Tuberculosis (TB) is a rapidly spreading disease in the world. When left undiagnosed and thus untreated, mortality rates of patients with tuberculosis are high. Standard diagnostics still rely on methods developed in the last century. They are slow and often unreliable. So, Computer-aided diagnosis (CAD) has been popular and many researchers are interested in this research area different approaches have been proposed for TB detection and lung disease classification. In this paper, we present a method for detection of Tuberculosis in X-Ray images by using MATLAB which includes Pre Processing of Image, Segmentation, and Feature extraction from that image
TB infections need to be X-rayed and screened for active TB to ensure proper treatment of their infections. Taking Standard Chest X-rays (CXRs) is an inexpensive way to screen for the presence of TB. The purpose of the screening system is to identify everything that is or could be related to a patient having TB infections. But mass screening of a large population is time-consuming and tedious work, which requires considerable effort when done manually. For this reason, Computer-aided diagnostic systems (CAD) are used to detect Tuberculosis infections in chest X-rays. These systems have the potential to lessen the TB detection error risk and also depend on the radiologists. In this paper, we describe how we differentiate between normal and abnormal CXRs with manifestations of TB, using image processing techniques in MATLAB.
We used feature matching for extraction by clusters we find classifies the disease but we get that much accuracy
Does the image processing system consist of image pre-processing we reduce the noise in segmentation use a Discrete wavelet transform further we proceed? feature selection and extraction by that we can find the appropriate determination of image. The image needs to be reduced to certain determining characteristics and the analysis of these characteristics gives the relevant information After the feature extraction stage, the features have to be analyzed, classifiers like Bayesian classifiers and Support Vector Machines (SVM) are used to classify features and find the best values for them.