Title | ||
---|---|---|
Improved Parkinson’s Disease Classification from Diffusion MRI Data by Fisher Vector Descriptors |
Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/978-3-319-24571-3_15 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
neurodegenerative diseases,diagnosis,diffusion magnetic resonance imaging,machine learning,feature extraction | Linear separability,Feature vector,Diffusion MRI,Pattern recognition,Computer science,Fractional anisotropy,Curse of dimensionality,Feature extraction,Artificial intelligence,Encoding (memory),Magnetic resonance imaging | Conference |
Volume | ISSN | Citations |
9350 | 0302-9743 | 1 |
PageRank | References | Authors |
0.35 | 5 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Luis Salamanca | 1 | 28 | 5.63 |
Nikos A. Vlassis | 2 | 2050 | 158.24 |
Nico Diederich | 3 | 1 | 0.35 |
Florian Bernard | 4 | 118 | 14.54 |
Alexander Skupin | 5 | 8 | 2.58 |