2 items tagged with 'voxel-based morphometry'.
Predicting behavioral variant frontotemporal dementia with pattern classification in multi-center structural MRI data.
PURPOSE: Frontotemporal lobar degeneration (FTLD) is a common cause of early onset dementia. Behavioral variant frontotemporal dementia (bvFTD), its most common subtype, is characterized by deep … alterations in behavior and personality. In 2011, new diagnostic criteria were suggested that incorporate imaging criteria into diagnostic algorithms. The study aimed at validating the potential of imaging criteria to individually predict diagnosis with machine learning algorithms. MATERIALS & METHODS: Brain atrophy was measured with structural magnetic resonance imaging (MRI) at 3 Tesla in a multi-centric cohort of 52 bvFTD patients and 52 healthy control subjects from the German FTLD Consortium's Study. Beside group comparisons, diagnosis bvFTD vs. controls was individually predicted in each subject with support vector machine classification in MRI data across the whole brain or in frontotemporal, insular regions, and basal ganglia known to be mainly affected based on recent meta-analyses. Multi-center effects were controlled for with a new method, "leave one center out" conjunction analyses, i.e. repeatedly excluding subjects from each center from the analysis. RESULTS: Group comparisons revealed atrophy in, most consistently, the frontal lobe in bvFTD beside alterations in the insula, basal ganglia and temporal lobe. Most remarkably, support vector machine classification enabled predicting diagnosis in single patients with a high accuracy of up to 84.6%, where accuracy was highest in a region-of-interest approach focusing on frontotemporal, insular regions, and basal ganglia in comparison with the whole brain approach. CONCLUSION: Our study demonstrates that MRI, a widespread imaging technology, can individually identify bvFTD with high accuracy in multi-center imaging data, paving the road to personalized diagnostic approaches in the future.
Authors: S. Meyer, K. Mueller, K. Stuke, S. Bisenius, J. Diehl-Schmid, F. Jessen, J. Kassubek, J. Kornhuber, A. C. Ludolph, J. Prudlo, A. Schneider, K. Schuemberg, I. Yakushev, M. Otto, M. L. Schroeter
Date Published: 29th Mar 2017
Publication Type: Journal article
Human Diseases: frontotemporal dementia
PubMed ID: 28348957
Citation: Neuroimage Clin. 2017 Feb 6;14:656-662. doi: 10.1016/j.nicl.2017.02.001. eCollection 2017.
Created: 13th May 2019 at 10:22, Last updated: 7th Dec 2021 at 17:58
Impact of image acquisition on voxel-based-morphometry investigations of age-related structural brain changes.
A growing number of magnetic resonance imaging studies employ voxel-based morphometry (VBM) to assess structural brain changes. Recent reports have shown that image acquisition parameters may influence … VBM results. For systematic evaluation, gray-matter-density (GMD) changes associated with aging were investigated by VBM employing acquisitions with different radiofrequency head coils (12-channel matrix coil vs. 32-channel array), different pulse sequences (MP-RAGE vs. MP2RAGE), and different voxel dimensions (1mm vs. 0.8mm). Thirty-six healthy subjects, classified as young, middle-aged, or elderly, participated in the study. Two-sample and paired t-tests revealed significant effects of acquisition parameters (coil, pulse sequence, and resolution) on the estimated age-related GMD changes in cortical and subcortical regions. Potential advantages in tissue classification and segmentation were obtained for MP2RAGE. The 32-channel coil generally outperformed the 12-channel coil, with more benefit for MP2RAGE. Further improvement can be expected from higher resolution if the loss in SNR is accounted for. Use of inconsistent acquisition parameters in VBM analyses is likely to introduce systematic bias. Overall, acquisition and protocol changes require careful adaptations of the VBM analysis strategy before generalized conclusion can be drawn.
Authors: D. P. Streitburger, A. Pampel, G. Krueger, J. Lepsien, M. L. Schroeter, K. Mueller, H. E. Moller
Date Published: 15th Feb 2014
Publication Type: Not specified
PubMed ID: 24188812
Citation: Neuroimage. 2014 Feb 15;87:170-82. doi: 10.1016/j.neuroimage.2013.10.051. Epub 2013 Nov 2.
Created: 9th May 2019 at 08:37, Last updated: 7th Dec 2021 at 17:58