Enzo Ferrante – Towards anatomically plausible medical image segmentation, registration and reconstruction

/ August 13, 2020/

When:

September 1, 2020 @ 12:00 pm – 1:00 pm

2020-09-01T12:00:00-04:00

2020-09-01T13:00:00-04:00

Abstract: In this seminar, we will discuss our recent works on representation learning to improve anatomical plausibility in biomedical image segmentation, registration and reconstruction. We will see how denoising autoencoders can be used to learn low-dimensional encodings of anatomical structures and propose different ways in which these embeddings can be incorporated into deep learning models. The idea is to constraint the space of solutions and encourage anatomical plausibility in the model output. We will explore different application domains, ranging from X-ray image registration [1] and segmentation [2,3] to skull reconstruction in brain CT images [4].

[1] Learning deformable registration of medical images with anatomical constraints

Mansilla L, Milone D, Ferrante E.

Neural Networks, Elsevier (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)

[3] Anatomical priors for image segmentation via post-processing with denoising autoencoders

Larrazabal A, Martinez C and Ferrante E.

MICCAI 2019.

[4] Self-supervised Skull Reconstruction in Brain CT Images with Decompressive Craniectomy

Matzkin F, Newcombe V, Stevenson S, Khetani A, Newman T, Digby R, Stevens A, Glocker B, Ferrante E

Accepted for publication at MICCAI 2020.

Bio: Enzo completed his PhD in Computer Sciences under the supervision of Prof. Nikos Paragios at Université Paris-Saclay (CentraleSupeléc / INRIA) in Paris, and his undergrad in Systems Engineering at UNICEN University (Tandil, Argentina). He worked as a postdoctoral researcher with Dr. Ben Glocker at Imperial College London (BioMedIA Lab) in the UK. He returned to Argentina in 2017, where he holds a research scientist position from the Argentina’s National Research Council (CONICET) and a lecturer position at Universidad Nacional del Litoral. He leads the Machine Learning for Biomedical Image Computing research line in the Research Institute for Signals, Systems and Computational Intelligence, sinc(i). His research interests span both artificial intelligence and biomedical image analysis, with focus on deep learning methods.