Our objective is to develop image reconstruction techniques, modeling/simulation tools and accurate attenuation and scatter correction techniques for Positron Emission Tomography (PET) and Single-Photon Emission Computed Tomography (SPECT), as well as the assessment of new possible designs of PET detection modules using sophisticated Monte Carlo techniques. We are particularly interested in improving the quality and quantitative accuracy of nuclear medicine images, and statistical analysis of different reconstruction algorithms and attenuation and scatter correction techniques. We are particularly interested in developing brain imaging protocols using nuclear medicine technology to study brain function and to apply multivariate statistics to brain images to study the neurofunctional networks underlying cognitive performance. More recently, the lab has been involved in the development of detector modules and novel designs for dedicated high-resolution PET cameras in collaboration with CERN and other research institutions.
Treatment response prediction using MRI-based pre-, post-, and delta-radiomic features and machine learning algorithms in colorectal cancer.
Deep learning-based auto-segmentation of organs at risk in high-dose rate brachytherapy of cervical cancer.
Quantitative Molecular Positron Emission Tomography Imaging Using Advanced Deep Learning Techniques.
The promise of artificial intelligence and deep learning in PET and SPECT imaging.
Département de radiologie et informatique médicale