Automated MR morphometry to predict Alzheimer's disease in mild cognitive impairment

Prediction of progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD) is challenging but essential for early treatment. This study aims to investigate the use of hippocampal atrophy markers for the automatic detection of MCI converters and to compare the predictive value to manually obtained hippocampal volume and temporal horn width.

A study was performed with 15 patients with Alzheimer and 18 patients with MCI (ten converted, eight remained stable in a 3-year follow-up) as well as 15 healthy subjects. MRI scans were obtained at baseline and evaluated with an automated system for scoring of hippocampal atrophy. The predictive value of the automated system was compared with manual measurements of hippocampal volume and temporal horn width in the same subjects.

The conversion to AD was correctly predicted in 77.8% of the cases (sensitivity 70%, specificity 87.5%) in the MCI group using automated morphometry and a plain linear classifier that was trained on the AD and healthy groups. Classification was improved by limiting analysis to the left cerebral hemisphere (accuracy 83.3%, sensitivity 70%, specificity 100%). The manual linear and volumetric approaches reached rates of 66.7% (40/100%) and 72.2% (60/87.5%), respectively.

The automatic approach fulfills many important preconditions for clinical application. Contrary to the manual approaches, it is not observer-dependent and reduces human resource requirements. Automated assessment may be useful for individual patient assessment and for predicting progression to dementia.