Manuscript Number : CSEIT174442
Computer Aided Analysis of Chest X-Ray Images for Early Detection of Cardiomegaly using Euler Numbers
Authors(2) :-J Ebenezer, A C S Rao Cardiomegaly is an unusual cardiac condition in which the human heart grows larger in size and becomes bigger than it usually is. Cardiomegaly can be detected early by computing Cardiothoracic Ratio(CTR) from chest X-ray images (CXR).As it is difficult for medical experts to examine CXR manually, a Computer-Aided Diagnosis (CAD) system is required to precisely calculate the Cardiothoracic ratio and accurately predict the onset of Cardiomegaly. In this paper, we use euler number based thresholding method for lung region segmentation from CXR images. The resultant binarized image is used for calculating Cardiothoracic Ratio using a computational algorithm. The proposed method is experimented on two datasets: JRST and India. JRST contains 247 chest X-rays and India set contains 100 chest X-rays. An overall accuracy of 96.25% and the overall (lung segmentation time + CTR computation time) average computation of 0.8215 seconds was acheived. The proposed method is compared with existing methods and it gives high accuracy and high performance.
J Ebenezer Chest X ray images; Computer Aided Analysis;Euler number; Cardiomegaly; Cardiothoracic Ratio Computation. Publication Details Published in : Volume 2 | Issue 7 | September 2017 Article Preview
Department of Computer Science, Vignan's Foundation for Science Technology and Research, Guntur, Andhra Pradesh, India
A C S Rao
Department of Computer Science, IIT(ISM) Dhanbad, Jharkhand, India
Date of Publication : 2017-09-30
License: This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 338-346
Manuscript Number : CSEIT174442
Publisher : Technoscience Academy