Tuberculosis is one of the major health concerns which an infectious disease is caused by the bacterium Mycobacterium tuberculosis (MTB). Tuberculosis generally affects the lungs, but can also affect other parts of the body. Most infections do not have symptoms, known as latent tuberculosis. In 2014, there were 9.6 million cases of active TB which resulted in 1.5 million deaths. More than 95% of deaths occurred in developing countries. Automatic systems to detect TB on chest radiographs (CXRs) can improve the efficiency of diagnostic algorithms for pulmonary TB.A computer aided detection (CAD) system was developed which combines several sub scores of supervised subsystems detecting textural, shape, and focal abnormalities into one TB score. A typical thin curvilinear shape of fissure profiles inside 2D cross-sections, the dos filter is presented by first defining nonlinear derivatives along a triple stick kernel in varying directions. To accommodate pathological abnormality and orientation deviation, a max-min cascading and multiple plane integration scheme is adopted to form a shape-tuned likelihood for 3D surface patches discrimination. Our main contribution is to isolate the fissure patches from adhering clutters by introducing a branchpoint removal algorithm, and a multi-threshold merging framework is employed to compensate for local intensity inhomogeneity