New imaging method may speed up diagnosis of malaria

A collaborative research group from the University of Helsinki (Helsinki, Finland) and the Karolinska Institute (Stockholm, Sweden), has developed a novel malaria diagnostic tool that is based upon computer vision screening and visualization of Plasmodium falciparum candidate areas in digitized blood smears.

In this newly developed approach, Giemsa-stained thin blood films with P. falciparum ring-stage trophozoites and uninfected controls are digitally scanned. Parasite candidate regions are then identified based on color and object size, followed by the extraction of image features, which are then used as input to a support vector machine classifier. The final diagnosis is conducted by a health-care professional based on the visualized images.

The tool is reportedly capable of reaching a diagnostic sensitivity and specificity of 95 and 100%, respectively, thereby achieving a level of accuracy that is comparable to the quality criteria defined by the World Health Organization.

Research Director Johan Lundin, from the University of Helsinki, who collaborated on the project, commented that the group’s ultimate aim is to “develop methods that are significantly less labor intensive than the traditional ones and have a potential to considerably increase the throughput in malaria diagnostics.”

Source: Linder N, Turkki R, Walliander M et al. A malaria diagnostic tool based on computer vision screening and visualization of Plasmodium falciparum candidate areas in digitized blood smears. PLoS One 9(8), e104855 (2014).