Development of a medical training mannequin for ultrasound-guided needle interventions

Achievement of competence in medical interventions requires practice, and early stages of practice are best done in simulation, typically using some combination of digital (computer generated) and physical (mannequin) models. The overall objective of the pro;osed MITACS Globalink project is to design, implement and evaluate a practical embodiment of the novel low-cost ultrasound-guided kidney intervention […]

Read More
AI-based interpretation of lung ultrasound

Lung ultrasound is an efficient and widespread method used in bedside diagnostic examinations. The interpretation of ultrasound in emergency care is an extremely difficult task, especially for less experienced physicians. The objective of the project is to implement and validate comprehensive AI-based approach using deep learning to assist in identifying diagnostically relevant imaging features and […]

Read More
Algorithmes de déduction pour les modèles d’ordonnancement sous contraintes minimisant le délai moyen

Un ordonnancement est défini par le planning d’exécution des tâches et d’allocation des ressources, et vise généralement à satisfaire un ou plusieurs objectifs. La fonction objectif la mieux traitée est la minimisation du délai total, i.e. la date de fin de l’ordonnancement. Une part conséquente et structurée de la littérature y est consacrée que ce […]

Read More
Development of recommender system based on user and item data

With this project, we aim to increase our knowledge and experience in recommender systems. We are specifically interested in testing various data structures and algorithms that will allow us to provide recommendations to our users based on their interest (user-user), as well as the intrinsic similarities between different elements of our database (item-item). Based on […]

Read More
Develop anatomical compartment model protocols for human anatomical segmentation

This project will help Voronoi Health Analytics improve and refine their advanced artificial models used for automating interpreting and analyzing medical images. The intern will help with data collection processes that are required in order to train state of the art AI models for automating medical image analysis, resulting in more efficient and effective health […]

Read More
Approche bayésienne en tractographie : modélisa

La recherche sur le cerveau se tourne de plus en plus vers des études qui consistent à observer un même groupe d’individus sur une longue période. De ces études, nous sommes désormais capables d’extraire une multitude d’informations relativement complexes (multi-dimensionnalité) sur le fonctionnement du cerveau. Or, les outils statistiques actuels ne permettent pas de considérer […]

Read More
Machine learning developer interns within cross-functional teams to develop and commercialize AI-powered solutions – Part 2

AltaML is an innovative company capitalizing on a major technological trend: artificial intelligence (AI) technologies, enabled by big data, are driving a fourth industrial revolution. AI will transform all industries, but traditional industries face challenges in implementing AI. AltaML has a unique business model to overcome barriers to adoption of AI solutions by industry, which […]

Read More
Machine learning developer interns within cross-functional teams to develop and commercialize AI-powered solutions – Part 3

AltaML is an innovative company capitalizing on a major technological trend: artificial intelligence (AI) technologies, enabled by big data, are driving a fourth industrial revolution. AI will transform all industries, but traditional industries face challenges in implementing AI. AltaML has a unique business model to overcome barriers to adoption of AI solutions by industry, which […]

Read More
Building Spatio-temporal Transformers for Egocentric 3D Pose Estimation

Using a fisheye head-mounted camera to estimate human pose in 3D has become increasingly popular in recent years due to its ability to capture activities in unconstrained environments. Egocentric 3D human pose estimation (HPE) has a number of challenges due to self-occlusions and strong distortions. Intermediate heatmap-based representations have been found to be effective in […]

Read More
Artificial intelligence for the prediction of variables in health

Today, thanks to microelectronics, it is possible to find technology that continuously collects data such as motion kinematics or physiological data. This type of technology is commonly referred to as wearable and therefore the scope of this project is to find methodologies based on artificial intelligence for the creation of models that can predict a […]

Read More
Automated Video Content Chaptering via Machine Learning

The research will focus on building a deep learning model to analyze video and audio streams of input video material, essentially creating something like a table of contents, for example: * Minutes 0-3: Introduction. Our topic is binomial coefficients. * Minutes 3-4: Problem source. * Minutes 4-6: Details of the mathematics. Calculations of values. * […]

Read More