Journal of International Academy of Physical Therapy Research (국제물리치료학회지)

International Academy of Physical Therapy Research (국제물리치료연구학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning Frameworks for Cervical Mobilization Based on Website Images

  • Choi, Wansuk (Department of Physical Therapy, International University of Korea) ;
  • Heo, Seoyoon (Department of Occupational Therapy, Kyungbok University)
  • Received : 2020.12.11
  • Accepted : 2021.01.20
  • Published : 2021.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Background: Deep learning related research works on website medical images have been actively conducted in the field of health care, however, articles related to the musculoskeletal system have been introduced insufficiently, deep learning-based studies on classifying orthopedic manual therapy images would also just be entered. Objectives: To create a deep learning model that categorizes cervical mobilization images and establish a web application to find out its clinical utility. Design: Research and development. Methods: Three types of cervical mobilization images (central posteroanterior (CPA) mobilization, unilateral posteroanterior (UPA) mobilization, and anteroposterior (AP) mobilization) were obtained using functions of 'Download All Images' and a web crawler. Unnecessary images were filtered from 'Auslogics Duplicate File Finder' to obtain the final 144 data (CPA=62, UPA=46, AP=36). Training classified into 3 classes was conducted in Teachable Machine. The next procedures, the trained model source was uploaded to the web application cloud integrated development environment (https://ide.goorm.io/) and the frame was built. The trained model was tested in three environments: Teachable Machine File Upload (TMFU), Teachable Machine Webcam (TMW), and Web Service webcam (WSW). Results: In three environments (TMFU, TMW, WSW), the accuracy of CPA mobilization images was 81-96%. The accuracy of the UPA mobilization image was 43~94%, and the accuracy deviation was greater than that of CPA. The accuracy of the AP mobilization image was 65-75%, and the deviation was not large compared to the other groups. In the three environments, the average accuracy of CPA was 92%, and the accuracy of UPA and AP was similar up to 70%. Conclusion: This study suggests that training of images of orthopedic manual therapy using machine learning open software is possible, and that web applications made using this training model can be used clinically.

Keywords

References

  1. Giansanti D. The Artificial Intelligence in Digital Pathology and Digital Radiology: Where Are We? Healthcare. 2021;9(1):30. doi:10.3390/healthcare9010030
  2. Heo M-S, Kim J-E, Hwang J-J, et al. Artificial intelligence in oral and maxillofacial radiology: what is currently possible? Dentomaxillofacial Radiol. 2020;50(3):20200375. doi:10.1259/dmfr.20200375
  3. Applications of Artificial Intelligence in Musculoskeletal Imaging: From the Request to the Report - Natalia Gorelik, Soterios Gyftopoulos, 2021. Accessed April 14, 2021. https://journals.sagepub.com/doi/abs/10.1177/0846537120947148
  4. Liao Y, Vakanski A, Xian M. A Deep Learning Framework for Assessing Physical Rehabilitation Exercises. IEEE Trans Neural Syst Rehabil Eng. 2020;28(2):468-477. doi:10.1109/TNSRE.2020.2966249
  5. JMIR Research Protocols - Adherence Tracking With Smart Watches for Shoulder Physiotherapy in Rotator Cuff Pathology: Protocol for a Longitudinal Cohort Study. Accessed April 14, 2021. https://www.researchprotocols.org/2020/7/e17841/
  6. Heo M-S, Kim J-E, Hwang J-J, et al. Artificial intelligence in oral and maxillofacial radiology: what is currently possible? Dentomaxillofacial Radiol. 2021;50(3):20200375. doi:10.1259/dmfr.20200375
  7. Bengio Y, Courville A, Vincent P. Representation Learning: A Review and New Perspectives. IEEE Trans Pattern Anal Mach Intell. 2013;35(8):1798-1828. doi:10.1109/TPAMI.2013.50
  8. Ito M, Iyatomi H. Web application firewall using character-level convolutional neural network. In: 2018 IEEE 14th International Colloquium on Signal Processing Its Applications (CSPA). ; 2018:103-106. doi:10.1109/CSPA.2018.8368694
  9. A Web Application Supported Learning Environment for Enhancing Classroom Teaching and Learning Experiences - ScienceDirect. Accessed April 14, 2021. https://www.sciencedirect.com/science/article/pii/S1877042812049786
  10. Lee C-J, Choi S-W. A New Normal of Lifelong Education According to the Artificial Intelligence and EduTech Industry Trends and the Spread of the Untact Trend. In: Kim H, Lee R, eds. Software Engineering in IoT, Big Data, Cloud and Mobile Computing. Studies in Computational Intelligence. Springer International Publishing; 2021:191-205. doi:10.1007/978-3-030-64773-5_16
  11. Artificial intelligence for education: Knowledge and its assessment in AI-enabled learning ecologies: Educational Philosophy and Theory: Vol 0, No 0. Accessed April 14, 2021. https://www.tandfonline.com/doi/abs/10.1080/00131857.2020.1728732
  12. How artificial intelligence (AI) could have helped our medical education during the COVID-19 pandemic - A student's perspective - PubMed. Accessed April 14, 2021. https://pubmed.ncbi.nlm.nih.gov/32755431/
  13. Serviciu pentru containerizarea mediilor de dezvoltare in cloud. Accessed April 14, 2021. http://www.repository.utm.md/handle/5014/13285
  14. goormIDE - A Powerful Cloud IDE Service. goormIDE. Accessed April 14, 2021. https://ide.goorm.io/