Automated Hippocampal Subfield Measures as Predictors of Conversion from Mild Cognitive Impairment to Alzheimer’s Disease in Two Independent Cohorts

Abstract

Previous studies have shown that hippocampal subfields may be differentially affected by Alzheimer’s disease (AD). This study used an automated analysis technique and two large cohorts to (1) investigate patterns of subfield volume loss in mild cognitive impairment (MCI) and AD, (2) determine the pattern of subfield volume loss due to age, gender, education, APOE ε4 genotype, and neuropsychological test scores, (3) compare combined subfield volumes to hippocampal volume alone at discriminating between AD and healthy controls (HC), and predicting future MCI conversion to AD at 12 months. 1,069 subjects were selected from the AddNeuroMed and Alzheimer’s disease neuroimaging initiative (ADNI) cohorts. Freesurfer was used for automated segmentation of the hippocampus and hippocampal subfields. Orthogonal partial least squares to latent structures (OPLS) was used to train models on AD and HC subjects using one cohort for training and the other for testing and the combined cohort was used to predict MCI conversion. MANCOVA and linear regression analyses showed multiple subfield volumes including Cornu Ammonis 1 (CA1), subiculum and presubiculum were atrophied in AD and MCI and were related to age, gender, education, APOE ε4 genotype, and neuropsychological test scores. For classifying AD from HC, combined subfield volumes achieved comparable classification accuracy (81.7 %) to total hippocampal (80.7 %), subiculum (81.2 %) and presubiculum (80.6 %) volume. For predicting MCI conversion to AD combined subfield volumes and presubiculum volume were more accurate (81.1 %) than total hippocampal volume. (76.7 %).

The Role of MRI Biomarkers and Their Interactions with Cognitive Status and APOE ε4 in Nondemented Elderly Subjects

“…There were significant positive correlations between the neuropsychological tests, like MocA, and the subfield volumes. These results were also consistent with previous studies [17, 23, 42] and indicated that atrophy may be associated with cognitive impairment. All of these results confirmed that the Chinese AD population has a quite similar atrophy pattern to the previously reported Caucasian results.…”

“…In our study, we found a significant reduction in the bilateral hippocampal subfield volume in MCI patients, which replicated previous studies [3, 17, 23, 33–35]. Four subfields of the hippocampus were significantly different between the MCI and NC groups (FDR corrected), indicating that atrophy of the left presubiculum/subiculum and right CA2_3 and CA4_DG volume may be a more powerful biomarker for MCI than other hippocampal subfields.…”

“…One possible reason is the genotypes. For example, many studies have shown that the APOE ε4 gene affects the hippocampal subfields and cortical thickness in AD and MCI [23, 24]. APOE ε4 allele carriers have shown smaller hippocampal subfields [15, 25, 26] and cortical thickness [24, 27].…”

The Worldwide Alzheimer's Disease Neuroimaging Initiative: An update

“…In the first case, the classifier performed with 84% sensitivity and 91% specificity, and its prediction of conversion from MCI to AD at 12 months was 91% [60]. The combination of the hippocampal subfields volumes achieved an AD/HC classification accuracy of 82% and a prediction accuracy of 81% [61].…”

“…Two other efforts used orthogonal partial least squares to latent structures, a multivariate analysis technique, to classify subjects with AD and HC. The classifier models involved cortical thickness measures and subcortical volumes in the first study [60] and hippocampal subfield volumes in the second study [61]. In the first case, the classifier performed with 84% sensitivity and 91% specificity, and its prediction of conversion from MCI to AD at 12 months was 91% [60].…”