Gamification in Medical Image Annotation

  • Background

    Supervised machine learning (ML) models in healthcare usually require large amounts of high-quality annotated medical images as training data. To ensure adequate annotation quality, medical image annotation tasks (e.g., outlining objects of interest in CT or MRI images) are usually done manually by medical professionals with pertinent knowledge about human anatomy. In addition to being error-prone, manual annotation is time-intensive, monotonous and exhausting. Hence, it is often difficult for annotators to stay motivated and engaged with the task, which is however an important determinant of annotation quality. One approach to motivate annotators is gamification, which describes the process of transforming a system or activity into one which affords similar positive experiences and practices as found in games. While gamification has been praised for its motivational effects in domains like fitness apps or surveys, research also suggests that successful gamification design is difficult and requires a good understanding of the specific application context. 


    This is an umbrella topic since topics of interest change rapidly. A specific topic will be selected during a first meeting. Possible include, but are not limited to:

    • Development of design guidelines for using individual gamification elements (e.g., badges, leaderboards) or gamification mechanics (e.g., social comparison) in medical image annotation
    • Experimental design on the effects of gamification on cognitive load in annotation tasks
    • Review on the impact of gamification on the perceived professionality of information systems in healthcare

    Introductory Literature

    • Koivisto, J., & Hamari, J. (2019). The rise of motivational information systems: A review of gamification research. International Journal of Information Management, 45, 191-210.

    • Alaghbari, S., Mitschick, A., Blichmann, G., …, Dachselt, R.: Achiever or explorer? gamifying the creation process of training data for machine learning In: Mensch und Computer 2020. ACM, New York, USA (2020)

    • Jauer, M.-L., Spicher, N., Deserno, T.M.: Gamification concept for acquisition of medical image segmentation via crowdsourcing. In: Proc. SPIE, Medical Imaging 2021 (2021)

    • Lowry, P.B., Petter, S., Leimeister, J.M.: Desperately seeking the artefacts and the foundations of native theory in gamification research: why information systems researchers can play a legitimate role in this discourse and how they can better contribute. European Journal of Information Systems, 29(6), 609–620 (2020)