Send to

Choose Destination
Neuroimage. 2018 Sep;178:753-768. doi: 10.1016/j.neuroimage.2018.05.065. Epub 2018 Jun 2.

A comparison of various MRI feature types for characterizing whole brain anatomical differences using linear pattern recognition methods.

Author information

FIDMAG Germanes Hospitalàries Research Foundation, Avda. Jordà 8, 08035, Barcelona, Spain; Fundació ACE. Institut Català de Neurociències Aplicades, Marqués de Sentmenat 57, 08029, Barcelona, Spain. Electronic address:
Barcelonaβeta Brain Research Center, Pasqual Maragall Foundation. Barcelona, Carrer de Wellington 30, 08005, Barcelona, Spain; CIBER en Bioingenieria, Biomateriales y Nanomedicina (CIBER-BBN), Spain. Electronic address:
FIDMAG Germanes Hospitalàries Research Foundation, Avda. Jordà 8, 08035, Barcelona, Spain. Electronic address:
Wellcome Centre for Human Neuroimaging, UCL Institute of Neurology, 12 Queen Square, London, WC1N 3BG, UK. Electronic address:


There is a widespread interest in applying pattern recognition methods to anatomical neuroimaging data, but so far, there has been relatively little investigation into how best to derive image features in order to make the most accurate predictions. In this work, a Gaussian Process machine learning approach was used for predicting age, gender and body mass index (BMI) of subjects in the IXI dataset, as well as age, gender and diagnostic status using the ABIDE and COBRE datasets. MRI data were segmented and aligned using SPM12, and a variety of feature representations were derived from this preprocessing. We compared classification and regression accuracy using the different sorts of features, and with various degrees of spatial smoothing. Results suggested that feature sets that did not ignore the implicit background tissue class, tended to result in better overall performance, whereas some of the most commonly used feature sets performed relatively poorly.


Diffeomorphism; Gaussian process; Model selection; Pattern recognition; Scalar momentum; Structural MRI; VBM

[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Elsevier Science Icon for PubMed Central
Loading ...
Support Center