🧠Postdoctoral Fellow / Research Associate
Department of Radiology, Mayo Clinic, Rochester, MN, USA
PhD in Medicine (Medical Physics and Technology)
2017-01-01
2021-07-01
University of Oulu, Finland
MSc in Biomedical and Clinical Technology (Ing.)
2013-09-01
2016-09-01
Czech Technical University, Prague & University of Groningen, Netherlands (Erasmus Mundus Joint Degree)
BSc in Biomedical Engineering (Summa Cum Laude)
2009-09-01
2013-06-27
Jimma University, Ethiopia
We developed a machine learning framework to quantify disease heterogeneity and progression in multiple system atrophy and Parkinson's disease using structural and diffusion MRI.
We tested whether combining plasma biomarkers, genetics, cardiovascular risk, and lifestyle measures with MRI improves prediction of cognitive decline beyond any single data …
We introduce THETA (Tau Heterogeneity Evaluation in Alzheimer's Disease), a novel tau PET summary metric that captures the full spatial heterogeneity of tau deposition across the …
We developed a machine learning method to identify transition points in Alzheimer's disease biomarkers as a supplement to the reliable worsening method.
We conducted a systematic comparison of cross-scanner harmonization methods for structural MRI and demonstrated that widely adopted techniques may not perform as reliably as the …
I will remotely attend AAIC 2026 in London to present recent work in neuroimaging and machine learning for Alzheimer's disease.
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 …
Diffusion methods have overtaken GANs for generating images. Turning MRI into PET is within reach, yet a realistic picture is not a trustworthy one.
Disease trajectories are not lines. They bend, and the bend is where the clinical meaning hides.
Explainability tools tell you which features a model used. They rarely tell you which ones mattered.
A handful of dark specks, a few millimeters across, scattered anywhere in the brain. That is a cerebral microbleed, and it is one of the hardest things in neuroimaging to pin down. …