Where a model looks is not why it decides
Explainability tools tell you which features a model used. They rarely tell you which ones mattered.
Dr. Robel Gebre
Postdoctoral Fellow / Research Associate
Department of Radiology, Mayo Clinic, Rochester, MN, USA
I am a Research Associate in the Department of Radiology at Mayo Clinic, developing and validating quantitative imaging biomarkers for Alzheimer’s disease and related neurodegenerative conditions.
My work includes tau PET quantification, multisite MRI harmonization, disease progression modeling, and machine learning imaging signatures of rare disorders such as multiple system atrophy.
TPE: finding the turning point in disease progression
Disease trajectories are not lines. They bend, and the bend is where the clinical meaning hides.
From noise to PET: diffusion is winning, but is it really?
Diffusion methods have overtaken GANs for generating images. Turning MRI into PET is within reach, yet a realistic picture is not a trustworthy one.
PET Tracer Classification and the Tau Therapeutic Window
A podium talk on a 2.5D deep learning classifier for PET tracer identification, and a poster introducing the tau therapeutic window as an eligibility criterion for anti-amyloid …