An app to help scientists sort through thousands of images of brain scans to use in large-scale studies of brain disease has been created by a group of staff and students from Cardiff University.
The app, dubbed NeuroSwipe, is a citizen science collaboration between students at the University’s National Software Academy and academics at the Cardiff University Brain Research Imaging Centre (CUBRIC).
The app trains non-scientists to become experts at recognising brain scans that would be suitable for a scientific study, potentially saving researchers valuable time.
Normally, the individuals who are involved in a scientific study will have different images created of their brain which, for a number of different reasons, such as moving excessively during the brain scan, can vary in quality and so do not provide an accurate and useable picture.
With the largest of these studies including hundreds of thousands of people, the result is a huge bank of images that need to be checked by a trained expert to ensure consistent data quality before the scientific analysis can begin.
“The image filtering process has been largely automated in recent years but training an artificial-intelligence programme to detect poor quality scans is challenging,” said Dr Judith Harrison from CUBRIC, who is leading on the project.
“The human eye is exquisitely sensitive to subtle differences in size, shape, colour and appearance, so that’s why we wanted to get the public involved.”