[en] Due to the complex clinical picture of Parkinson’s disease (PD), the reliable diagnosis of patients is still challenging. A promising approach is the structural characterization of brain areas affected in PD by diffusion magnetic resonance imaging (dMRI). Standard classification methods depend on an accurate non-linear alignment of all images to a common reference template, and are challenged by the resulting huge dimensionality of the extracted feature space. Here, we propose a novel diagnosis pipeline based on the Fisher vector algorithm. This technique allows for a precise encoding into a high-level descriptor of standard diffusion measures like the fractional anisotropy and the mean diffusivity, extracted from the regions of interest (ROIs) typically involved in PD. The obtained low dimensional, fixed-length descriptors are independent of the image alignment and boost the linear separability of the problem in the description space, leading to more efficient and accurate diagnosis. In a test cohort of 50 PD patients and 50 controls, the implemented methodology outperforms previous methods when using a logistic linear regressor for classification of each ROI independently, which are subsequently combined into a single classification decision.
Luxembourg Centre for Systems Biomedicine (LCSB): Integrative Cell Signalling (Skupin Lab) ; Luxembourg Centre for Systems Biomedicine (LCSB): Experimental Neurobiology (Balling Group) ; Luxembourg Centre for Systems Biomedicine (LCSB): Machine Learning (Vlassis Group)
Development of Novel Machine Learning methodologies for early Parkin- son’s disease diagnosis from multi-modal MRI
FnR ; FNR9169303 > Luis Salamanca Mi?o > > Development of Novel Machine Learning methodologies for early Parkinson's disease diagnosis from multi-modal MRI > 01/03/2015 > 28/02/2017 > 2014
[University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
