UCLA researchers develop hand-held malaria diagnosis technique
Aydogan Ozcan and his research group were heavily involved in developing the technology, which represents an improvement of more than two orders of magnitude compared to other nano imaging techniques. The technique allows doctors to detect individual particles below 100 nanometers in size across a field-of-view of 20.5 square millimeters. Ozcan's team published the research in Nature Photonics, Optics.org reports.
Ozcan recently spoke about the technique at the SPIE Photonics West conference in San Francisco.
"Lensless imaging can construct images of cells from their 'almost-shadows', through computational microscopy and on-chip holography, which are good enough to allow visual identification of malaria-infected red blood cells," Ozcan said, according to Optics.org.
The on-chip microscopy technique then allows for the delivery of the images to human gamers to crowdsource a malaria diagnosis through the BioGames platform.
"BioGames is a virtual gaming platform, displaying those images and allowing an unlimited number of gamers from any location in the world to access and indicate which of the images they believe show the presence of infection," Ozcan said, Optics.org reports.
The BioGames platform trains players using a frame of images of red blood cells, which can be marked as infected or healthy. The system is then able to dynamically assess the performance of the gamers as they progress.
When the platform encounters difficult to diagnose images, it crowdsources the images for diagnosis by the human players. The data is checked for accuracy and then fed back through the system, allowing the algorithms to improve through added training data.
"The presence of control images on each screen is linked to a ranking of players, behind the scenes," Ozcan said, according to Optics.org. "It's similar to other big data management scenarios; the crowd, in this case professionals and non-experts, against the machine."
Ozcan said the malaria diagnosis game could stop the bottleneck in diagnosis by exploiting the visual recognition of non-experts to achieve more diagnoses with fewer available experts, Optics.org reports.