An AI Approach for Human Body Structure Diagnosis

DOI

10.2991/978-94-6463-926-1_15How to use a DOI?

Keywords

Computer Vision; Human Body Structure Diagnosis; Pose Detection Models; Vertebral Fracture Osteoporosis

Abstract

Artificial Intelligence (AI) is rapidly transforming medical technology. By analyzing vast datasets, AI enhances diagnostic accuracy, optimizes treat-ment plans, and accelerates drug discovery. It also improves patient care through remote monitoring and personalized medicine. Nowadays, human body structure diagnosis uses invasive electromagnetic waves, i.e., X-rays, CT scans, or MRI, advanced imaging. AI has been integrated with these, enhancing accuracy and efficiency through image analysis and predictive modeling. However, the high cost of instrument access can be challenging, especially for the elderly in large population countries. AI through computer vision has the possibility to predict human body joints or landmarks with pose detection models. This paper shows a brief method, results, and discusses diagnosis of human body structure, e.g., vertebral fracture osteoporosis (VF), using pose detection models. First, pose models determined the shoulder-hip joints of subjects of VF. Further analysis computes the slopes of shoulder line, hip line, and vertebral line. Diagnosis is determined by degrees of deviation of these lines from a perpendicular line as a reference. Results show subjects suffering from VF have the highest degrees of deviation. The BlazePose model successfully points to landmark poses coordinate within maximum mAP (100%). Subject of VCF diagnosis with 10 degrees inclination of spinal alignment. Due to limited resources, this paper does not cover standard degrees of deviation and metrics benchmarking.

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  - 2025/12/31
TI  - An AI Approach for Human Body Structure Diagnosis
BT  - Proceedings of the International Conference on Applied Science and Technology on Engineering Science 2025 (iCAST-ES 2025)
PB  - Atlantis Press
SP  - 119
EP  - 128
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-926-1_15
DO  - 10.2991/978-94-6463-926-1_15
ID  - Swardika2025
ER  -