An additional field of application is the process of image registration, in which the computer aligns images taken at different times to allow optimal comparison. At the SPIE conference, MEVIS researcher Alessa Hering will present a self-learning algorithm to facilitate follow-up examinations of patients with lung tumors. Has the lump in the patient’s lung grown in a couple of weeks, or has it shrunk as anticipated following the therapy? In order to assess this, recent and older images need to be aligned to show exactly the same structures. Fraunhofer experts have significantly accelerated this automatic image registration. “We were able to achieve a 40-fold acceleration of the already efficient registration at an acceptable quality,” says Meine. “Previously, the process took eight seconds. With deep learning, it takes only 0.2 seconds.”

At the conference, the MEVIS experts will present some of their new software components as live demonstrations. They will also offer two courses for experts who want to become acquainted with this still novel topic. “We are now in a phase in which deep learning is gradually entering the medical routine,” stresses Hans Meine. “This is why we are already working together with clinical partners and firms.”

Back to HCB News

CT Homepage