Researcher

Florence Marie Muller

Research disciplines
  • Engineering and technology
    • Other (bio)medical engineering not elsewhere classified
    • Data visualisation and imaging
Expertise
PET-CT Dynamic imaging and kinetic modelling Deep learning denoising and image generation Medical image processing
Other academic online profiles
Bio
Florence Muller obtained her Master of Engineering degree in Mechanical and Materials Engineering from the University of Birmingham (UK) in July 2020. On graduation, she was awarded the Ray Smallman prize for best academic performance. During her undergraduate studies in Birmingham, she received the Rolls-Royce Academic prize and her master thesis (supported by Rolls-Royce plc.) explored very advanced techniques of predictive modelling for crack growth behaviour in turbine disc alloys of aero-engines. In 2020-2022, Florence pursued a Master of Science in Biomedical Engineering at Ghent University (Belgium). During her master, she worked with the Medical Image and Signal Processing (MEDISIP) group for her master thesis entitled “Dose reduction and image enhancement in micro-CT using deep learning”. In recognition of her master thesis work, she received the Biomedical Excellence Award (issued by moveUP.care), and also won the 2022 IE-net prize (awarded by the Flemish Association of Engineering) and the Jozef Plateauprijs (awarded by the alumni association of engineers from Ghent University). In August 2022, she joined the MEDISIP group as a PhD student in Biomedical Engineering (with promotors: prof. Stefaan Vandenberghe and prof. Christian Vanhove). Her PhD work “Deep Learning-Enhanced 4D Total-Body PET Imaging” is funded by the Research Foundation Flanders (FWO). She spent the first year of her PhD abroad at the University of Pennsylvania (Philadelphia, U.S.A.) as part of the Physics and Instrumentation Group under the mentorship of prof. Joel Karp and dr. Margaret Daube-Witherspoon. As a visiting research scholar, she was jointly funded by the Fulbright Commission and the Belgian American Educational Foundation. In her PhD, Florence is working on the development of deep learning strategies for image processing (denoising in 3D/4D) and data corrections, aiming for PET-CT dose reduction (e.g., CT-less attenuation correction in PET). Her scientific interests include the integration of artificial intelligence methods into image generation and processing to obtain more quantitatively accurate PET and CT image for clinical and preclinical applications. She is also actively involved in a new collaborative project that aims to develop a flat panel total-body PET scanner with low-cost monolithic high-resolution detectors: the Walk-Through Total-Body PET for patients in upright standing position (instead of patient positioning on a bed) to achieve higher patient throughput. Her research projects have, so far, resulted in four A1 publications and thirteen conference contributions (9 posters, 4 orals) as first author. Date: March 2024