No abstract

Background: Alzheimer’s disease (AD) is the most common form of progressive and irreversible dementia, and accurate diagnosis of AD at its prodromal stage is clinically important. Currently, computer-aided diagnosis of AD and mild cognitive impairment (MCI) using 18F-fluorodeoxy-glucose positron emission tomography (18F-FDG PET) imaging is usually based on low-level imaging features or deep learning methods, which have difficulties in achieving sufficient classification accuracy or lack clinical significance. This research therefore aimed to implement a new feature extraction method known as radiomics, to improve the classification accuracy and discover high-order features that can reveal pathological information. Methods: In this study, 18F-FDG PET and clinical assessments were collected in a cohort of 422 individuals [including 130 with AD, 130 with MCI, and 162 healthy controls (HCs)] from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and 44 individuals (including 22 with AD, and 22 HCs) from Huashan Hospital, Shanghai, China. First, we performed a group comparison using a two-sample Student’s t test to determine the regions of interest (ROIs) based on 30 AD patients and 30 HCs from ADNI cohorts. Second, based on two time scans of 32 HCs from ADNI cohorts, we used Cronbach’s alpha coefficient for radiomic feature stability analyses. Pearson’s correlation coefficients were regarded as a feature selection criterion, to select effective features associated with the clinical cognitive scale [clinical dementia rating scale in its sum of boxes (CDRSB); Alzheimer’s disease assessment scale (ADAS)] with 500-times cross-validation. Finally, a support vector machine (SVM) was used to test the ability of the radiomic features to classify HCs, MCI and AD patients. Results: As a result, we identified brain regions which were mainly distributed in the temporal, occipital and frontal areas as ROIs. A total of 168 radiomic features of AD were stable (alpha > 0.8). The classification experiment led to maximal accuracies of 91.5%, 83.1% and 85.9% for classifying AD versus HC, MCI versus HCs and AD versus MCI. Conclusion: The research in this paper proved that the novel approach based on high-order radiomic features extracted from 18F-FDG PET brain images that can be used for AD and MCI computer-aided diagnosis.

No abstract

No abstract

Diagnosing Alzheimer’s disease (AD) in the preclinical stage offers opportunities for early intervention; however, there is currently a lack of convenient biomarkers to facilitate the diagnosis. Using radiomics analysis, we aimed to determine whether the features extracted from multiparametric magnetic resonance imaging (MRI) can be used as potential biomarkers. This study was part of the Sino Longitudinal Study on Cognitive Decline 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 this cohort 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 “nonconverters” according to individuals’ future cognitive status, and this cohort was used as a separate test dataset; cohort three included 37 converters (13 from the Alzheimer’s Disease Neuroimaging Initiative) and was used as another test set for independent longitudinal research. We extracted radiomics features from multiparametric MRI scans 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 three 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: the large zone high-gray-level emphasis feature of the right posterior cingulate gyrus, the variance feature of the left superior parietal gyrus, and the coarseness feature of the left posterior cingulate gyrus; their levels were correlated with amyloid-β deposition and predicted future cognitive decline (areas under the curve 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 multiparametric MRI scans could represent potential biomarkers of preclinical AD.