Comparison of Architectures of Deep Learning-Based Segmentation in Lower Extremity Human Thermal Imaging

Segmentation is the process of distinguishing the desired area in an image from the background and other objects. With the development of deep learning methods, the importance of segmentation has increased, and it is now used in many fields such as medicine, industry, and autonomous systems. In this study, binary segmentation was performed on a dataset prepared with human lower extremity thermal images, and the detection of specified regions was achieved. Five different deep learning-based models were specifically designed for the problem and trained using the cross-validation method. The obtained results were recorded, and their performances were compared. Among the created models, the MCRNet model achieved the best result on the test data with a 97% Dice Similarity Coefficient, 94% Jaccard Index, and 0.12 BCE Loss value. This study was conducted to improve the analysis of athlete injuries on thermal images and to compare models that achieve accurate and efficient segmentation results.