Elodie attended and presented at the 2024 International Conference on Image Processing (ICIP) in Abu Dhabi, UAE
Elodie had the chance to attend the 2024 IEEE International Conference on Image Processing in Abu Dhabi, Emirates. She presented her work during an oral session about Medical Image Analysis. This work was part of her Ph.D. projects and was entitled Uncovering communities of pipelines in the task fMRI analytical space. In this work, she used graph representations to explore the relationships between fMRI pipelines results and the stability of their relationships across different study contexts. The results were useful to evaluate the potential generalisability and robustness to unseen context of methods to mitigate analytical variability, for instance, style transfer between statistic maps.
Elodie Germani
Postdoctoral Researcher
Elodie Germani works with Prof. Shadi Albarqouni as a postdoctoral researcher. She did her PhD at the University of Rennes, under the supervision of Dr. Camille Maumet and Prof. Elisa Fromont. After four years of medicine school at the University of Versailles, she took a shift in her career and started a Master’s degree in bioinformatics. Her research focuses on exploring, modelling and building solutions to take into account the variability of data in medical imaging, particularly using deep representation learning. During her PhD, her goal was to facilitate the re-use of data shared on public databases by taking into account the different sources of variability. In the future, she would like to focus more in the use of real-world data and on the robustness of machine learning models to dataset shifts and privacy attacks.