A research paper based on BALANCED’s HEWMEN-powered game Eye in the Sky: Defender will be presented to an audience of fellow researchers at the 7th International Conference on Serious Games and Applications for Health, IEEE SeGAH 2019, to be held in Kyoto, Japan, from 5 – 7 of August 2019, at the Ritsumeikan Center for Games Studies.

The paper, titled Training Players to Analyze Age Related Macular Degeneration Optical Coherence Tomography Scans Using a HCG, details how Eye in the Sky: Defender allows players with no prior training in OCT analysis to achieve results similar to trained medical professionals after a small number of playthroughs. It’s exciting to think of the possibilities that computer vision techniques integrated into games could unlock.

Here is a abstract of the paper being presented:

Researchers use optical coherence tomography (OCT) scans to diagnose and evaluate the effectiveness of various treatments and therapies for patients with Age-Related Macular Degeneration (AMD), the leading cause of severe visual impairment in the developed world. While automated evaluation procedures exist, AMD OCT analysis often requires verification or modification by a trained OCT evaluator. With millions of OCT scans performed per year, demand for new evaluation approaches increases. Human computing has proven to be an effective way to crowdsource a variety of scientific problems, as well as leverage human pattern-recognition ability. Video games allow users to interact with the scientific data while also leveraging the elements game developers require to maintain engagement. The authors investigate whether game interactions can train players to evaluate AMD OCT images, creating Eye in the Sky: Defender, which designed gameplay around OCT scan evaluation while supporting the desired outcomes via game mechanics rather than explicit training. In early prototype testing, results suggest player learning within four OCT-image-based game levels. Evaluations of accuracy using the mean user line input reflected a 92% improvement from a players’ initial image evaluation. Spearman rank correlation and Procrustes analysis indicate mean user line accuracy within 10% by image 4 and improved results compared to the automatically generated line in more challenging images. These results suggest Human Computation games can train users to analyze AMD and OCT scans, encouraging expanded research.