Automated hippocampal shape analysis predicts the onset of dementia in mild cognitive impairment

Abstract

The hippocampus is involved at the onset of the neuropathological pathways leading to Alzheimer’s disease (AD). Individuals with Mild Cognitive Impairment (MCI) are at increased risk of AD. Hippocampal volume has been shown to predict which MCI subjects will convert to AD. Our aim in the present study was to produce a fully automated prognostic procedure, scalable to high throughput clinical and research applications, for the prediction of MCI conversion to AD using 3D hippocampal morphology. We used an automated analysis for the extraction and mapping of the hippocampus from structural magnetic resonance scans to extract 3D hippocampal shape morphology, and we then applied machine learning classification to predict conversion from MCI to AD. We investigated the accuracy of prediction in 103 MCI subjects (mean age 74.1 years) from the longitudinal AddNeuroMed study. Our model correctly predicted MCI conversion to dementia within a year at an accuracy of 80% (sensitivity 77%, specificity 80%), a performance which is competitive with previous predictive models dependent on manual measurements. Categorization of MCI subjects based on hippocampal morphology revealed more rapid cognitive deterioration in MMSE scores (p < 0.01) and CERAD verbal memory (p < 0.01) in those subjects who were predicted to develop dementia relative to those predicted to remain stable. The pattern of atrophy associated with increased risk of conversion demonstrated initial degeneration in the anterior part of the cornus ammonis 1 (CA1) hippocampal subregion. We conclude that automated shape analysis generates sensitive measurements of early neurodegeneration which predates the onset of dementia and thus provides a prognostic biomarker for conversion of MCI to AD.

Automated Segmentation of Hippocampal Subfields in Drug-Naïve Patients with Alzheimer Disease

“…6 However, these results were not in line with those in previous studies using the manual segmentation of hippocampal subfields or 3D surface mapping of the hippocampus. 5,22 As to this discrepancy, Hanseeuw et al suggested that there was a boundary difference between the studies and possible CA1 hypertrophy in aMCI. They also suggested that the reproducibility of their method would permit more consistency between studies than was possible with manual methods.…”

Using neuroimaging to help predict the onset of psychosis

“…It is also possible to use the results of previous research to limit predictive models to regions of interest 70 , although this relies on the assumption that findings from mass univariate approaches are applicable to a multi-variate analyses.…”

An Overview of Quantitative Magnetic Resonance Imaging Analysis Studies in the Assessment of Alzheimer’s Disease

“…Global hippocampal volume may not be the most accurate technique for the prediction of conversion from MCI to AD and for the classification of MCI patients. Shape analysis appears to be a more sensitive measure than volume analysis for the assessment of AD [20], [24].…”

“…In a recent study, Costafreda et al, [24] used a fully automated procedure to extract 3D hippocampal shape morphology in order to predict conversion from MCI to AD. Their predicting model had an accuracy of 80% (sensitivity 77%, and specificity 80%) which was competitive with other predictive models which used non automated measurements.…”