Crowdsourced game to fight malaria
Players around the world fights malaria by hunting parasites on blood images uploaded directly from affected areas.
Crowdsourcing Malaria Parasite Quantification: An Online Game for Analyzing Images of Infected Thick Blood Smears
There are 600,000 new malaria cases daily worldwide. The gold standard for estimating the parasite burden and the corresponding severity of the disease consists in manually counting the number of parasites in blood smears through a microscope, a process that can take more than 20 minutes of an expert microscopist’s time.
This research tests the feasibility of a crowdsourced approach to malaria image analysis. In particular, we investigated whether anonymous volunteers with no prior experience would be able to count malaria parasites in digitized images of thick blood smears by playing a Web-based game.
The the results were published in the Journal of Medical Internet Research: Crowdsourcing Malaria Parasite Quantification: An Online Game for Analyzing Images of Infected Thick Blood Smears.
Exhaustive computations measured the parasite counting accuracy for all players as a function of the number of games considered and the experience of the players. In addition, we propose a mathematical equation that accurately models the collective parasite counting performance.
Today the project has started the deployment phase on real terrain, a group of experts has traveled to Mozambique to get infected blood samples on the fly, this samples are uploaded continously to the Malariaspot.org platform, where players will hunt parasites over the blood samples and the results are resturned in hours to the original blood image uploader.
This concept is being applied to more disseases where a human detection is needed, from our original team new students has been hired to keep the project alive, with great results. The original web-app has been ported to iOS and Android and now a clone called TuberSpot was developed to detect the tuberculosis bacteria. And more clones are on the way to be released.
Results revealed that combining 22 games from nonexpert players achieved a parasite counting accuracy higher than 99%. The findings support the conclusion that nonexperts are able to rapidly learn how to identify the typical features of malaria parasites in digitized thick blood samples and that combining the analyses of several users provides similar parasite counting accuracy rates as those of expert microscopists.
This experiment illustrates the potential of the crowdsourced gaming approach for performing routine malaria parasite quantification, and more generally for solving biomedical image analysis problems, with future potential for telediagnosis related to global health challenges.