I completed a Master's in Computer Vision and Image Processing at Sorbonne Université, after a Bachelor's in Computer Science at UBO.

My graduate training focused on machine learning, deep learning, signal and image processing, and their scientific applications, particularly biomedical imaging.

Throughout my Master's, I carried out four research internships in biological image analysis and computational neuroscience, three of them involving fluorescence microscopy data. During my first internship at the Biological Image Analysis Unit of Institut Pasteur, I developed statistical methods to cluster single-neuron activity into functional assemblies. In a second internship, I helped develop a method to track neurons in microscopy videos of a freely deforming organism (Hydra). At Washington University in St. Louis, I developed methods to infer brain-wide functional interactions and estimate the dimensionality of neural activity from large-scale microscopy recordings of zebrafish larvae. At the École Normale Supérieure, I contributed to developing an image processing toolbox that extracts astrocytic networks from calcium imaging recordings of mouse astrocytes and represents them as spatio-temporal graphs.

I then moved from academic research to industry, spending over a year at Hera-MI, a medical software company. There, I first built graphical interface features for software that helps radiographers assess mammography image quality in clinical settings, then worked on the design and development of machine learning systems for breast cancer screening from X-ray mammography.

At the CENTURI Multi-Engineering Platform, I now bring this image processing and machine learning background to a new challenge: helping researchers analyze their imaging and omics data jointly, which can reveal structure that neither modality shows on its own.

Keywords: Machine Learning, Deep Learning, Segmentation, Tracking, Image Processing, Computer Vision, Multimodal Data Integration, Spatial Omics, Reproducible Pipelines, FAIR Data