Search Results for author: Eugene Vorontsov

Found 13 papers, 7 papers with code

Label noise in segmentation networks : mitigation must deal with bias

no code implementations5 Jul 2021 Eugene Vorontsov, Samuel Kadoury

In this work, we explore biased and unbiased errors artificially introduced to brain tumour annotations on MRI data.

Medical Image Segmentation Semantic Segmentation

Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics

1 code implementation NeurIPS 2019 Giancarlo Kerg, Kyle Goyette, Maximilian Puelma Touzel, Gauthier Gidel, Eugene Vorontsov, Yoshua Bengio, Guillaume Lajoie

A recent strategy to circumvent the exploding and vanishing gradient problem in RNNs, and to allow the stable propagation of signals over long time scales, is to constrain recurrent connectivity matrices to be orthogonal or unitary.

Towards annotation-efficient segmentation via image-to-image translation

no code implementations2 Apr 2019 Eugene Vorontsov, Pavlo Molchanov, Christopher Beckham, Jan Kautz, Samuel Kadoury

Specifically, we propose a semi-supervised framework that employs unpaired image-to-image translation between two domains, presence vs. absence of cancer, as the unsupervised objective.

Brain Tumor Segmentation Image-to-Image Translation +2

On orthogonality and learning RNNs with long term dependencies

no code implementations ICML 2017 Eugene Vorontsov, Chiheb Trabelsi, Samuel Kadoury, Chris Pal

We find that hard constraints on orthogonality can negatively affect the speed of convergence and model performance.

Liver lesion segmentation informed by joint liver segmentation

no code implementations24 Jul 2017 Eugene Vorontsov, An Tang, Chris Pal, Samuel Kadoury

We propose a model for the joint segmentation of the liver and liver lesions in computed tomography (CT) volumes.

Computed Tomography (CT) Lesion Detection +2

Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation

no code implementations16 Feb 2017 Michal Drozdzal, Gabriel Chartrand, Eugene Vorontsov, Lisa Di Jorio, An Tang, Adriana Romero, Yoshua Bengio, Chris Pal, Samuel Kadoury

Moreover, when applying our 2D pipeline on a challenging 3D MRI prostate segmentation challenge we reach results that are competitive even when compared to 3D methods.

Medical Image Segmentation Semantic Segmentation

On orthogonality and learning recurrent networks with long term dependencies

1 code implementation31 Jan 2017 Eugene Vorontsov, Chiheb Trabelsi, Samuel Kadoury, Chris Pal

We find that hard constraints on orthogonality can negatively affect the speed of convergence and model performance.

The Importance of Skip Connections in Biomedical Image Segmentation

1 code implementation14 Aug 2016 Michal Drozdzal, Eugene Vorontsov, Gabriel Chartrand, Samuel Kadoury, Chris Pal

In this paper, we study the influence of both long and short skip connections on Fully Convolutional Networks (FCN) for biomedical image segmentation.

Semantic Segmentation

Metastatic liver tumour segmentation from discriminant Grassmannian manifolds

no code implementations31 Aug 2015 Samuel Kadoury, Eugene Vorontsov, An Tang

The early detection, diagnosis and monitoring of liver cancer progression can be achieved with the precise delineation of metastatic tumours.

Cannot find the paper you are looking for? You can Submit a new open access paper.