Abstract:
Tuberculosis and pneumonia are debilitating respiratory diseases that pose significant health challenges
globally. Timely and accurate diagnosis of these diseases is crucial for effective treatment and control.
This has led to the development of innovative technologies for the detection and diagnosis of tuberculosis
and pneumonia, including the use of deep learning models and computer-aided diagnosis systems. In this
study, we have curated a comprehensive dataset containing chest X-ray images with four distinct classes:
normal, tuberculosis-infected, pneumonia-infected, and co-infected cases. We have implemented deep
learning models, including InceptionV3 classify these images. Our results show that InceptionV3 achieved
the highest accuracy of 98.76 percent in disease classification. This system holds the potential to assist
healthcare professionals in the early and accurate diagnosis of tuberculosis and pneumonia, ultimately
improving patient outcomes and reducing the burden on healthcare systems.
