Recent Advances of Malaria Parasites Detection Systems Based on Mathematical Morphology

Abstract

Malaria is an epidemic health disease and a rapid, accurate diagnosis is necessary for proper intervention. Generally, pathologists visually examine blood stained slides for malaria diagnosis. Nevertheless, this kind of visual inspection is subjective, error-prone and time-consuming. In order to overcome the issues, numerous methods of automatic malaria diagnosis have been proposed so far. In particular, many researchers have used mathematical morphology as a powerful tool for computer aided malaria detection and classification. Mathematical morphology is not only a theory for the analysis of spatial structures, but also a very powerful technique widely used for image processing purposes and employed successfully in biomedical image analysis, especially in preprocessing and segmentation tasks. Microscopic image analysis and particularly malaria detection and classification can greatly benefit from the use of morphological operators. The aim of this paper is to present a review of recent mathematical morphology based methods for malaria parasite detection and identification in stained blood smears images.

Keywords: malaria; mathematical morphology; medical image analysis; red blood cells segmentation.

Figure 1

Different illumination conditions generate different images because of the absence of a standardized acquisition procedure. From left to right: acquisition of the same smear with four microscope’s brightness levels. Courtesy of CHUV, Lausanne.

Figure 2

Types of human malaria parasites: from left to right, P. falciparum in its schizont stage, P. vivax in two gametocytes specimens and one ring stage, P. ovale in its ring stage, P. malariae in its schizont stage. Courtesy of CHUV, Lausanne.

Figure 3

Examples of malaria parasite stages. First row, from left to right: P. falciparum ring, trophozoite, schizont, gametocyte; second row, from left to right: P. ovale ring, trophozoite, schizont, gametocyte; third row, from left to right: P. malariae ring, trophozoite, schizont, gametocyte; last row, from left to right: P. vivax ring, developed trophozoite, gametocyte. Courtesy of CHUV, Lausanne.

Figure 3

Examples of malaria parasite stages. First row, from left to right: P. falciparum ring, trophozoite, schizont, gametocyte; second row, from left to right: P. ovale ring, trophozoite, schizont, gametocyte; third row, from left to right: P. malariae ring, trophozoite, schizont, gametocyte; last row, from left to right: P. vivax ring, developed trophozoite, gametocyte. Courtesy of CHUV, Lausanne.

Figure 4

Malaria infected blood smears types. This image shows a comparison between staining colouration procedures and smears thickness. On top, left: thick smear with Giemsa stain [26], right: thin smear with Giemsa stain (courtesy of CHUV). On bottom, left: thick smear with Leishman stain [26], right: thin smear with Leishman stain (courtesy of CHUV). Dots in thick smears and rings in thin smears are P. Falciparum ring stages, while elongated erythrocytes (in images on the right) are affected from P. Falciparum in its trophozoite schizont stage. The difference between thick and thin smears is clearly evident by observing cells and parasite shapes. Thin smears typically offer a better shape representation, while thick ones contain smaller and less clear region shapes. Furthermore, Giemsa stain shows a better contrast between cells, parasites and background respect to Leishman stain.