Francis Dutil

Learn More
Ischemic stroke is the most common cerebrovascular disease, and its diagnosis, treatment, and study relies on non-invasive imaging. Algorithms for stroke lesion segmentation from magnetic resonance imaging (MRI) volumes are intensely researched, but the reported results are largely incomparable due to different datasets and evaluation schemes. We approached(More)
Generative Adversarial Networks (GANs) have gathered a lot of attention from the computer vision community, yielding impressive results for image generation. Advances in the adversarial generation of natural language from noise however are not commensurate with the progress made in generating images, and still lag far behind likelihood based methods. In(More)
We investigate the integration of a planning mechanism into sequence-to-sequence models using attention. We develop a model which can plan ahead in the future when it computes its alignments between input and output sequences, constructing a matrix of proposed future alignments and a commitment vector that governs whether to follow or recompute the plan.(More)
We investigate the integration of a planning mechanism into an encoder-decoder architecture with attention. We develop a model that can plan ahead when it computes alignments between the source and target sequences not only for a single time-step, but for the next k timesteps as well by constructing a matrix of proposed future alignments and a commitment(More)
We present a fully automated generative method for brain tumor segmentation in multi-modal magnetic resonance images. We base the method on the type of generative model often used for healthy brain tissues, where tissues are modeled by Gaussian mixture models combined with a spatial tissue prior. We extend the basic model with a tumor prior, which uses(More)
We investigate the integration of a planning mechanism into an encoder-decoder architecture with attention for character-level machine translation. We develop a model that plans ahead when it computes alignments between the source and target sequences, constructing a matrix of proposed future alignments and a commitment vector that governs whether to follow(More)
  • 1