Early Detection of Tuberculosis Using Machine Learning Techniques on Chest X-Ray Images

Tuberculosis (TB) continues to be one of the leading infectious diseases affecting millions of people globally, particularly in developing countries. Timely diagnosis plays a critical role in controlling transmission and reducing mortality. Chest X-ray imaging is widely used for pulmonary tuberculosis screening; however, manual interpretation depends heavily on expert radiologists and may lead to delays or subjective errors. In this paper, an automated tuberculosis detection system based on machine learning techniques is presented. The proposed model combines Convolutional Neural Networks (CNN) for deep feature extraction with Support Vector Machine (SVM) for classification. Preprocessing techniques such as resizing, normalization, and augmentation are applied to enhance dataset quality and improve generalization. The hybrid approach allows effective extraction of visual patterns associated with TB infection and produces reliable classification results. Experimental findings demonstrate that the system achieves high accuracy while maintaining computational efficiency. The proposed solution can serve as a supportive diagnostic tool in resource-limited healthcare environments.