Advancing tuberculosis screening: A tailored CNN approach for accurate chest X-ray analysis and practical clinical integration

Abstract

Pulmonary tuberculosis (PTB) is a chronic infectious disease claiming approximately 1.5 million lives annually, emphasizing the need for timely diagnosis to improve survival and limit its spread. Chest X-rays are effective for identifying TB-related lung abnormalities, often before symptoms arise, making early detection crucial. Our project enhances PTB screening by leveraging a CNN model trained on 12,848 images from reliable open-access datasets. The system achieves 99.72 % accuracy in binary classification (normal vs. abnormal) and 99.61 % in distinguishing healthy, TB, and non-TB cases, outperforming existing solutions. This ML-driven tool enables swift, cost-effective, and precise PTB detection, ensuring targeted treatment and addressing medicolegal needs through reliable and accountable diagnostics.