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.
Novel adversarial semantic structure deep learning for MRI-guided attenuation correction in brain PET/MRI.
Estimation of the radiation dose in pregnancy: an automated patient-specific model using convolutional neural networks.
Fast and accurate pseudo multispectral technique for whole-brain MRI tissue classification.
Construction of patient-specific computational models for organ dose estimation in radiological imaging.
Département de radiologie et informatique médicale