Automated detection of plasmodium falciparum from Giemsa-stained thin blood films

This paper investigates automated detection of malaria parasites in images of Giemsa-stained thin blood films. We aim to determine parasitemia based on automatic segmentation, feature extraction and classification methods. Segmentation relies on adaptive thresholding and watershed methods. Statistical features are then computed for each cell and classified using SVM binary classifier. Accuracy of classification is validated based on the leave-one-out cross-validation technique. This processing pipeline is applied on total 15 images of Giemsa-stained thin blood films and yields 92.71% sensitivity, 97.35% specificity and 97.17% accuracy.