An Early Detection of Tuberculosis Using Chest X-Ray with Computer-Aided Diagnosis through Machine Learning and Deep Learning Methodology

Tuberculosis (TB) remains a global health concern, necessitating the development of advanced diagnostic tools for early detection. This study proposes a robust framework for the early detection of TB utilizing Chest X-Ray (CXR) images with a focus on Computer-Aided Diagnosis (CAD) powered by machine learning techniques. The methodology involves a series of stages including image pre-processing, segmentation, feature extraction, classification, and performance evaluation. The first stage employs a median filter for image pre-processing to enhance the quality of CXR images by reducing noise and improving clarity. Subsequently, a Fuzzy C-means (FCM) algorithm is applied for segmentation, effectively isolating regions of interest associated with potential TB manifestations. The proposed framework combines image preprocessing, segmentation, feature extraction, and SVM-based classification to achieve early detection of TB using CXR images. The incorporation of advanced machine learning techniques enhances the accuracy and efficiency of TB diagnosis. The performance metrics provide a comprehensive evaluation of the proposed system, demonstrating its potential as a valuable tool for clinicians in the early detection of tuberculosis.