Computer Aided Automatic Detection of Tuberculosis in Chest Radiographs

Author(s):

N.Noorul mubeena , Ultra College Of Engineering and Technology for Women, Madurai, Tamil Nadu, India; S.Anusha, Ultra College Of Engineering and Technology for Women, Madurai, Tamil Nadu, India; G.Chitra, Ultra College Of Engineering and Technology for Women, Madurai, Tamil Nadu, India; C.Sujatha, Ultra College Of Engineering and Technology for Women, Madurai, Tamil Nadu, India

Keywords:

Subsystem, subscore, shape, texture, and focul analysis Chest radiographs, computer-aided diagnosis

Abstract:

Tuberculosis (TB) is a common disease with high mortality and morbidity rates worldwide. Automatic systems to detect TB on chest radiographs (CXRs) can improve the efficiency of diagnostic algorithms for pulmonary TB.The noise reduction performed in chest X-ray image to detect and remove the impulse noises in the image. The features are extracted from the chest image and trained and classified using SVM (Support vector machine) classifier.The performance of the proposed system is analyzed in terms of sensitivity, specificity and accuracy. Computer aided detection (CAD) system was developed which combines several subscores of supervised subsystems detecting textural, shape, and focal abnormalities into one TB score. A general framework was developed to combine an arbitrary number of sub- scores: subscores were normalized, collected in a feature vector and then combined using a supervised classifier into one combined score. TB score allows for a necessary adaptation of the CAD system to different settings or different operational requirements.

Other Details:

Manuscript Id	:	IJSTEV2I10032
Published in	:	Volume : 2, Issue : 10
Publication Date	:	01/05/2016
Page(s)	:	106-109

Download Article