CLINICIANS can carry out single case analyses of 3D structural MR and FDG PET scans to extract diagnostic markers for Alzheimer's disease and other dementias (hippocampal/medial temporal atrophy and cortical hypometabolism).
Scans are anonymized when uploaded to the infrastructure and confidentiality is guaranteed.
Markers are extracted by comparing the scan to recognized and representative normative datasets.
Specific tools available for clinicians are AdaBoost, Freesurfer, SPM, MetaROI, HCI8. Please consider that these are not medical devices and that they are not intended for medical use.
AdaBoost is a machine learning method that is mainly used to segment hippocampus regions from 3D T1-weighted structural brain Magnetic Resonance (MR) scans. This has been made possible thanks to the support of the following contributors: Paul Thompson (USC) and DECIDE initiative;
Freesurfer is a set of automated tools for reconstruction of the brain's cortical surface and other subcortical brain structures (e.g.: Hippocampus) from MRI data.
SPM performs a voxel-based analysis of FDG-PET brain images for the assessment of neurodegenerative diseases, by the detection of hypo-metabolic patterns due to pathological conditions. The detection is obtained by the comparison between the PET signal of the single subject under analysis and a reference PET database of normal subjects. The present version of SPM makes use of the FDG PET EADC healthy controls dataset as the normative dataset and template. This has been made possible thanks to the support of the following contributors: Philip Scheltens; Bart van Berkel; Wiesje van der Flier (Amsterdam). Giovanni B. Frisoni; Anna Caroli; Barbara Paghera (Brescia). Flavio Nobili, Silvia Morbelli; Andrea Brugnolo (Genoa). Mira Didic; Eric Guedj (Marseilles). Robert Perneczky; Alexander Dredzga (Munich).
MetaROI is an average metabolism index computed on a set of analytically derived regions of interest (i.e.: left angular, right angular, left temporal, right temporal, and bilateral posterior cingulate binary masks in Montreal Neurological Institute space) reflecting AD hypometabolism pattern. MetaROI index is normalized using the pons and cerebellar vermis ROIs in MNI space. MetaROI has been shown sensitive in the detection of longitudinal cognitive and functional changes in AD and MCI patients. This has been made possible thanks to the support of the following contributor: William Jagust (UC Berkeley & Lawrence Berkeley National Laboratory, California).
HCI is an AD-related hypometabolic convergence index. HCI has been shown able to separate patients with clinical AD from healthy older persons. This has been made possible thanks to the support of the following contributors: Kewei Chen and Eric Reiman (Banner Alzheimer's Institute, Phoenix).