Carola‐Bibiane Schönlieb

This paper uses contrastive learning on regional biomechanical properties from MRE to improve brain age prediction and detect neurodegeneration, finding that stiffness and damping ratio are sensitive biomarkers for Alzheimer's and MCI.

This study predicts fluorescent Cell Painting images from brightfield images using deep learning, achieving high correlation and demonstrating potential for downstream analysis and repurposing imaging channels.

This paper quantifies structural connectome disruptions in glioblastoma patients using diffusion MRI and shows their association with worse prognosis and survival.

This paper introduces a regularisation framework for cryo-EM structure determination using a convolutional neural network trained on known macromolecular structures, showing improved reconstructions on simulated data.