Content Based Image Retrieval Approaches for Detection of Malarial Parasite in Blood Images

Malaria is a serious global health problem, and rapid, accurate diagnosis is required to control thedisease. An image processing algorithm to automate the diagnosis of malaria in blood images isproposed in this paper. The image classification system is designed to positively identify malariaparasites present in thin blood smears, and differentiate the species of malaria. Images areacquired using a charge-coupled device camera connected to a light microscope. Morphologicaland novel threshold selection techniques are used to identify erythrocytes (red blood cells) andpossible parasites present on microscopic slides. Image features based on colour, texture andthe geometry of the cells and parasites are generated, as well as features that make use of apriori knowledge of the classification problem and mimic features used by human technicians. Atwo-stage tree classifier using back propogation feed forward neural networks distinguishesbetween true and false positives, and then diagnoses the species (Plasmodium Falciparum, P.Vivax, P. Ovale or P. Malariae) of the infection. Malaria samples obtained from the variousbiomedical research facilities are used for training and testing of the system. Infected erythrocytesare positively identified with two measurable parameters namely sensitivity and a positivepredictive value (PPV), which makes the method highly sensitive at diagnosing a completesample, provided many views are analyzed.