Tuberculosis Diagnosis Using CNN: A Deep Learning Approach

Still a major worldwide health concern, tuberculosis (TB) seriously affects lung health and offers great difficulties for disease control. Effective treatment and prevention depend on early identification of TB, hence lowering transmission rates and enhancing patient outcomes. Using chest X-ray pictures, this work advances the TB diagnosis by use of a Convolutional Neural Network (CNN). Comprising 4200 pictures total, 3500 from normal cases and 700 from TB-positive patients-divisible into 2940 images for training and 1260 for validation. The CNN model proposed in this work has great potential to significantly increase diagnostic accuracy with an astonishing 98% accuracy. By including advanced picture analysis techniques, this work fits with Sustainable Development Goals (SDGs) related to outstanding health and well-being, so reducing inequality and so promoting new ideas for worldwide health challenges. These findings demonstrate how well CNN s diagnose early tuberculosis, which is essential for earlier intervention and management, and ultimately contributes to the development of better communities and a reduction in the disease load.