DefinePK

Abstract

This paper is an attempt to investigate the possibility of automating assessment of joint damage in hand radiographs. The goal is to design a segmentation algorithm to obtain the area which is an object, the joint space. Image segmentation is the process of partitioning a digital image into several segments. For this study has collected 46 hand radiographic images. Treatment of image preprocessing is done using adaptive threshold and the concept of morphological gradient, then performed segmentation with watershed transformation. Segmentation results were analyzed based on the level of accuracy, sensitivity and specificity using the ROC. Results of the segmentation process is preceded by preprocessing produce images that are not over-segmentation and produce images that are more evident than the value of accuracy of 95.75%, 70.51% sensitivity and specificity of 96.99% in a high percentage.