Computerized radiogrammetry of third metacarpal using watershed and active appearance model

Abstract

Osteoporosis is a bone disorder, causing loss of bone mass and increased risk of fragility fracture. Osteoporosis can be diagnosed at a low cost using computerized metacarpal radiogrammetry of the third metacarpal bone of hand X-ray images. The most widely used methods for segmentation of hand bones are deformable models such as Active Shape Model (ASM), Active Appearance Model (AAM), etc. that make use of prior information of the shape and appearance of the object. However, due to the presence of other metacarpal bones having similar shape and size in its proximity, segmentation of third metacarpal bone in isolation becomes challenging and the deformable methods could fail. In this paper, we propose a method to automatically locate and segment the third metacarpal bone using marker-controlled watershed segmentation. Radio-grammetric measurements are determined automatically from the shaft of the third metacarpal bone and can be used to derive bone indices for the detection of bone loss due to osteoporosis. The measurements obtained from the proposed method and AAM are compared with ground truth. The results obtained show that the proposed approach is an efficient method for automated radiogrammetry of third metacarpal bone that can be used as a low cost tool for the early diagnosis of osteoporosis. � 2018 IEEE.