Computer aid to diagnostic in epilepsy and Alzheimer''s disease

Computer aided diagnosis in neuroimaging must rely on advanced image processing techniques to detect and quantify subtle signal changes that may be surrogate indicators of disease state. This book proposes two such novel methodologies that are both based on large volumes of interest, are data driven, and make use of cross-sectional scans scans: appearance-based classification (ABC) and voxel-based classification (VBC). The concept of appearance in ABC represents the union of intensity and shape information extracted from magnetic resonance images (MRI). The classification method relies on a linear modeling of appearance features via principal components analysis, and comparison of the distribution projection coordinates for the populations under study within a reference multidimensional appearance eigenspace. Classification is achieved using forward, stepwise linear discriminant analyses,in multiple cross-validated trials. Applications are shown for the lateralization of seizure focus in temporal lobe epilepsy, as well as classification in Alzheimer's disease.

Autorentext

Dr. Simon Duchesne received his Bachelor in Engineering Physics (1993) from the Royal Military College in Kingston (Ontario, Canada), his M.Sc. in Medical Physics (2001) and his Ph.D. in Biomedical Engineering (2005) from McGill University in Montreal (Quebec, Canada). He is now a researcher at Université Laval in Quebec City (Quebec, Canada).

Klappentext

Computer aided diagnosis in neuroimaging must rely on advanced image processing techniques to detect and quantify subtle signal changes that may be surrogate indicators of disease state. This book proposes two such novel methodologies that are both based on large volumes of interest, are datä driven, and make use of cross-sectional scans scans: appearance-based classification (ABC) and voxel-based classification (VBC). The concept of appearance in ABC represents the union of intensity and shape information extracted from magnetic resonance images (MRI). The classification method relies on ä linear modeling of appearance features viä principal components analysis, and comparison of the distribution projection coordinates for the populations under study within a reference multidimensional appearance eigenspace. Classification is achieved using forward, stepwise linear discriminant analyses, in multiple cross-validated trials. Applications are shown for the lateralization of seizure focus in temporal lobe epilepsy, as well as classification in Alzheimer''s disease.