My PhD focuses on Continual Learning and Out-of-distribution detection for magnetic resonance images (MRIs) and computer tomography (CT) scans. Due to differences in the acquisition process across -and even within- medical institutions, this data often suffers from domain shift. Deep Learning models which are not trained specifically to deal with multi-domain data behave unreliably when applied to out-of-distribution images. My goal is to facilitate the use of Deep learning models for both segmentation and classification/detection in clinical multi-institutional settings.
I am mainly involved in the and RACOON projects. I am also a member of the EVA-KI. You can follow me on Twitter at MICCAI Student Board and see my publication list in @camgbus. My work was recently featured in Google Scholar. Computer Vision News
If you’re interested in these topics and have experience working with PyTorch, please write me an email to inquire about current (Fortgeschrittenes) Visual Computing Praktikum (6 CP) and Master Thesis topics.