Workshop 2 -Gamification of Medical Image Annotation Tasks
Wednesday, 13.09.2023, 9:30 – 12:00
by Simon Warsinsky
To realize their potential, artificial intelligence (AI) models in medicine often require large amounts of high-quality annotated medical images (e.g., surgical images, CT scans) as training data. Annotation of such images (e.g., segmenting relevant structures) often must be manually done by medical experts, which is a time-intensive, monotonous and tedious process. Thus, it is often difficult for annotators to stay motivated and engaged with medical image annotation task, which can negatively impact annotation quality. One approach to motivate individuals is gamification—the use of game design elements (e.g., points, badges, leaderboards) in non-game contexts. Gamification has shown great potential in application areas like healthcare or education to motivate people to perform certain behaviors (e.g., increased physical activity). To be successful, gamification concepts do however require a careful and context-specific design. In this workshop, we look at gamification as a way to foster annotation quality through annotators’ increased motivation and engagement. Following a brief introduction to medical image annotation tasks and gamification, participants will have the chance to design and discuss their own gamification concepts for medical image annotation tasks. Afterwards, we will introduce a real-world example of a gamified medical image annotation tool from our own research, which participants get to test and provide feedback on.
Simon Warsinsky is a research associate at the Institute of Applied Informatics and Formal Description Methods (AIFB) of the Karlsruhe Institute of Technology (KIT), as well as doctoral researcher in the Helmholtz Information and Data Science School for Health (HIDSS4Health). He received his master’s degree in Information Systems from KIT in 2021. His research interests include gamification, health behavior change and expert data annotation tasks. Currently, he is researching the design of successful gamification concepts for medical image annotation tasks.