We develop computer vision image processing algorithms for analysis of medical images that are focused on registration and segmentation. These techniques are applied to different research projects that include image guided neurosurgery and disease diagnosis, prognosis and quantification for diseases such as multiple sclerosis, epilepsy, schizophrenia and degenerative diseases such as Alzheimer’s dementia.
In the Neuro Imaging and Surgical Technologies Lab of the Brain Imaging Centre of the Montreal Neurological Institute, our team develops computerized image processing techniques such as non-linear image registration, model-based segmentation and appearance-based segmentation to automatically identify, quantify and characterize structures within the human brain. These techniques are applied to large databases of magnetic resonance (MR), computed tomography (CT) and ultrasound (US) data from normal subjects to quantify anatomical variability and to characterize the morphological changes associated disease. The data derived can be used for diagnosis and prognosis and to help study natural history of disease and to improve understanding of disease pathology. In image-guided neurosurgery (IGNS), these techniques provide the surgeon with computerized tools to assist in integrating and interpreting anatomical, functional and vascular imaging data, permitting the effective planning and execution of minimally invasive neurosurgical procedures. Our research has been supported by grants from NSERC, CIHR, FQRNT, CFI, NIH and FRSQ.
You can learn more about our research projects, the research team in the lab, our collaborations or look through our recent publications.