Predicting progression of mild cognitive impairment (MCI) to Alzheimer’s disease (AD) is clinically important. In this study, we propose a dual-model radiomic analysis with multivariate Cox proportional hazards regression models to investigate promising risk factors associated with MCI conversion to AD. T1 structural magnetic resonance imaging (MRI) and 18F-Fluorodeoxyglucose (FDG) positron emission tomography (PET) data, from the AD Neuroimaging Initiative database, were collected from 131 patients with MCI who converted to AD within 3 years and 132 patients with MCI without conversion within 3 years. These subjects were randomly partition into 70% training dataset and 30% test dataset with multiple times. We fused MRI and PET images by wavelet method. In a subset of subjects, a group comparison was performed using a two-sample t-test to determine regions of interest (ROIs) associated with MCI conversion. 172 radiomic features from ROIs for each individual were established using a published radiomics tool. Finally, L1-penalized Cox model was constructed and Harrell’s C index (C-index) was used to evaluate prediction accuracy of the model. To evaluate the efficacy of our proposed method, we used a same analysis framework to evaluate MRI and PET data separately. We constructed prognostic Cox models with: clinical data, MRI images, PET images, fused MRI/PET images, and clinical variables and fused MRI/PET images in combination. The experimental results showed that captured ROIs significantly associated with conversion to AD, such as gray matter atrophy in the bilateral hippocampus and hypometabolism in the temporoparietal cortex. Imaging model (MRI/PET/fused) provided significant enhancement in prediction of conversion compared to clinical models, especially the fused-modality Cox model. Moreover, the combination of fused-modality imaging and clinical variables resulted in the greatest accuracy of prediction. The average C-index for the clinical/MRI/PET/fused/combined model in the test dataset was 0.69, 0.73, 0.73 and 0.75, and 0.78, respectively. These results suggested that a combination of radiomic analysis and Cox model analyses could be used successfully in survival analysis and may be powerful tools for personalized precision medicine patients with potential to undergo conversion from MCI to AD.

Purpose Positron emission tomography (PET) with 18 F-fluorodeoxyglucose (FDG) reveals altered cerebral metabolism in individuals with mild cognitive impairment (MCI) and Alzheimer's dementia (AD). Previous metabolic connectome analyses derive from groups of patients but do not support the prediction of an individual's risk of conversion from present MCI to AD. We now present an individual metabolic connectome method, namely the Kullback-Leibler Divergence Similarity Estimation (KLSE), to characterize brain-wide metabolic networks that predict an individual's risk of conversion from MCI to AD. Methods FDG-PET data consisting of 50 healthy controls, 332 patients with stable MCI, 178 MCI patients progressing to AD, and 50 AD patients were recruited from ADNI database. Each individual's metabolic brain network was ascertained using the KLSE method. We compared intra-and intergroup similarity and difference between the KLSE matrix and group-level matrix, and then evaluated the network stability and inter-individual variation of KLSE. The multivariate Cox proportional hazards model and Harrell's concordance index (C-index) were employed to assess the prediction performance of KLSE and other clinical characteristics. Results The KLSE method captures more pathological connectivity in the parietal and temporal lobes relative to the typical group-level method, and yields detailed individual information, while possessing greater stability of network organization (within-group similarity coefficient, 0.789 for sMCI and 0.731 for pMCI). Metabolic connectome expression was a superior predictor of conversion than were other clinical assessments (hazard ratio (HR) = 3.55; 95% CI, 2.77-4.55; P < 0.001). The predictive performance improved further upon combining clinical variables in the Cox model, i.e., C-indices 0.728 (clinical), 0.730 (group-level pattern model), 0.750 (imaging connectome), and 0.794 (the combined model). This article is part of the Topical Collection on Advanced Image Analyses (Radiomics and Artificial Intelligence).

Background: Detecting subtle changes in visual attention from electroencephalography (EEG) and the perspective of eye movement in mild cognitive impairment (MCI) patients can be of great significance in screening early Alzheimer's disease (AD) in a large population at primary care. Objective: We proposed an automatic, non-invasive, and quick MCI detection approach based on multimodal physiological signals for clinical decision-marking. Methods: The proposed model recruited 152 patients with MCI and 184 healthy elderly controls (HC) who underwent EEG and eye movement signal recording under a visual stimuli task, as well as other neuropsychological assessments. Forty features were extracted from EEG and eye movement signals by linear and nonlinear analysis. The features related to MCI were selected by logistic regression analysis. To evaluate the efficacy of this MCI detection approach, we applied the same procedures to achieve the Clinical model, EEG model, Eye movement model, EEG+ Clinical model, Eye movement+ Clinical model, and Combined model, and compared the classification accuracy between the MCI and HC groups with the above six models. Results: After the penalization of logistic regression analysis, five features from EEG and eye movement features exhibited significant differences (p < 0.05). In the classification experiment, the combined model resulted in the best accuracy.

Objective: Accurate diagnosis of early Alzheimer disease (AD) plays a critical role in preventing the progression of memory impairment. We aimed to develop a new deep belief network (DBN) framework using 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) metabolic imaging to identify patients at the mild cognitive impairment (MCI) stage with presymptomatic AD and to discriminate them from other patients with MCI. Methods: 18F-fluorodeoxyglucose-PET images of 109 patients recruited in the ongoing longitudinal Alzheimer’s Disease Neuroimaging Initiative study were included in this analysis. Patients were grouped into 2 classes: (1) stable mild cognitive impairment (n = 62) or (2) progressive mild cognitive impairment (n = 47). Our framework is composed of 4 steps: (1) image preprocessing: normalization and smoothing; (2) identification of regions of interest (ROIs); (3) feature learning using deep neural networks; and (4) classification by support vector machine with 3 kernels. All classification experiments were performed with a 5-fold cross-validation. Accuracy, sensitivity, and specificity were used to validate the results. Result: A total of 1103 ROIs were obtained. One hundred features were learned from ROIs using the DBN. The classification accuracy using linear, polynomial, and RBF kernels was 83.9%, 79.2%, and 86.6%, respectively. This method may be a powerful tool for personalized precision medicine in the population with prediction of early AD progression.

No abstract