APPLICATION OF IMAGE PROCESSING TECHNIQUE TO STUDY MALARIA PARASITES IN BLOOD

Abstract

Malaria is a mosquito borne infectious disease of humans and other animals caused by protozoan parasitic of the plasmodium. The most serious and virulent forms of the disease are caused by P. falciparum which contributes to the majority of deaths associated with the disease. Commonly, the disease is transmitted via a bite from an infected female anopheles mosquito, which introduces the organisms from its saliva into a person's circulatory systems. The malaria diagnosis is normally accomplished by visual microscopy which is time consuming and offers low accuracy because of the operator’s tiredness and lack of profession in job. To overcome of this liability, we designed an automatic system. The automatic diagnostic process reduces the diagnostic time and also, it can be worked as a second opinion for pathologists and may be useful in malaria screening. The aim of this research is to count the red blood cells that are infected by malarial parasites using digital image processing implementation. As there were the possibilities of other artifacts in the smear blood samples, only RBCs need to be segmented. The artifacts other than RBCs were removed from the image. The resulting image was consisted of only extracted RBCs and used to estimate parasitisimia. Parasitemia was determined as the ratio of the number of infected erythrocytes to the total number of erythrocytes in an image. In this research work, a total of 15 patients’ clinical data plasmodium parasite infected blood smears were considered and investigated by using image processing. Based on the developed morphological based code, it was found that, the parasite infected malaria disease can be detected with an accuracy 99.84% sensitivity 97.73% specivity 99.92% based on selected dependent variables.