Abstract
BACKGROUND: This study aimed to explore the potential of a combination of 18F-fluorodeoxyglucose positron emission tomography ((18)F-FDG PET) and magnetic resonance imaging (MRI) to improve predictions of conversion from mild cognitive impairment (MCI) to Alzheimer's disease (AD). The predictive performances and specific associated biomarkers of these imaging techniques used alone (single-modality imaging) and in combination (dual-modality imaging) were compared. METHODS: This study enrolled 377 patients with MCI and 94 healthy control participants from 2 medical centers. Enrolment was based on the patients' brain MRI and PET images. Radiomic analysis was performed to evaluate the predictive performance of dual-modality (18)F-FDG PET and MRI scans. Regions of interest (ROIs) were determined using an a priori brain atlas. Radiomic features in these ROIs were extracted from the MRI and (18)F-FDG PET scan data. These features were either concatenated or used separately to select features and construct Cox regression models for prediction in each modality. Harrell's concordance index (C-index) was then used to assess the predictive accuracies of the resulting models, and correlations between the MRI and (18)F-FDG PET features were evaluated. RESULTS: The C-indices for the two test datasets were 0.77 and 0.80 for dual-modality (18)F-FDG PET/MRI, 0.75 and 0.73 for single-modality (18)F-FDG PET, and 0.74 and 0.76 for single-modality MRI. In addition, there was a significant correlation between the crucial image signatures of the different modalities. CONCLUSIONS: These results indicate the value of imaging features in monitoring the progress of MCI in populations at high risk of developing AD. However, the incremental benefit of combining (18)F-FDG PET and MRI is limited, and radiomic analysis of a single modality may yield acceptable predictive results.