NEURAL NETWORK-ASSISTED DETECTION OF PRIMARY TUBERCULOSIS FOR IMPROVED DIAGNOSIS

Abstract

The aim of the study is to develop a predictive model for Tuberculosis (Tb), a serious chronic infectious disease. Tb (caused by a bacterial Mycobacterium tuberculosis) causes enormous global health issues, and early detection is critical for initiating treatment on time. Leveraging the power of Convolutional Neural Networks (CNN), a deep learning model, a robust system was constructed to predict Tb status based on chest X-ray images. Traditional diagnostic methods often involve time-consuming laboratory tests, necessitating the need for more efficient and accessible approaches. The proposed CNN model was trained using a large dataset of annotated chest X-ray images, enabling it to learn relevant features indicative of Tb infection. Extensive evaluation and validation confirmed the model's high accuracy and reliability in diagnosing Tb, thereby providing a valuable tool for healthcare professionals. By revolutionizing medical image analysis, these models have the power to transform healthcare delivery, leading to better patient outcomes, optimized resource allocation, and significant advancements in the field. Continued research, collaboration, and implementation are crucial to fully harness the future potential of deep learning models in clinical practice.