The EADC-ADNI harmonized protocol for hippocampal segmentation: A validation study.

Recently, a group of major international experts have completed a comprehensive effort to efficiently define a harmonized protocol for manual hippocampal segmentation that is optimized for Alzheimer's research (known as the EADC-ADNI Harmonized Protocol (the HarP)). This study compares the HarP with one of the widely used hippocampal segmentation protocols (Pruessner, 2000), based on a single automatic segmentation method trained separately with libraries made from each manual segmentation protocol. The automatic segmentation conformity with the corresponding manual segmentation and the ability to capture Alzheimer's disease related hippocampal atrophy on large datasets are measured to compare the manual protocols. In addition to the possibility of harmonizing different procedures of hippocampal segmentation, our results show that using the HarP, the automatic segmentation conformity with manual segmentation is also preserved (Dice's κ=0.88,κ=0.87 for Pruessner and HarP respectively (p = 0.726 for common training library)). Furthermore, the results show that the HarP can capture the Alzheimer's disease related hippocampal volume differences in large datasets. The HarP-derived segmentation shows large effect size (Cohen's d = 1.5883) in separating Alzheimer's Disease patients versus normal controls (AD:NC) and medium effect size (Cohen's d = 0.5747) in separating stable versus progressive Mild Cognitively Impaired patients (sMCI:pMCI). Furthermore, the area under the ROC curve for a LDA classifier trained based on age, sex and HarP-derived hippocampal volume is 0.8858 for AD:NC, and for 0.6677 sMCI:pMCI. These results show that the harmonized protocol-derived labels can be widely used in clinic and research, as a sensitive and accurate way of delineating the hippocampus.

A comparison of accurate automatic hippocampal segmentation methods.

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.

Detection of Alzheimer's disease signature in MR images seven years before conversion to dementia: Toward an early individual prognosis.

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.

MRI and cognitive scores complement each other to accurately predict Alzheimer's dementia 2 to 7 years before clinical onset.

BACKGROUND: Predicting cognitive decline and the eventual onset of dementia in patients with Mild Cognitive Impairment (MCI) is of high value for patient management and potential cohort enrichment in pharmaceutical trials. We used cognitive scores and MRI biomarkers from a single baseline visit to predict the onset of dementia due to AD in an amnestic MCI (aMCI) population over a nine-year follow-up period. METHOD: All aMCI subjects from ADNI1, ADNI2, and ADNI-GO with available baseline neurocognitive scores and T1w MRI were included in the study (n = 756). We built a Naïve Bayes classifier for every year over a 9-year follow-up period and tested each one with Leave one out cross validation. RESULTS: We reached 87% prediction accuracy at five years follow-up with an AUC > 0.85 from two to seven years (peaking at 0.92 at five years). Both neurocognitive scores and MRI biomarkers were needed to make the prognostic models highly sensitive and specific, especially for longer follow-ups. MRI features are more sensitive, while cognitive features bring specificity to the prediction. CONCLUSION: Combining cognitive scores and MRI biomarkers yield accurate prediction years before onset of dementia. Such a tool may be helpful in selecting patients that would most benefit from lifestyle changes, and eventually early treatments that would slow cognitive decline and delay the onset of dementia.