Finding very early biomarkers of Alzheimer's Disease (AD) to aid in individual prognosis is of major interest to accelerate the development of new therapies. Among the potential biomarkers, neurodegeneration measurements from MRI are considered as good candidates but have so far not been effective at the early stages of the pathology. Our objective is to investigate the efficiency of a new MR-based hippocampal grading score to detect incident dementia in cognitively intact patients. This new score is based on a pattern recognition strategy, providing a grading measure that reflects the similarity of the anatomical patterns of the subject under study with dataset composed of healthy subjects and patients with AD. Hippocampal grading was evaluated on subjects from the Three-City cohort, with a followup period of 12 years. Experiments demonstrate that hippocampal grading yields prediction accuracy up to 72.5% (P < 0.0001) 7 years before conversion to AD, better than both hippocampal volume (58.1%, P = 0.04) and MMSE score (56.9%, P = 0.08). The area under the ROC curve (AUC) supports the efficiency of imaging biomarkers with a gain of 8.4 percentage points for hippocampal grade (73.0%) over hippocampal volume (64.6%). Adaptation of the proposed framework to clinical score estimation is also presented. Compared with previous studies investigating new biomarkers for AD prediction over much shorter periods, the very long followup of the Three-City cohort demonstrates the important clinical potential of the proposed imaging biomarker. The high accuracy obtained with this new imaging biomarker paves the way for computer-based prognostic aides to help the clinician identify cognitively intact subjects that are at high risk to develop AD.

The hippocampus is one of the first brain structures affected by Alzheimer's disease (AD). While many automatic methods for hippocampal segmentation exist, few studies have compared them on the same data. In this study, we compare four fully automated hippocampal segmentation methods in terms of their conformity with manual segmentation and their ability to be used as an AD biomarker in clinical settings. We also apply error correction to the four automatic segmentation methods, and complete a comprehensive validation to investigate differences between the methods. The effect size and classification performance is measured for AD versus normal control (NC) groups and for stable mild cognitive impairment (sMCI) versus progressive mild cognitive impairment (pMCI) groups. Our study shows that the nonlinear patch-based segmentation method with error correction is the most accurate automatic segmentation method and yields the most conformity with manual segmentation (κ=0.894). The largest effect size between AD versus NC and sMCI versus pMCI is produced by FreeSurfer with error correction. We further show that, using only hippocampal volume, age, and sex as features, the area under the receiver operating characteristic curve reaches up to 0.8813 for AD versus NC and 0.6451 for sMCI versus pMCI. However, the automatic segmentation methods are not significantly different in their performance.

No abstract