期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
卷号：5
期号：7
页码：13824
DOI：10.15680/IJIRSET.2016.0507208
出版社：S&S Publications
摘要：Tuberculosis is a major health problem in many regions of the world. This infection in weak immuneHIV/AIDS patients and multi-drug-resistant bacterial strains has severed the problem. Also diagnosing tuberculosisstill is a challenge. When left undiagnosed and thus untreated, mortality rates of patients with tuberculosis are high.Standard diagnostics still rely on old methods of the last century. They are slow and often unreliable. In an effort toreduce the burden of the disease, this project presents our automated approach for detecting tuberculosis using chestradiographs. In this project system first extracts the lung region using segmentation method then features are extractedusing filters and then the selection of features is done. Selected features are given as input to the classifier, which givesoutput as TB positive or negative.
关键词：Computer-aided detection and diagnosis; lung;pattern recognition and classification; segmentation;tuberculosis(TB); X-ray imaging
