CAMILA G

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 distribution shift. Deep learning models behave unreliably when applied to out-of-distribution images. My goal is to facilitate the use of such models for both segmentation and classification/detection in clinical multi-institutional settings... Check out pre-prints of my recent publications below, and reach out if you're interested in collaborating!... Distance-based detection of out-of-distribution silent failures for Covid-19 lung lesion segmentation

Primary location: Darmstadt