We find deep learning as a subset of machine learning that runs an incurable disease diagnostic system with multi-neural architectures. In recent age a neural model has capabilities to detect more accurately and quickly resulting classified labels. It helps medical practitioners to develop and explain effective detection systems. Tuberculosis is one of the biggest threats that has been remaining a contagious disease since its discovery, posing a significant risk to millions of lives. Many people yield to tuberculosis because of incomplete treatments or the lack of preventive measures. An effective pulmonary TB diagnostic system has remained a big challenge. As it is a contagious disease, it mainly affects the lungs and other vital organs of the human body. Through this paper, an enhanced detection model to classify tuberculosis and non-TB cases using clinical X-ray images has been proposed. The augmented histogram equalized X-rays were applied to top state-of-the-art classifiers, with ResNet50 and ResNet152 achieving the best results, showing accuracies of 99.20% and 99.10%, respectively.