Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Improved Parkinson’s disease classification from diffusion MRI data by Fisher vector descriptors
Salamanca Mino, Luis; Vlassis, Nikos; Diederich, Nico et al.
2015In Improved Parkinson’s disease classification from diffusion MRI data by Fisher vector descriptors
Peer reviewed
 

Files


Full Text
paper1223_defSubmitted.pdf
Author preprint (363.17 kB)
Download
Annexes
VideoPosterBidiMICCAI.mp4
(53.62 MB)
Explanatory video of the paper
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Neurodegenerative diseases; Diagnosis; Diffusion magnetic resonance imaging; Machine Learning; Feature Extraction
Abstract :
[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.
Research center :
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)
Disciplines :
Computer science
Neurology
Author, co-author :
Salamanca Mino, Luis ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Vlassis, Nikos ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
Diederich, Nico ;  Adobe Research
Bernard, Florian ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC)
Skupin, Alexander  ;  University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
External co-authors :
yes
Language :
English
Title :
Improved Parkinson’s disease classification from diffusion MRI data by Fisher vector descriptors
Publication date :
October 2015
Event name :
Medical Image Computing and computer assisted intervention
Event place :
Munich, Germany
Event date :
October, 5-9
Audience :
International
Main work title :
Improved Parkinson’s disease classification from diffusion MRI data by Fisher vector descriptors
Pages :
119-126
Peer reviewed :
Peer reviewed
FnR Project :
FNR9169303 - Development Of Novel Machine Learning Methodologies For Early Parkinson's Disease Diagnosis From Multi-modal Mri, 2014 (01/03/2015-28/02/2017) - Luis Salamanca Miño
Name of the research project :
Development of Novel Machine Learning methodologies for early Parkin- son’s disease diagnosis from multi-modal MRI
Available on ORBilu :
since 14 February 2016

Statistics


Number of views
162 (10 by Unilu)
Number of downloads
236 (5 by Unilu)

Bibliography


Similar publications



Contact ORBilu