The Minc toolkit contains the open source libraries and image processing tools developed in the NIST lab and at the McConnell Brain Imaging Centre, Montreal Neurological Institute. More information about the toolkit can be found on the official BIC-MNI software website.
Ibis Neuronav is the open source image-guided neurosurgery platform developed by the NIST lab and used routinely in the operating rooms at the Montreal Neurological Institute. More information about the platform can be found on the official Ibis website.
White Matter Hyperintensities Segmentation Pipeline
White matter hyperintensities (WMHs) are considered to be one of the major signs of SVD on MRI and are associated with neurological and cognitive symptoms and physical difficulties. We have developed automated tools for segmentation of WMHs in Alzheimer’s patients using multiple contrasts of MR images. More information about the pipeline can be found here.
Brain tIsue SegmentatiOn pipeliNe (BISON)
Accurate automated tissue segmentation is challenging due to the variability in the tissue intensity profiles caused by differences in scanner models, acquisition protocols, as well as the age of the subjects and presence of pathology. We have developed BISON (Brain tIsue SegmentatiOn pipeliNe), a new pipeline for tissue segmentation using a random forests classifier and a set of intensity and location priors obtained based on T1w images. More information about the pipeline can be found here.
FWML and DAWM Separation Tool
Focal white matter lesions (FWML) and diffuse abnormal white matter (DAWM) are two categories of white matter T2-weighted (T2w) hyperintensities which show different degrees of demyelination, axonal loss and immune cell density in pathology, potentially offering distinct correlations with symptoms. We have developed an automated tool to separate FWML and DAWM based on their intensity profile in T2-weighted images. More information about the tool can be found here.
Lateral ventricles are reliable and sensitive indicators of brain atrophy and disease progression in behavioral variant frontotemporal dementia (bvFTD). VentRa takes a comma separated (.csv) file providing the path for the raw T1-weighted images as well as age and sex of the subjects as input, and provides preprocessed images along with ventricle segmentations, QC files for the segmentations, as well as a .csv file including the diagnosis (based on the classifier trained on bvFTD vs the mixed group data) along with all the extracted ventricle features: i.e. total ventricle volume, ventricle volumes in each lobe and hemisphere, anterior-posterior ratio (APR), left-right temporal lobe ratio (LRTR), and left-right frontal ratio (LRFR). More information about the tool can be found here.