Markus Frey

CellSeg3D introduces self-supervised 3D cell segmentation models for fluorescence microscopy, achieving performance comparable to supervised methods without requiring ground truth labels.

This paper develops a deep-learning framework to decode sensory and behavioural variables from wide-band neural data with minimal user input and generalization across stimuli and brain regions.

This paper develops DeepMReye, a deep learning model that decodes gaze position from MR signals for camera-less eye tracking in fMRI studies.

This study links neural population directional tuning in the human visual-navigation network to memory performance and behavior using fMRI and encoding models.