CAD-based automatic detection of tuberculosis in chest radiography using hybrid method

Automated processes are essential in medical imaging to identify anomalies. This study uses chest radiography (CXR) for CAD analysis, which is indicated for about 90% of TB patients. Even when it is cost effective, certain reasons are difficult to pinpoint. Using a deformable active contour model, the first phase involves inputting CXR lung field segmentation and identifying highlights within the segmented lung region, along with TB detection calculations. The algorithm's segmentation output is evaluated using two parameters. Moving on to the second phase, features are extracted and optimised using a hybrid multiresolution approach. Various transform coefficients were statistically analysed to obtain a feature collection. The final stage is to classify lung anomalies using MSVM and KNN for three publicly available datasets. The classification performance of the JSRT, Montgomery, and Shenzhen datasets is assessed. The recommended method identifies pulmonary TB 96.5% of the time.