Computer vision for microscopy diagnosis of malaria

Malaria is a serious infectious disease caused by a peripheral blood parasite of the genus Plasmodium. According to the World Health Organization (WHO), it causes more than 1 million deaths arising from approximately 300–500 million infections every year [1]. Although there are newer techniques [2], manual microscopy for the examination of blood smears [3] (invented in the late 19th century), is currently "the gold standard" for malaria diagnosis. Diagnosis using a microscope requires special training and considerable expertise [4]. It has been shown in several field studies that manual microscopy is not a reliable screening method when performed by non-experts due to lack of training especially in the rural areas where malaria is endemic [5-7]. An automated system aims at performing this task without human intervention and to provide an objective, reliable, and efficient tool to do so.An automated diagnosis system can be designed by understanding the diagnostic expertise and representing it by specifically tailored image processing, analysis and pattern recognition algorithms. Although it is not a popular research topic, a noticeable number of vision studies directly address the automated diagnosis of malaria [8-16]. Despite being very specialized, if the fatality figures are considered their results may be considered more important than some other popular computer vision applications.This study provides an overview of computer vision studies of malaria diagnosis and intends to fill a gap in this area by doing so. There are some different interpretations of the requirements and thus the applicability of the proposed solutions to the problem. Here, these differences are addressed; the practicality, robustness, accuracy of the proposed solutions and their applicability to perform the actual diagnosis task are questioned. Moreover, the evaluation methods chosen to measure and assess the accuracy are discussed. In addition, some other works of the literature which conc