An MRI‐based index to measure the severity of Alzheimer's disease‐like structural pattern in subjects with mild cognitive impairment

Abstract

Background Structural magnetic resonance imaging (MRI) is sensitive to neurodegeneration and can be used to estimate the risk of converting to Alzheimer’s disease (AD) in individuals with mild cognitive impairment (MCI). Brain changes in AD and prodromal AD involve a pattern of widespread atrophy. The use of multivariate analysis algorithms could enable the development of diagnostic tools based on structural MRI data. In this study we investigated the possibility of combining multiple MRI features in the form of a severity index. Methods We used baseline MRI scans from two large multicentre cohorts (AddNeuroMed and ADNI). Based on volumetric and cortical thickness measures at baseline with AD cases and healthy control (CTL) subjects as training sets, we generated an MRI-based severity index using the method of orthogonal projection to latent structures (OPLS). The severity index tends to be close to 1 for AD patients and 0 for CTL subjects. Values above 0.5 indicate a more AD-like pattern. The index was then estimated for subjects with MCI, and the accuracy of classification was investigated. Results Based on the data at follow-up, 173 subjects converted to AD, of whom 112 (64.7%) were classified as AD-like and 61 (35.3%) as CTL-like. Conclusion We found that joint evaluation of multiple brain regions provided accurate discrimination between progressive and stable MCI, with better performance than hippocampal volume alone, or a limited set of features. A major challenge is still to determine optimal cut-off points for such parameters and to compare their relative reliability.

Measuring Global Brain Atrophy with the Brain Volume/Cerebrospinal Fluid Index: Normative Values, Cut-Offs and Clinical Associations

“…A lower BV/CSF index at baseline correlated with increased disease severity and global cognitive impairment, in line with previous studies [4,14,15,19,20,21,22,23]. Further, the index also correlated with domain-specific cognitive measurements at baseline.…”

“…Interestingly, we found a significant interaction showing faster atrophy over 1 year in AD and MCI-C patients as compared with MCI-S patients and controls. Previous studies have investigated global brain atrophy in AD, MCI and control groups [15,16,17,18,19,20,22,23], but the only study that tested for the same interaction did not find a significant effect [19]. …”

“…Alzheimer patients have greater brain atrophy than MCI patients, and both have greater atrophy than cognitively normal controls [4,15,16,17,18,40]. The gradient of global brain atrophy was reflected by the BV/CSF index (AD > MCI-C > MCI-S > controls).…”

“…Some studies have investigated associations with CSF biomarkers and cognition [4,14,15,18,19,20,21,22,23,24,25,26,27,28,29,30]. However, an important limitation that obstructs the use of measurements of global brain atrophy in clinical practice is the lack of normative values for interpretation.…”

“…All methods mentioned above have identified a gradient of global brain atrophy of AD > mild cognitive impairment (MCI) > healthy controls [4,14,15,16,17,18]. Some studies have investigated associations with CSF biomarkers and cognition [4,14,15,18,19,20,21,22,23,24,25,26,27,28,29,30].…”