Computer Vision and Explainable Approaches for Chest Tuberculosis Screenings

This research delves into leveraging artificial intelligence for tuberculosis (TB) screening via chest radiography, addressing a persistent global health threat that impacts millions each year. The study's primary goal is to innovate remote diagnostic techniques that apply computer vision to facilitate early disease detection. This investigation critically evaluates convolutional neural networks, particularly ResNet50 and EfficientNet-B7, for their effectiveness in localizing and identifying pulmonary lesions. The findings reveal that ResNet50 excels in delineating lung structures, while EfficientNet-B7 outperforms in pathology identification. Both models, however, demonstrate pronounced sensitivity to image quality, often encountering difficulty in differentiating pathologies in complex anatomical regions. Achieving an impressive accuracy of approximately 99.6% on publicly accessible datasets, the models experienced a performance reduction to 79.3% on private clinical datasets, underscoring the variability in model efficacy across different data sources. The study underscores the critical role of explainable AI (XAI) methods, including Grad-CAM, Captum, and SHAP, in enhancing interpretability and aiding clinicians in comprehending the decision-making pathways of AI models. In sum, this research highlights AI's potential in advancing TB screening while addressing inherent challenges related to image fidelity and model generalizability.