Lung disease pattern detection in X-ray images plays a crucial role in early diagnosis and treatment planning. This study introduces a novel approach that integrates the African Vulture Optimization Algorithm (AVOA) with Convolutional Neural Networks (CNN) to enhance detection accuracy and efficiency. Existing methods often suffer from high false detection rates, poor generalization, and inadequate feature extraction, especially in complex or overlapping lung pathologies. To overcome these challenges, the proposed framework employs CNN for deep feature extraction, while AVOA optimizes network parameters and feature selection, ensuring robust learning and reduced overfitting. The hybrid model not only improves feature representation but also accelerates convergence during training. The proposed method is applied to public lung X-ray datasets to identify patterns indicative of diseases such as tuberculosis, pneumonia, and COVID-19. Experimental results show that the CNN-AVOA model outperforms conventional deep learning models, achieving a classification accuracy of 96.8%, with superior precision and recall rates. This approach demonstrates significant potential in automated medical diagnostics, reducing human error and improving patient outcomes.

Keywords :

Lung Disease Detection, X-ray Imaging, African Vulture Optimization Algorithm, Convolutional Neural Network, Deep Learning, Medical Image Analysis