Intelligent Malaria Detection and Species Classification: A Case of Rwanda

Malaria is a disease caused by the Plasmodium parasite, transmitted through the bites of infected Anopheles mosquitoes. It is one of the deadliest global health issues that remains a challenge for many sub-Saharan African countries. To address this difficulty, an efficient digital approach for parasite detection and identification of species and life cycles is required. This paper presents a comprehensive case study that primarily focuses on the comparison of feature extraction methods done on blood smear images within the context of Faster R-CNN backbone models used to detect and identify malaria parasite species. To extract features, the blood smear images utilized in this research have been collected from Rwanda, as the considered sub-Saharan case study. The study investigates the performance of various feature extraction techniques aiming a comparison, in the context of the developing world.