Developments in Computer Aided Diagnosis Used for Tuberculosis Detection Using Chest Radiography: a Survey

One of the major health problems of global concern is Tuberculosis (TB). According to global report of the WHO, approximately 1.3 million people, out of the 8.6 million reported, died of TB in 2012. Most of the TB deaths can be prevented if it is detected at an early stage. Hindrance to this is improper diagnosis at initial stages. Chest X ray (CXR) image is the primary medical diagnosis used for identifying the lung diseases at the first stage. Interpreting the information from CXR depends upon the experience of the physician and the possibility of over and under diagnosis is very high. To identify the disease accurately a proper classification tool along with computer aided diagnosis should be used. Neural network can be used as a classifier tool for the same. Advancement in VLSI technology reduces the computational complexity of Artificial Neural Networks (ANN). Applications of neural networks to medical images (X-ray images of TB and lung cancer) during adolescent stages have resulted in remarkable improvements in diagnosis. This paper describes the fundamentals of radiology of lungs (analysis of CXR), image processing with the aid of ANN and recent developments in this area using computer aided diagnosis (CAD). We have analysed CXR images of several patients and found that an accurate classifier is required for proper diagnosis of TB from these images.