New public-private AI research lab for medical image analysis at the University of Amsterdam

UvA professors Cees Snoek and Marcel Worring are starting a new public-private research lab together with researchers from the Inception Institute of Artificial Intelligence Ltd. from the United Arab Emirates led by Professor Ling Shao. Within the new AIM lab, the researchers will focus on using artificial intelligence for medical image analysis. The lab will form part of ICAI, the national Innovation Center for Artificial Intelligence, located at Amsterdam Science Park.

Medical practice requires more and more interpretation of digital images. Human experts are expensive, error prone and get tired. Recent developments in image recognition, in particular through 'deep learning', have shown that computers can extract more information from images and are sometimes more reliable than people due to their increased accuracy. However, image recognition has mainly focused on everyday images such as those that can be found on Instagram and YouTube. ‘Adapting and further developing image recognition to the characteristics of medical images is an important challenge for the AIM Lab’, says Cees Snoek, one of the scientific directors of the AIM Lab. ‘From a technical perspective, work will be done on fundamental and relatively general AI models and algorithms that can be applied to specific diseases.’

AI for faster diagnosis

Over the next five years, seven PhD researchers will work in the lab on projects that will focus, among other things, on achieving a quicker diagnosis of Alzheimer’s disease, modelling cardiac rhythms and on generating automatic reports based on X-ray images.

The AIM Lab is the seventh lab to form part of ICAI. Over the past year, AIRlab Amsterdam (a joint industry lab with Ahold Delaize), the National Police Lab (collaboration between UvA, Utrecht University and the National Police) and Elsevier AI Lab (partnership between UvA, VU University Amsterdam and Elsevier) were created.

This release was first published 18 March 2019 by the University of Amsterdam.