APPLICATION OF THE YOLO MODEL FOR AUTOMATIC DETECTION OF KEY POINTS ON IMAGES OF THE REAR PART OF THE FOOT FOR DIAGNOSING FLAT-VALGUS DEFORMITY OF THE FOOT

Zhilin Valentin Valerievich

Flat-valgus deformity of the foot (FVDF) is a common orthopedic disorder requiring accurate diagnosis for effective treatment. This study investigates the application of the YOLO model for automatic detection of key points on images of the rear part of the foot related to FVDF. A dataset including images with various degrees of foot deformation was collected for this purpose. The YOLO model was trained on these data, and its accuracy was evaluated on a test set. The results showed that the YOLO model has the potential to automate the diagnosis of FVDF, and increasing the volume of training data can improve its performance. These findings highlight the prospects of using the YOLO model in clinical practice to enhance the diagnosis and treatment of FVDF.

Keywords:flat-valgus deformity of the foot, YOLO, diagnosis