Sensitivity and specificity of medial temporal lobe visual ratings and multivariate regional MRI classification in Alzheimer's disease

Abstract

Background: Visual assessment rating scales for medial temporal lobe (MTL) atrophy have been used by neuroradiologists in clinical practice to aid the diagnosis of Alzheimer's disease (AD). Recently multivariate classification methods for magnetic resonance imaging (MRI) data have been suggested as alternative tools. If computerized methods are to be implemented in clinical practice they need to be as good as, or better than experienced neuroradiologists and carefully validated. The aims of this study were: (1) To compare the ability of MTL atrophy visual assessment rating scales, a multivariate MRI classification method and manually measured hippocampal volumes to distinguish between subjects with AD and healthy elderly controls (CTL). (2) To assess how well the three techniques perform when predicting future conversion from mild cognitive impairment (MCI) to AD.

Methods: High resolution sagittal 3D T1w MP-RAGE datasets were acquired from 75 AD patients, 101 subjects with MCI and 81 CTL from the multi-centre AddNeuroMed study. An automated analysis method was used to generate regional volume and regional cortical thickness measures, providing 57 variables for multivariate analysis (orthogonal partial least squares to latent structures using seven-fold cross-validation). Manual hippocampal measurements were also determined for each subject. Visual rating assessment of MTL atrophy was performed by an experienced neuroradiologist according to the approach of Scheltens et al.

Results: We found prediction accuracies for distinguishing between AD and CTL of 83% for multivariate classification, 81% for the visual rating assessments and 89% for manual measurements of total hippocampal volume. The three different techniques showed similar accuracy in predicting conversion from MCI to AD at one year follow-up.

Conclusion: Visual rating assessment of the MTL gave similar prediction accuracy to multivariate classification and manual hippocampal volumes. This suggests a potential future role for computerized methods as a complement to clinical assessment of AD.

Figure 1. Representations of ROIs included as candidate input variables in the multivariate OPLS model.

(A) Regional volumes. (B) Regional cortical thickness measures.

Figure 2. Visual assessment of the medial temporal lobe atrophy was performed on a single MR-slice posterior to the amygdala and the mamillary bodies.

The was positioned so the hippocampus, the pons and the cerebral peduncles were all visible. The visual assessment included hippocampus proper, dentate gyrus, subiculum, parahippocampal gyrus, entorhinal cortex and surrounding CSF spaces such as temporal horn and choroid fissure. The right and left side were rated separately. Scores range from 0 (no atrophy) to 4 (end stage atrophy).

Figure 3. OPLS cross validated score plots and MRI measures of importance for the separation between AD and CTL.

(A) The scatter plot visualises group separation and the predictability of the AD vs. CTL model. Each black square represents an AD subject and each gray circle a control subject. Control subjects to the left of zero and AD subjects to the right of zero are falsely predicted. Q²(Y)>0.05 (statistically significant model). (B) Measures above zero have a larger value in controls compared to AD and measures below zero have a lower value in controls compared to AD. A measure with a high covariance is more likely to have an impact on group separation than a measure with a low covariance. Measures with jack knifed confidence intervals that include zero have low reliability.