AUTOMATED MEASUREMENT OF FOOT DEFORMITIES: FLATFOOT, HIGH ARCH, CALCANEAL FRACTURE

Abstract

Radiographic measurements of foot deformities are used to determine, among other things, such conditions as flatfoot, high arch, or calcaneal fracture. Those measurements are achieved by estimating four angles. Manual assessment of those angles is time-consuming not to mention inevitable errors of such approximation. To the best of the authors knowledge, currently there is no research focusing on finding those four angles. In this paper an algorithm for automatic assessment of those angles, based on extremely randomized trees, is being proposed. Moreover this diagnostic assisting system was intended to be as generic as possible and could be applied, to some degree, to other similar problems. To demonstrate usefulness of this method, correlations of automated measurements with manual ones against correlations of manual measurements with manual ones are being compared. The significance level for manual-manual measurements comparison is less than 0.001 in case of all four angles. The significance level for automated-manual measurements comparison is also less than 0.001 in all cases. The results show that the search for the aforementioned angles can be automated. Even with the use of a generic algorithm a high degree of precision can be achieved, allowing for a more efficient diagnosis.