Abstract

Within the scope of this investigation, we carried out experiments to investigate the potential of the Vision Transformer (ViT) in the field of medical image analysis. The diagnosis of osteoporosis through inspection of X-ray radio-images is a substantial classification problem that we were able to address with the assistance of Vision Transformer models. In order to provide a basis for comparison, we conducted a parallel analysis in which we sought to solve the same problem by employing traditional convolutional neural networks (CNNs), which are well-known and commonly used techniques for the solution of image categorization issues. The findings of our research led us to conclude that ViT is capable of achieving superior outcomes compared to CNN. Furthermore, provided that methods have access to a sufficient quantity of training data, the probability increases that both methods arrive at more appropriate solutions to critical issues.

Details

Title
Comparative analysis of vision transformers and convolutional neural networks in osteoporosis detection from X-ray images
Author
Sarmadi, Ali 1 ; Razavi, Zahra Sadat 2 ; van Wijnen, Andre J. 3 ; Soltani, Madjid 4 

 K. N. Toosi University of Technology, Department of Mechanical Engineering, Tehran, Iran (GRID:grid.411976.c) (ISNI:0000 0004 0369 2065) 
 K. N. Toosi University of Technology, Department of Mechanical Engineering, Tehran, Iran (GRID:grid.411976.c) (ISNI:0000 0004 0369 2065); Iran University Medical Sciences, Physiology Research Center, Tehran, Iran (GRID:grid.411746.1) (ISNI:0000 0004 4911 7066); Iran University Medical Sciences, Biochemistry Research Center, Tehran, Iran (GRID:grid.411746.1) (ISNI:0000 0004 4911 7066) 
 University of Vermont, Department of Biochemistry, Burlington, USA (GRID:grid.59062.38) (ISNI:0000 0004 1936 7689); Erasmus University Medical Center, Department of Internal Medicine, Rotterdam, The Netherlands (GRID:grid.5645.2) (ISNI:0000 0004 0459 992X) 
 K. N. Toosi University of Technology, Department of Mechanical Engineering, Tehran, Iran (GRID:grid.411976.c) (ISNI:0000 0004 0369 2065); University of Waterloo, Department of Electrical and Computer Engineering, Waterloo, Canada (GRID:grid.46078.3d) (ISNI:0000 0000 8644 1405); University of Waterloo, Centre for Biotechnology and Bioengineering (CBB), Waterloo, Canada (GRID:grid.46078.3d) (ISNI:0000 0000 8644 1405); BC Cancer Research Institute, Department of Integrative Oncology, Vancouver, Canada (GRID:grid.46078.3d); International Business University, Centre for Sustainable Business, Toronto, Canada (GRID:grid.46078.3d) 
Pages
18007
Publication year
2024
Publication date
2024
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
3087617892
Copyright
© The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.