Abstract

With reports of 9.9 million people being infected with tuberculosis by WHO, there is a dire need to curtail the spread of tuberculosis. In spite of having faced many impediments like lack of certified radiologist and chest radiography hardware which are expensive, diagnosis of tuberculosis still remains undetected at early stage. Chest radiography is one of the earliest method of detection used and is an asset for diagnosis of TB especially in early stages of infection, in a resource limited setting as well as for differential diagnosis. In the times of artificial intelligence (AI), we can see many modern platforms for the development of Computer-aided detection (CAD) through machine learning (ML) and deep learning (DL) and there are data coming forth indicating their utilization to the maximum. These approaches involve in hospital settings for examining the diseases through clinical aetiology as well as X-ray images of the patient. Presently, efforts and strategies are being framed and articulated to bring more accuracy adopting the use of the AI and machine learning approaches for the diagnosis of TB. This survey provides an insight to the application and use of CAD for the diagnosis of TB.