Pulmonary Tuberculosis Detection using Digitally Photographed Chest X-RAY Images

Abstract

Many countries have been facing problems concerning Pulmonary Tuberculosis. These illnesses have a great toll on human lives whether young or old. Medicines and health awareness have driven Health and Medical institutions to embrace the advancement in the medical field. It aimed to maximize the ability of Medical science to combat this illness. With medical and computer science combined led Artificial Intelligence and Neural networks to produce a drastic product in the early detection of Pulmonary Tuberculosis. Moreover, Image processing of captured photographs of Chest X-ray results was processed using a technique. The Contrast Low Adaptive Histogram Equalization and Grab Cut was used to concentrate on the region of interest for lungs. The Radial basis function was utilized as the network model and part of the program is to use Scikit learn in determining the confusion matrix, precision, recall, f1-score, and support. The concept was the first step to provide medical “diagnosis”, especially in low and hard-up far-flung communities that were rarely visited by a specialist for Chest X-ray interpretation.