Radiomic Features of Hippocampal Subregions in Alzheimer’s Disease and Amnestic Mild Cognitive Impairment

• Published in: Frontiers in aging neuroscience Vol. 10; p. 290
• Main Authors: Feng, Feng, Wang, Pan, Zhao, Kun, Zhou, Bo, Yao, Hongxiang, Meng, Qingqing, Wang, Lei, Zhang, Zengqiang, Ding, Yanhui, Wang, Luning, An, Ningyu, Zhang, Xi, Liu, Yong
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 25.09.2018; Frontiers Media S.A
• Subjects: Alzheimer's disease; amnestic mild cognitive impairment; Atrophy; Automation; Biomarkers; Classification; Cognitive ability; Dementia; Dementia disorders; Disease; hippocampal subregions; Hippocampus; Hospitals; Magnetic resonance imaging; Memory; Morphology; Neurology; Neuroscience; NMR; Nuclear magnetic resonance; Patients; radiomic features; Radiomics; Statistical analysis; support vector machine; Therapeutic applications; Beijing China; China; alzheimer’s disease; radiomic features; hippocampal subregions; support vector machine; amnestic mild cognitive impairment
• ISSN: 1663-4365; 1663-4365
• DOI: 10.3389/fnagi.2018.00290

Alzheimer's disease (AD) is characterized by progressive dementia, especially in episodic memory, and amnestic mild cognitive impairment (aMCI) is associated with a high risk of developing AD. Hippocampal atrophy/shape changes are believed to be the most robust magnetic resonance imaging (MRI) markers for AD and aMCI. Radiomics, a method of texture analysis, can quantitatively examine a large set of features and has previously been successfully applied to evaluate imaging biomarkers for AD. To test whether radiomic features in the hippocampus can be employed for early classification of AD and aMCI, 1692 features from the caudal and head parts of the bilateral hippocampus were extracted from 38 AD patients, 33 aMCI patients and 45 normal controls (NCs). One way analysis of variance (ANOVA) showed that 111 features exhibited statistically significant group differences ( < 0.01, Bonferroni corrected). Among these features, 98 were significantly correlated with Mini-Mental State Examination (MMSE) scores in AD and aMCI subjects ( < 0.01). The support vector machine (SVM) model demonstrated that radiomic features allowed us to distinguish AD from NC with an accuracy of 86.75% (specificity = 88.89% and sensitivity = 84.21%) and an area under curve (AUC) of 0.93. In conclusion, these findings provide evidence showing that radiomic features are beneficial in detecting early cognitive decline, and SVM classification analysis provides encouraging evidence for using hippocampal radiomic features as a potential biomarker for clinical applications in AD.