Browsing by Author "Bayrak, Ahmet"

Now showing 1 - 4 of 4

Monitoring the Reactions of Athletes With History of Rectus Femoris Proximal Tear Healed With Different Methods To Training Load With Thermography
(2023) Bayrak, Ahmet; Ergene, Mehmet Celalettin; Ceylan, Murat
Although rectus femoris (RF) injuries are rare, it is an important muscle that should be considered because of its contribution to actions such as shooting and fast running in football. In the literature, there is no consensus on which conservative or surgical methods should be preferred in RF total rupture. Although MRI is the gold standard method in the detection of injury, there is a controversy in the literature for post-injury imaging and follow-up. In addition, there is a lack of diagnostic imaging methods in the literature on how training load affects athletes. In current study, the effect of training load on athletes is evaluated by thermography after treatment of the RF muscle with different methods. This study is worthy of being a case report in terms of providing evidence on how the training load affects the sports lives of athletes who return to sports after surgery or conservative treatment.
Citation - WoS: 2
Citation - Scopus: 2
A New Deep Learning Based End-To Pipeline for Hamstring Injury Detection in Thermal Images of Professional Football Player
(Taylor & Francis Ltd, 2025) Ergene, Mehmet Celalettin; Bayrak, Ahmet; Ceylan, Murat
Football clubs use various methods such as thermal imaging which is a non-invasive and faster method to detect injuries and increase the success rate of the football club by reducing the injury rate. Studies have proven that with thermal imaging it is possible to detect inflammation caused by an injury. Therefore, it is possible to detect potential injury with infrared thermography. One of the biggest handicaps of injury detection with thermal imaging is that it is open to subjective interpretation, there are many points that can be missed, and it takes time to analyse them one by one. In order to avoid this problem, to increase the success of injury detection, a deep learning supported pipeline has been designed in this study to detect injuries from thermal images. In this pipeline, the hamstring muscle region from the football player thermal images was segmented using U-Net architecture. After that in order to detect injuries, segmented muscle region is classified by using Densenet, Resnet, VGG, Efficientnet architectures variations and feature pyramid added at the end of these architectures. Among the architectures used for classification, the EfficientnetB0 and EfficientnetB1+feature pyramid architectures are the most successful, with accuracies of 83.9% and 81%, respectively.
Tracking the Injury Recovery of Professional Football Players With Infrared Thermography: Preliminary Study
(2020) Ergene, Mehmet Celalettin; Bayrak, Ahmet; Ceylan, Murat
Infrared thermography is a non-invasive method of translating and viewing the radiating heat from the target surface collected by the infrared sensor into temperature as a digital image. Infrared thermography contains very useful data, especially for medical reasons. However, it has been accepted just recently. Although its usage is still questioned in sports medicine, recent studies claimed that infrared thermography can be used to examine muscle problems, injuries, and joint problems, etc. Sports medicine, physiotherapists, and medical imaging have vital importance for football teams and its’ success. During a season football teams lose a lot of matches because of the high rate of injury. That is why preventing an injury has more importance for a football team than healing an existing injury. In consequence physiotherapists use many methods to prevent football players from being injured and monitorise the injury such as creatine kinase tests, muscle strength measurements, MRI, etc. However, these methods are either not enough successful or expensive. In our study, we have developed an image processing software to examine lower extremities muscle problems of football players when they occur and after they rested a day. With this software, we aim to help physiotherapists to regulate rehabilitation plan and decide when to end the rehabilitation. Thanks to this, physiotherapists can decide to rest the football players or start treatment so that they will not get injured unnecessarily and will have a lower risk of injury. Thorough this the success of the football teams will increase because the football players will not miss matches because of the extreme training or overlooked injuries. In our proposed method, with infrared thermography, 3 football players with documented injuries were observed. They have studied again after the football players rested for 1 day and the findings were analyzed. For that the thermographic color palette’s RGB values are calculated in such a way that the upper and lower color values are discovered. In the next step, a binary mask is created, and this mask is blended with the grayscale original image, and the areas with muscle problems are displayed colored so that the physiotherapists can detect and examine problems easier. In the results part, it is shown that the areas are detected better than the human eye. It is concluded that with the help of the image processing algorithm muscle problems are detected successfully and the healing process after the resting is observed.
The Use of Prototypical and Siamese Networks in the Determination of Lower Extremity Injuries in Professional Football Players with Thermographic Data
(Taylor & Francis Ltd, 2025) Ergene, Mehmet Celalettin; Bayrak, Ahmet; Ceylan, Murat
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.