Deep Learning-Based Malaria Detection: A Comparative Study of CNN Architectures

Malaria continues to pose a significant global health challenge, necessitating accurate and timely diagnostic methods to enhance patient outcomes.Traditional microscopic techniques, though effective, are labor-intensive and reliant on expert interpretation.This study investigates the potential of deep learning-based approaches for automated malaria detection, evaluating the performance of MobileNetV2, NASNetMobile, Xception, and InceptionResNetV2.Comparative analysis reveals that Xception outperformed the other models, offering an optimal balance of accuracy and efficiency.This study provides a robust foundation for selecting the most suitable deep learning models for malaria diagnosis, particularly in resource-limited settings.