Enzo ferrante

Invited by Matias Goldin, researcher Enzo Ferrante (Research institute for signals, systems and computational intelligence CONICET / Universidad Nacional del Litoral in Santa Fe, Argentina) will give a talk on Friday July 7th, 10.30 AM, in the conference room of the UCL, 13 Rue Moreau.

This talk will be dealing with "Objective evaluation of human visual function with electroencephalography.".

Abstract: In this seminar, we will discuss some of our studies [1,2,3] on representation learning to improve anatomical plausibility in biomedical image segmentation. We will see how autoencoders can be used to learn low-dimensional embeddings of anatomical structures and propose different ways these embeddings can be incorporated into deep learning models for segmentation and registration.

[1] Learning deformable registration of medical images with anatomical constraints
Mansilla L, Milone D, Ferrante E.
Neural Networks (2020)

[2] Post-DAE: Anatomically Plausible Segmentation via Post-Processing with Denoising Autoencoders
Larrazabal A, Martinez C, Glocker B, Ferrante E.
IEEE Transactions on Medical Imaging (2020)
MICCAI 2019 (conference version)

[3] HybridGNet - Improving anatomical plausibility in image segmentation via hybrid graph neural networks: applications to chest x-ray image analysis
Gaggion N, Mansilla L, Mosquera C., Milone D, Ferrante E.
IEEE Transactions on Medical Imaging (2022)
MICCAI 2021 (conference version)

Enzo hold a permenent position as CONICET faculty researcher in Argentina, leading a research line on machine learning methods for biological and medical image analysis at the Research institute for signals, systems and computational intelligence (CONICET / Universidad Nacional del Litoral) in Santa Fe, Argentina. He's also a professor at Universidad Torcuato Di Tella and Universidad de San Andrés, in Buenos Aires, Argentina. In 2012 he received his Systems Engineering Degree from UNICEN University, Tandil, Argentina. In May 2016, he defended his PhD thesis in Computer Sciences, at the Université Paris-Saclay (CentraleSupeléc / INRIA) in France (Paris) where he worked on deformable registration of multimodal medical images, using graphical models and discrete optimization techniques, under the supervision of Prof. Nikos Paragios. After that, until August 2017, he was a postdoc research associate at Imperial College London (BioMedIA lab), under the supervision of Prof. Ben Glocker working on deep learning and brain image segmentation.

He has also worked at several research institutes around the world. In 2021, he received a Fulbright Fellowship to visit the A. Martinos Center for Biomedical Imaging (Massachusetts General Hospital - Harvard Medical School) in Boston. In 2014, as PhD intern he spent 3 months working on shape understanding for the Computer Vision and Geometry Lab at Stanford University, California, USA. During 2010, he was an intern at STEEP Team (INRIA Grenoble, France) working on transport/land-use mathematical modeling.