Development of a Mobile-Based Convolution Neural Network Framework for Rapid Malaria Detection from Blood Smears

Abstract

Malaria, a vector-borne parasitic disease caused by Plasmodium parasites, continues to pose a substantial threat to global public health. Despite considerable progress in its control and treatment, malaria remains a significant cause of morbidity and mortality, particularly in resource-limited regions. The ability to diagnose malaria infections accurately and swiftly is paramount for effective disease management. Traditional methods of malaria diagnosis, relying on microscopic examination of blood smears, have proven to be accurate but are often hindered by limitations in infrastructure and expertise, particularly in remote and underserved areas. This research focuses on the development of a mobile-based Convolution Neural Network (CNN) framework for rapid malaria parasite detection from blood smear images using Android mobile phones. Blood smear images provide a reasonable and clinically relevant representation of malaria disease which makes it a preferred choice for malaria detection from mobile phones. By leveraging smartphone technology and state-of-the-art deep learning algorithms, this pioneering endeavour aims to normalize malaria diagnostics, providing healthcare workers with a powerful tool for early detection and treatment, irrespective of their location or access to advanced laboratory facilities. The dataset for infected and non-infected parasites was acquired online from Kaggle. The dataset was preprocessed and partitioned into training, testing, and validation sets. The developed model was converted to tflite and was used for the mobile application. A validation accuracy of 94.88% was obtained from the validation set while an accuracy of 95.81% was obtained from the testing set.