<![CDATA[Malaria is a life-threatening disease caused by Plasmodium parasites and transmitted through the bite of infected mosquitoes. Accurate and early detection is essential for effective treatment and control. In this study, we propose an enhanced deep learning approach using a Convolutional Neural Network (CNN) optimized with a Convolutional Block Attention Module (CBAM) to classify red blood cell images as malaria-infected or uninfected. The CBAM mechanism enables the model to focus more effectively on the most informative spatial and channel features, thereby improving its ability to detect subtle patterns in microscopic blood smear images. We compare the performance of the CBAM-optimized CNN against a baseline CNN using accuracy, precision, recall, and F1-score metrics. Experimental results show that integrating CBAM significantly improves classification performance, achieving higher detection accuracy and greater robustness against visual noise and variations. This study highlights the effectiveness of attention-based optimization in medical image classification tasks, particularly in resource-limited settings where reliable and automated diagnosis is highly needed.]]>
Copyrights © 2025
