Search liu.se

Anders Eklund, associate professor at the department of biomedical engineering (IMT), has received a research grant of 3.6 million crowns from the Swedish research council

Common statistical methods used to analyse brain activity through images taken with MRI scanners cannot be trusted, as shown by Anders Eklund and Hans Knutsson of Linköping University, in the highly-ranked journal PNAS.

Sharing sensitive data, such as images of brain tumor patients, is complicated. This makes development of AI models for medical image analysis challenging. LiU researchers shows how such models can be trained without sharing sensitive information.

AI makes it possible to quickly and accurately mark areas to be eliminated with radiation when treating cancerous tumors. But due to lack of medical data to train AI models with, attempts are underway to train models with synthetic medical images.

At the end of September, the ASSIST project received 9 million sek in funding. The hope is that their research on automated analysis of brain images will be able to free up time for healthcare professionals.