期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2016
卷号：4
期号：4
页码：5374
DOI：10.15680/IJIRCCE.2016.0404301
出版社：S&S Publications
摘要：To decrease the mortality and to save the lives of patients suffering from pulmonary disease a National Library of Medicine (NLM) is developing a digital chest x-ray (CXR) screening system for deployment in resource constrained communities. An important step taken in the analysis of digital CXRs is the automatic detection of the lung regionsin chest X-ray. In this paper, we present a graph cut based robust lung segmentation method which will detects the lungs with high accuracy. Thismethod consists different stages such as(i) average lung shape model calculation, and (ii) lung boundary detection based on graph cut. Preliminary results on public chest x-rays demonstratethe robustness of the method. The National Library of Medicine (NLM) is now developing digitalchest X-ray (CXR) detection &screening system for deployment in resource constrained communities and developing countries worldwide and with a focus onearly detection of pulmonary diseases. A critical component in the computer-aided diagnosis of digital CXRs is the automatic detection of the lung regions. In this paper, we present a nonrigid registration-driven robust lung segmentation method usingwhich animage retrieval-based patient specific adaptive lung models that detects lung boundaries, surpassing state-of-the-art performance. The method consists of three main stages: 1) a content-based image retrieval approach (CBIR) using a partial Radon transform and Bhattacharyya shape similarity measure,2) creating the initial patient-specific anatomical model of lung shape using SIFT-flow for deformable registration of training masksto the patient CXRand 3) Extracting refined lung boundaries using a graph cuts optimization method 4) SVMClassifier
