Thomas Sanchez

e-mail: firstname dot lastname at unil dot ch

I am working as a postdoctoral researcher at the Medical Image Analysis Laboratory with Meritxell Bach Cuadra, in the SP CHUV-UNIL unit of the Center for Biomedical Imaging (CIBM). I am actively involved in the MULTIFACT consortium, a collaborative effort focused on the development of new imaging biomarkers to assess fetal brain development during pregnancy. This consortium allows me to work with amazing collaborators from Germany, Spain, France, and Switzerland. My contribution revolves around developing new methods to improve super-resolution reconstruction for fetal brain Magnetic Resonance Imaging (MRI), as well as robust, learning-based image quality control techniques.

My broader objective is to leverage the power of machine learning to address real-world challenges in medical imaging. I am particularly interested in developing simple and practical solutions that contribute to make machine learning research more open, reproducible and empirically rigorous.

I previously completed my PhD in Machine Learning at EPFL, Switzerland. I worked at the Laboratory for Information and Inference Systems (LIONS), under the supervision of Volkan Cevher. My research was focused on deep learning applied to medical imaging, mostly to problems of reconstruction and optimization of sampling trajectories for MRI.

Other research interests include generative models, inverse problems, variational inference, experiment design, and anything that has to do with best scientific practices!

Selected publications


  1. Preprint
    FetMRQC: Automated Quality Control for fetal brain MRI
    Thomas Sanchez, Oscar Esteban, Yvan Gomez, and 2 more authors
    arXiv preprint arXiv:2304.05879, 2023
  2. Conference
    Simulation-based parameter optimization for fetal brain MRI super-resolution reconstruction
    Priscille Dumast*, Thomas Sanchez*, Hélène Lajous, and 1 more author
    In Medical Image Computing and Computer Assisted Intervention–MICCAI 2023: 26th International Conference, 2023


  1. Thesis
    Learning to sample in Cartesian MRI
    Thomas Sanchez


  1. Preprint
    On the benefits of deep RL in accelerated MRI sampling
    Thomas Sanchez*, Igor Krawczuk*, and Volkan Cevher