Detection of Tuberculosis from Chest X-Ray Images Based on Modified Inception Deep Neural Network Model

Lung tuberculosis is a bacterial infection that causes more deaths in the world than any other infectious disease. Two billion people are infected with tuberculosis all around the world. It is caused by bacteria known as Mycobacterium tuberculosis or Tubercle bacillus. This research work strives to identify if any patient is affected by tuberculosis or not by analyzing their chest X-ray image. Due to this a lot of time and money of the patient can be saved. Once we receive a X-ray image as an input, we first pre-process the image and segment the lungs portion out of it. Then we apply the pre-processed image to our Modified Inception deep neural network model which determines whether the patient has tuberculosis or not with a validation accuracy of 91%.