Lookup NU author(s): Dr Luis Peraza Rodriguez,
Dr John-Paul Taylor,
Professor Marcus Kaiser
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
Predicting brain maturity using noninvasive magnetic resonance images (MRI) can distinguish different age groups and help to assess neurodevelopmental disorders. However, group-wise differences are often less informative for assessing features of individuals. Here, we propose a simple method to predict the age of an individual subject solely based on structural connectivity data from diffusion tensor imaging (DTI). Our simple predictor computes a weighted sum of connection strengths of an individual, where weights are the importance of that connection for an observed feature—age in this case. The weights are simply determined through correlations between connection strength and age; thus the proposed predictor requires no parameter tuning. We tested this approach using DTI data from 201 healthy subjects aged 4 to 85 years. After determining importance in a training dataset, our predicted ages in the test dataset showed a strong correlation (r = 0.79) with real age deviating by, on average, only about 9 years.
Author(s): Han CE, Peraza LR, Taylor J-P, Kaiser M
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: 2014 IEEE Biomedical Circuits and Systems Conference (BioCAS)
Year of Conference: 2014
Online publication date: 11/12/2014
Acceptance date: 01/01/1900
Library holdings: Search Newcastle University Library for this item