Hippocampal Subregions Volume and Texture for the Diagnosis of Mild Cognitive Impairment

Abstract

Abstract Purpose: The aim of this study was to examine the diagnostic efficacy of hippocampal subregions volume and texture in differentiating amnestic mild cognitive impairment (MCI) from normal aging changes. Materials and Methods: Ninety MCI subjects and eighty-eight well-matched healthy controls (HCs) were selected from the ADNI-1 or ADNI-2 Database.Twelve hippocampal subregions volume and texture features were extracted using Freesurfer and MaZda based on T1 weighted magnetic resonance images. Then, two-sample t-test and Least Absolute Shrinkage and Selection Operator (LASSO) regression were developed to select a subset of the original features. Finally, a support vector machine (SVM) was used to perform the classification task and the area under the curve (AUC), sensitivity, specificity, and accuracy were calculated to evaluate the diagnostic efficacy of the model. Results: The volume features with high discriminative power were mainly located in the bilateral CA1 and bilateral CA4, while texture feature were gray-level non-uniformity, run length non-uniformity and fraction. Our model based on hippocampal subregions volume and texture features achieved better classification performance with an AUC of 0.90. Conclusions: Based on hippocampal subregions volume and texture can be used to diagnose MCI. Moreover, we found that the features that contributed most to the model were mainly textural features, followed by volume. These results may guide future studies using structural scans to classify patients with MCI.