrammetry using Kinect sensor. Methods Color image and depth image collected by Kinect sensor are aligned to generate 3D point cloud. Unnecessary points are removed by filtering and segmentation methods, and the interested back point cloud is obtained. Representative points of two shoulders and anatomical landmarks on the back are extracted, and spine curve is fitted based on the points in the middle of the back derived from depth data. Uneven shoulders, Deep optics-based scoliosis assessment (DOSA) angle, kyphosis index and angle of trunk rotation (ATR) are combined to determine whether the spine is abnormal from three anatomical planes. Results Forty subjects with possible scoliosis were tested. Cobb angles were obtained based on X-ray imaging and DOSA angles were obtained by photographic imaging. The mean difference between the two angles mentioned above for all subjects was − 0.386°, and the variance was 7.773. 87.5% of the angle difference was between − 3° and 3°. When significant level a is 0.05, the critical value t 0.05 (39) equals ± 2.023, t value calculated according to the experimental data is -0.877, Cohen d is 0.138 and r 2 is 0.0193. It can be seen that the difference between the DOSA angle and the traditional standard Cobb angle is small. Conclusions For most subjects, measured values of scoliosis using this scoliosis screening system are similar to those obtained by X-ray, and have advantages of no radiation, lower cost, and more convenience.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-08-21
DOI
https://doi.org/10.1038/s41598-026-68082-9
Primary Topic
Scoliosis diagnosis and treatment
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Scoliosis screening system based on improved optical photogrammetry using a Kinect sensor

Tangzhu Yang, Yangshiyu Zhou, Xia LIU, Mingbo LI et al.
Scientific Reports
Scoliosis diagnosis and treatment
article

Scoliosis screening system based on improved optical photogrammetry using a Kinect sensor

Tangzhu Yang, Yangshiyu Zhou, Xia LIU, Mingbo LI, Zhaoyang LI
article en

Abstract

Abstract Background Scoliosis has become an important factor affecting human health, and there is a trend of younger age, so it is necessary to carry out scoliosis screening in communities and schools. However, common methods of scoliosis screening, such as manual physical examination and X-ray, require the experience of a professional physician and the procedure is complex, so they cannot meet requirements of fast, convenient and low cost. This paper presents a scoliosis screening system based on improved optical photogrammetry using Kinect sensor. Methods Color image and depth image collected by Kinect sensor are aligned to generate 3D point cloud. Unnecessary points are removed by filtering and segmentation methods, and the interested back point cloud is obtained. Representative points of two shoulders and anatomical landmarks on the back are extracted, and spine curve is fitted based on the points in the middle of the back derived from depth data. Uneven shoulders, Deep optics-based scoliosis assessment (DOSA) angle, kyphosis index and angle of trunk rotation (ATR) are combined to determine whether the spine is abnormal from three anatomical planes. Results Forty subjects with possible scoliosis were tested. Cobb angles were obtained based on X-ray imaging and DOSA angles were obtained by photographic imaging. The mean difference between the two angles mentioned above for all subjects was − 0.386°, and the variance was 7.773. 87.5% of the angle difference was between − 3° and 3°. When significant level a is 0.05, the critical value t 0.05 (39) equals ± 2.023, t value calculated according to the experimental data is -0.877, Cohen d is 0.138 and r 2 is 0.0193. It can be seen that the difference between the DOSA angle and the traditional standard Cobb angle is small. Conclusions For most subjects, measured values of scoliosis using this scoliosis screening system are similar to those obtained by X-ray, and have advantages of no radiation, lower cost, and more convenience.

Scientific Reports
Wuhan University of Technology (CN), Jianghan University (CN), Wuchang University of Technology (CN)
Quality Education
Openalex Percentile: Top 27%
Scoliosis diagnosis and treatment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.