Automatic morphometry in Alzheimer's disease and mild cognitive impairment

Abstract

This paper presents a novel, publicly available repository of anatomically segmented brain images of healthy subjects as well as patients with mild cognitive impairment and Alzheimer's disease. The underlying magnetic resonance images have been obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. T1-weighted screening and baseline images (1.5 T and 3 T) have been processed with the multi-atlas based MAPER procedure, resulting in labels for 83 regions covering the whole brain in 816 subjects. Selected segmentations were subjected to visual assessment. The segmentations are self-consistent, as evidenced by strong agreement between segmentations of paired images acquired at different field strengths (Jaccard coefficient: 0.802 ± 0.0146). Morphometric comparisons between diagnostic groups (normal; stable mild cognitive impairment; mild cognitive impairment with progression to Alzheimer's disease; Alzheimer's disease) showed highly significant group differences for individual regions, the majority of which were located in the temporal lobe. Additionally, significant effects were seen in the parietal lobe. Increased left/right asymmetry was found in posterior cortical regions. An automatically derived white-matter hypointensities index was found to be a suitable means of quantifying white-matter disease. This repository of segmentations is a potentially valuable resource to researchers working with ADNI data.

Magnetization-prepared rapid acquisition with gradient echo magnetic resonance imaging signal and texture features for the prediction of mild cognitive impairment to Alzheimer’s disease progression

“…Magnetization-prepared rapid acquisition with gradient echo (MP-RAGE) images and their corresponding segmentation masks were downloaded. The segmentation masks were provided by Heckemann et al 13 using multiatlas propagation enhanced registration, an automatic whole-brain multiregion segmentation method. In order to continue studying the same population as in previous works, 14 only data and images uploaded up to June 2012 were considered.…”

Quantitative MRI Brain Studies in Mild Cognitive Impairment and Alzheimer's Disease: A Methodological Review

“…It is also noted that are very few studies [30], [129] that combine volume, thickness, shape, intensity, and texture in multivariate assessment of the disease, which in turn may result to better classification and prediction accuracies. Martinez Torteya et al [80] used images from the ADNI database with their corresponding segmentation masks, provided by [147], to establish ROIs for every image. For each ROI they used 9 texture-related features together with 13 morphometrical features and 28 signal distribution related features.…”

Initial Evaluation of 18F-GE-179, a Putative PET Tracer for Activated N-Methyl d-Aspartate Receptors

“…An 83-region gray matter-only region-of-interest (ROI) map was produced for each of the 9 participants by transformation of 30 manually created atlases (19) to the participant's native MR imaging space using multiatlas propagation with enhanced registration and decision fusion (20). The resulting atlas was then multiplied by the thresholded gray matter component of the MR image and used to sample the radioactivity concentration (KBq/mL) in each of the 83 regions.…”