The use of Prototypical and Siamese Networks in the determination of lower extremity injuries in professional football players with thermographic data
Source abstract
Abstract
Early diagnosis of lower extremity injuries in professional football players is crucial for maintaining performance and minimising long-term risks. Despite the growing use of thermographic imaging as a non-invasive tool for detecting musculoskeletal disorders, its integration into automated injury detection systems remains limited, particularly under data-scarce conditions. Given the need for effective early detection methods and the potential of thermography in sports medicine, this study investigates the applicability of deep learning models for classifying lower extremity injuries. Specifically, it evaluates the performance of Prototypical Network and Siamese Network models using thermographic data collected from professional athletes. The original dataset consists of images from 16 healthy and 9 injured individuals, and through augmentation it was expanded to 360 healthy and 180 injured samples. The Prototypical Network achieved an accuracy of 97.78%, while the Siamese Network attained 94%. These findings indicate that both models are capable of accurate injury detection, despite challenges posed by class imbalance and limited data availability. In conclusion, the study highlights the effectiveness of thermographic imaging combined with deep metric learning in identifying injuries in professional football players and suggests that reliable results can be achieved even in constrained data environments.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Infrared Thermography in Medicine · Thermography and Photoacoustic Techniques · Sports injuries and prevention
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Konya Technical University
Selcuk University
AIVISIONTECH Electronic Software Company
References (24)
Show source-provided references
1. 10.1136/bmjsem-2019-00067510.1136/bmjsem-2019-000675 ↗
2. Marsh JLT Specialty. Football injury index. 2019 [cited 2024 Feb 5]. Available from: https://www.readkong.com/page/football-injury-index-english-premier-league-2018-19-9752534
3. 10.1007/s12178-015-9260-410.1007/s12178-015-9260-4 ↗
4. 10.1007/978-3-319-47410-6_410.1007/978-3-319-47410-6_4 ↗
5. 10.31590/ejosat.80415110.31590/ejosat.804151 ↗
6. 10.3791/355110.3791/3551 ↗
7. 10.10520/EJC13812010.10520/EJC138120 ↗
8. 10.1016/j.infrared.2021.10375410.1016/j.infrared.2021.103754 ↗
9. 10.1109/JSEN.2022.319230010.1109/JSEN.2022.3192300 ↗
10. 10.1016/j.infrared.2023.10471810.1016/j.infrared.2023.104718 ↗
11. 10.1080/17686733.2022.215867810.1080/17686733.2022.2158678 ↗
12. 10.1080/17686733.2019.164644910.1080/17686733.2019.1646449 ↗
13. 10.1080/17686733.2021.201037910.1080/17686733.2021.2010379 ↗
14. 10.1080/17686733.2020.185539010.1080/17686733.2020.1855390 ↗
15. 10.1080/17686733.2024.236496410.1080/17686733.2024.2364964 ↗
16. Bromley J, Guyon I, LeCun Y, et al. Signature verification using a “Siamese” time delay neural network. Adv Neural Inf Process Syst. 1993:6.
17. 10.48550/arXiv.1703.0517510.48550/arXiv.1703.05175 ↗
18. 10.1002/j.1538-7305.1948.tb01338.x10.1002/j.1538-7305.1948.tb01338.x ↗
19. 10.1007/978-3-540-76917-010.1007/978-3-540-76917-0 ↗
20. 10.5405/jmbe.105410.5405/jmbe.1054 ↗
21. 10.3390/life1404047810.3390/life14040478 ↗
22. 10.3390/electronics1123398710.3390/electronics11233987 ↗
23. 10.1109/ACCESS.2021.305109510.1109/ACCESS.2021.3051095 ↗
24. 10.3390/technologies1006011910.3390/technologies10060119 ↗