Automated Analysis of Orthopaedic X-ray Images based on Digital-Geometric Techniques

Oishila Bandyopadhyay, Arindam Biswas, Bhargab B. Bhattacharya

Abstract

This thesis reports several methods for automated analysis and interpretation of bone X-ray images. Automatic segmentation of the bone part in a digital X-ray image is a challenging problem because of its low contrast against the surrounding flesh. In this thesis, we propose a fully automated X-ray image segmentation technique, which is based on a variant of entropy measure of the image. We have also analyzed the geometric information embedded in the long-bone contour image to identify the presence of abnormalities in the bone and perform fracture detection, fracture classification, and bone cancer diagnosis.

Keywords

X-ray image, Segmentation, Entropy, Digital Straight line segment, Concavity index, Runs-test, Support vector machine

Full Text:

PDF (143Kb)
Copyright (c) 2016 Oishila Bandyopadhyay, Arindam Biswas, Bhargab B. Bhattacharya