Remote Pre-Diagnosis of Pes Planus and Pes Cavus Using Arch Index

Abstract

According to the literature, people with foot deformities report poor quality of life and nearly one-third of the population has some type of foot deformity. Of all the deformities, Pes Planus, caused by the loss of the medial longitudinal arch of the foot, and pes cavus, caused by having an abnormally high plantar longitudinal arch, are the ones that negatively influence the productivity of society most. In the light of the above, this study proposes a novel mobile pre-diagnosis system for pes planus and pes cavus that is utilizing conventional deformity identification methods accepted in the literature through a mobile phone app by harnesing image processing and deep neural networks. As part of the study, a prototype is implemented and tested using 34 participants - 22 (64.71%) males and 12 (35.29%) females - with an average age of 24.06. In order to benchmark our prototype, an orthopedic specialist was asked to identify the key decision making points, which was then used to calculate the deformity type, on a set of foot images collected from participants. Then the same images were fed to the prototype with the objective of identifying the key points and calculating the deformity type via the help of image processing and deep learning algorithms. The comparison of the results showed that specialist’s and prototypes findings were in 91.80% match, which indicated an overall success