1 in 2 of us will get some form of cancer in our lives (Cancer Research UK, 2015). Medical Image Perception is one of the key methods used to detect such abnormalities, and trained medical observers spend their lives saving ours. Yet despite extensive training and expertise, abnormalities can be subtle and difficult to detect, leading to some targets being missed. There is a wealth of healthcare interventions and technologies (including machine learning approaches) trying to tackle this problem. Building on the pioneering work by Kundel & Nodine, the goal of our project is to better understand the processes involved in human visual perception that contribute to decision-making in these life-saving tasks. We conduct experiments that try to reveal how medical scenes are processed as a function of expertise and how the first initial glimpse of a medical scene guides eye movements and decision-making. We make use of eye-tracking technology to objectively measure search behaviour and try to ground the explanations of our findings not just within the context of medical image perception, but also more broadly, with respect to how we make sense of all scenes as a function of expertise and task.
|Effective start/end date||30/09/06 → …|
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.