A New Method of Non-Invasive Diagnosis for Human Body Structure Using Pose-Detection

DOI

10.2991/978-94-6463-878-3_8How to use a DOI?

Keywords

AI for Human Body Structure Diagnosis; Modified Blazepose Model; Non-invasive Osteoporotic Diagnosis; Pose Model Estimation with 3D Geometric Translations

Abstract

Human body structures supported by the skeletal system are susceptible to osteoporotic vertebral compression fractures due to aging. The most common fracture among the geriatric population is vertebral fracture (25%), compared to hip fracture (24%). These symptoms, which largely stem from osteoporosis in post-menopausal women and men past their peak bone mass, carry significant health implications. Specifically, it can impair lung function, leading to a reduction in forced vital capacity of up to 9% and a higher risk of fatal pulmonary dysfunction. A diagnosis can be performed using invasive lateral radiography/X-rays, MRI, or bone scans to assess fracture severity. However, the lengthy and costly invasive diagnosis causes difficulties for the elderly. A new method of non-invasive diagnosis for human body structure is introduced. These new methods utilize pose-detection models. The 360-degree pose photos of the elderly are used to generate a 3D reality of elderly body models. This study results show the modified BlazePose detection successfully estimates 3D coordinates of key points of the body’s skeleton. The BlazePose model achieved 97.2% accuracy at an average percent of correct points with 20% tolerance and RMSE of about 30.1 in millimeter units. Through 3D geometric analysis, results found degrees of misaligned of the shoulder, hips, and vertebral translations. The misaligned bone structures, indicated by more than 10 degrees, suggest a high likelihood of a spinal problem. This new method demonstrates an advancement in AI capabilities for medical applications.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - I Ketut Swardika
AU  - Putri Alit Widyastuti Santiary
AU  - Dewa Ayu Indah Cahya Dewi
AU  - I Gusti Agung Made Yoga Mahaputra
PY  - 2025
DA  - 2025/10/31
TI  - A New Method of Non-Invasive Diagnosis for Human Body Structure Using Pose-Detection
BT  - Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2025 (ICOSTAS-EAS 2025)
PB  - Atlantis Press
SP  - 57
EP  - 65
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-878-3_8
DO  - 10.2991/978-94-6463-878-3_8
ID  - Swardika2025
ER  -