Hamza Kebiri joined the CIBM SP CHUV-UNIL Computational Neuroanatomy & Fetal Imaging Section in September 2023.
Hamza’s main research interest encompasses neuroscience, brain reconstruction, machine learning, and its applications to medical neuroimaging. His current works involve brain reconstruction of developing brains using diffusion MRI and translational aspects between high and low-field MRI and between pediatric populations.
Hamza received a bachelor’s and a master’s degree in Communication Systems from the Ecole Polytechnique Fédérale de Lausanne (EPFL) in Switzerland, and a master’s degree in Cognitive Science (Neuroinformatics & Neuroscience) from Osnabrück University, in Germany.
He has worked in a variety of machine learning projects including his EPFL master thesis in fraud detection on an online banking system, and a big data analysis of health risks from six hospitals.
In 2017, he joined the Connectomics department of the Max Planck Institute for Brain Research in Frankfurt. Under the direction of Prof. Moritz Helmstaedter, he focused on the segmentation and reconstruction of multibeam scanning electron microscopy (mSEM) data using deep neural networks.
Between 2019 and 2023, he performed a PhD thesis in the Life Science program of Lausanne University under the supervision of Dr. Meritxell Bach Cuadra, supported by the Swiss National Science Foundation (SNSF) project 182602. In his PhD project, he worked on the super-resolution reconstruction of fetal and newborn brains from diffusion magnetic resonance imaging (dMRI) data.
In 2022, he was awarded an FNS Mobility Grant to work as a visiting scholar on fetal and newborn projects in the IMAGINE group at Boston Children’s Hospital & Harvard Medical School in USA with Prof. Ali Gholipour and Prof. Davood Karimi, with whom the collaboration is still ongoing.
Dr. Kebiri started as a senior FNS researcher in the project aiming to tackle domain shifts in the reconstruction, segmentation, and quantitative mappings between newborn and fetal populations and between high (1.5T & 3T) and low (0.55T) field strengths.
KEYWORDS: low field, MRI, image reconstruction, fetal population, machine learning