Morpho-Geometrical Feature Extraction of Thin Blood Smear Microphotograph for Malaria Plasmodia Species and Life Stage Determination

Malaria is a mosquito-borne disease that is prevalent in tropical areas. The diagnosis of Malaria infection is conducted manually by examining a thin blood smear, conducted by an expert microscopist. Unfortunately, the manual examination of the blood slide can be time consuming and is prone to human errors. Hence, this research aims to develop an algorithm that is based on a priori knowledge of the experts [1]. In this research, a morpho-geometrical approach of feature extraction coupled with Naive Bayes classification are proposed to measure the infected cell's size and shape from a microscopic image, to do species and life stage differentiation of P. falciparum, P. malariae, P. ovale, and P. vivax. This is done with the help of computational geometry, recursive bottleneck detection algorithm, and thresholding with Otsu's algorithm. The proposed algorithm was evaluated using real malaria cases and validated with manual microscopy analysis by a microscopist. The results showed a Positive Predictive Value (PPV) score of 77.14%, sensitivity score of 84.37%, and an F1 score of 80.60%, which shows that the proposed feature extraction method is reliable and faithful to the expert's a priori knowledge.