PhD defense Mehmet Dalmis

Mehmet Dalmis will defend his PhD thesis with the title' Automated Analysis of Breast MRI: from Traditional Methods into Deep Learning' the 12th of September at 12.30 in the Auditorium of Radboud University

Advances in radiology improve healthcare by providing more detailed information about various diseases, such as cancer. However, increased complexity and information in radiological images, together with screening programs also increase workload of radiologists. Can computers help by automating some of their tasks? Researchers have been working on the use of computers in radiological image interpretation for a long time with limited success. However, the recently popularized technique ‘deep learning’ is changing this, leading to new artificial intelligence systems that perform at the accuracy level of the radiologists. This thesis focuses on the breast MRI dimension of this transition. It presents deep learning based artificial intelligence systems for automated reading of breast MRI. Results show the strong potential of deep learning algorithms to replace traditional computer algorithms for breast MRI and help radiologists in the interpretation of complex information obtained from these radiological images.

Extra information can be found at the Radboudumc website.