Automated quantification and classification of malaria parasites in thin blood smears

Malaria is a life threatening disease caused by mosquitoes of Anopheles genus that carries the plasmodium parasites. Malaria parasites identification is currently done based on patient's symptoms and parasitological testing. Both methods have several drawbacks such as limited access to microscopy experts especially in rural area practice, restricted diagnostic facilities and costly. This paper presents an approach to automatically quantify and classify erythrocytes infected by Plasmodium vivax at trophozoites stages in thin blood smears. Experimentation is conducted in MATLAB environment specifically using the Image Processing Toolbox. Tasks are divided into three main stages namely image preprocessing, segmentation and classification. In preprocessing, images were first converted to L*a*b* color space and then filtered to remove noises. For segmentation stage, a threshold for each image was calculated using Otsu method. Further, dilation and erosion were performed to completely remove background elements. In the classification stage, images were classified based on the number of infected red blood cell detected. Testing performed using 350 images yielded in 99.72% sensitivity, 99.94% specificity and 98.90% positive predictive value. Results proved that this proposed method is highly potential for automated malaria parasites identification system.