Scholar
Yaël Balbastre
Google Scholar ID: VvO_GoYAAAAJ
University College London
Citations & Impact
Citations
1,291
H-index
13
i10-index
20
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Paper “Learn2Synth: Learning Optimal Data Synynthesis using Hypergradients for Brain Image Segmentation” accepted at ICCV 2025; presented “Schwarz–Schur Involution: Lightspeed Differentiable Sparse Linear Solvers” at ICML 2025; work “A method for automatic 3D vasculature segmentation in ex vivo MRI using synthetic data” received Magna Cum Laude award at ISMRM 2025; released a new major version of Statistical Parametric Mapping, SPM25, which is the first major version since SPM12 (released in 2014).
Research Experience
- Was a faculty member at Massachusetts General Hospital (MGH) and Harvard Medical School (HMS). Served as a postdoctoral fellow with Bruce Fischl at MGH/HMS, and with John Ashburner and Martina Callaghan at UCL. Currently, a Newton International Fellow at University College London.
Education
- Completed PhD at the French Alternative Energies and Atomic Energy Commission (CEA), in the MIRCen and NeuroSpin laboratories, advised by Thierry Delzescaux and Jean-François Mangin.
Background
- Works on various aspects of medical image computing, with a focus on neuroimaging. Particularly interested in generative probabilistic models and their integration with machine learning techniques. Has worked on Bayesian shape modelling, image segmentation and registration, and quantitative MRI. Recently, focused on multimodal image registration and vasculature segmentation, aiming to build cellular-resolution atlases of the human brain.
Co-authors