Finnish researchers have claimed to develop a new system for diagnosing malaria infection faster.

 

 The method is based on computer vision algorithms similar to those used in facial recognition systems combined with visualisation of only the diagnostically most relevant areas.

 

 Tablet computers can be used to view the images.

 

 This is how it works.

 

 A thin layer of blood smeared on a microscope slide is first digitised.

 

 The algorithm analyses over 50,000 red blood cells per sample and ranks them according to the probability of infection.

 

 The programme then creates a panel containing images of over a hundred most likely infected cells and presents that panel to the user.

 

 The final diagnosis is done by a healthcare professional based on the images.

 

 "Our aim is to develop methods that are significantly less labour intensive than the traditional ones and have a potential to considerably increase the throughput in malaria diagnostics," said research director Johan Lundin from the Institute for Molecular Medicine Finland (FIMM), University of Helsinki.

 

 The accuracy of this method is comparable to the quality criteria defined by the World Health Organisation (WHO), he added.

 

 In the test setting, over 90 percent of the infected samples were accurately diagnosed based on the panel.

 

 The method of imaging and analysis could also be used for diagnosing diseases other than malaria.

 

 The research was published online in the PLOS ONE scientific journal.