Odin's Eye – A Close Look at Gamification of Labelling of Ophthalmic Diseases

Preprint for accepted abstract at "Joint Conference of the GMDS & CEN-IBS 2020".

Short summary

State of the art deep learning requires vast amounts of accurately labelled training data to enable high classification performance. In order to obtain sufficient amounts of data, data donation is a feasible approach. Yet, the data is only useable, if correct annotation are present. One way to create such annotations is crowd-sourcing via gamification. In this paper, we present an integrated training and annotation approach that allows large scale annotation of ophthalmic diseases.

Prototypes are available as Android APK and WebGL (https://www.medicaldatadonors.org/index.php/odins-eye/). An in-game video was created to demonstrate the gameplay (https://youtu.be/UehnND9gkvY).