Deep learning and radiomics

Project aim

Interreg has awarded a new Artificial Intelligence project (DAME, Deep learning Algorithms for Medical image Evaluation) worth 1.1 million euros, to Peter van Ooijen from the UMCG Center for Medical Imaging (CMI). 

The purpose of DAME is to develop a software solution that automatically detects deviations (such as tumors) in medical images by using deep-learning technologies. The major advantage of this innovation is that a generic algorithm will be able to recognize medical abnormalities across different imaging modalities (CT, MRI, etc.). This methodology allows the quick identification of healthy people as well as the detection of deviations that were not specifically sought, such as a second tumor in another location that did not cause any complaints. Furthermore, the identified image features can be used to predict treatment outcome and risk of complications in cancer patients treated with radiotherapy. DAME is expected to improve and accelerate medical diagnosis and treatment, while reducing costs for both the patient and the hospitals.

People involved

Marianna Sijtsema, Roel Steenbakkers, Hans Langendijk, Arjen van der Schaaf, Sanne van Dijk.

Collaborators

Radiology UMCG

SME COSMONiO, Netherlands)

Use-Lab GmbH, Germany

Pius-Hospital Oldenburg, Germany

Radiology West Münsterland, Germany