Radiomics Analysis of Magnetic Resonance Imaging Facilitates the Identification of Preclinical Alzheimer’s Disease: An Exploratory Study

Diagnosing Alzheimer’s disease (AD) in the preclinical stage offers opportunities for early intervention; however, there is currently a lack of convenient biomarkers. Using radiomics analysis, we aimed to determine whether the features extracted from multi-parametric magnetic resonance imaging (MRI) can be used as potential biomarkers. This study was part of the SILCODE project (NCT03370744), a prospective cohort study. All participants were cognitively healthy at baseline. Cohort 1 (n=183) was divided into individuals with preclinical AD (n=78) and controls (n=105) using amyloid-positron emission tomography, and was used as the training dataset (80%) and validation dataset (the remaining 20%); cohort 2 (n=51) was selected retrospectively and divided into ‘converters’ and ‘non-converters’ according to individuals’ future cognitive status, and was used as a separate test dataset; cohort 3 included 37 ‘converters’ (13 from the ADNI) and was used as another test set for independent longitudinal research. We extracted radiomics features from multi-parametric MRI from each participant, using t-tests, autocorrelation tests, and three independent selection algorithms. We then established two classification models (support vector machine [SVM] and random forest [RF]) to verify the efficiency of the retained features. Five-fold cross-validation and 100 repetitions were carried out for the above process. Furthermore, the acquired stable high-frequency features were tested in cohort 3 by paired two-sample t-tests and survival analyses to identify whether their levels changed with cognitive decline and impact conversion time. The SVM and RF models both showed excellent classification efficiency, with an average accuracy of 89.7–95.9% and 87.1–90.8% in the validation set, and 81.9–89.1% and 83.2–83.7% in the test set, respectively. Three stable high-frequency features were identified, all based on the structural MRI modality: Large zone high-gray-level emphasis feature of right posterior cingulate gyrus, Variance feature of left superior parietal gyrus, and Coarseness feature of left posterior cingulate gyrus; their levels were correlated with amyloid-β deposition and predicted future cognitive decline (AUCs 0.649–0.761). In addition, levels of the variance feature at baseline decreased with cognitive decline, and could affect the conversion time (p<0.05). In conclusion, this exploratory study shows that the radiomics features of multi-parametric MRI could represent potential biomarkers of preclinical AD.