The convergent and divergent patterns in brain perfusion between Alzheimer's disease and Parkinson's disease with dementia: An ASL MRI study

Comparison of 18F-FDG PET and arterial spin labeling MRI in evaluating Alzheimer's disease and amnestic mild cognitive impairment using integrated PET/MR

BACKGROUND

Developing biomarkers for early stage AD patients is crucial. Glucose metabolism measured by 18F-FDG PET is the most common biomarker for evaluating cellular energy metabolism to diagnose AD. Arterial spin labeling (ASL) MRI can potentially provide comparable diagnostic information to 18F-FDG PET in patients with neurodegenerative disorders. However, the conclusions about the diagnostic performance of AD are still controversial between 18F-FDG PET and ASL. This study aims to compare quantitative cerebral blood flow (CBF) and glucose metabolism measured by 18F-FDG PET diagnostic values in patients with Alzheimer's disease (AD) and amnestic mild cognitive impairment (aMCI) using integrated PET/MR.

RESULTS

Analyses revealed overlapping between decreased regional rCBF and 18F-FDG PET SUVR in patients with AD compared with NC participants in the bilateral parietotemporal regions, frontal cortex, and cingulate cortex. Compared with NC participants, patients with aMCI exclusively demonstrated lower 18F-FDG PET SUVR in the bilateral temporal cortex, insula cortex, and inferior frontal cortex. Comparison of the rCBF in patients with aMCI and NC participants revealed no significant difference (P > 0.05). The ROC analysis of rCBF in the meta-ROI could diagnose patients with AD (AUC, 0.87) but not aMCI (AUC, 0.61). The specificity of diagnosing aMCI has been improved to 75.56% when combining rCBF and 18F-FDG PET SUVR.

CONCLUSION

ASL could detect similar aberrant patterns of abnormalities compared to 18F-FDG PET in patients with AD compared with NC participants but not in aMCI. The diagnostic efficiency of 18F-FDG-PET for AD and aMCI patients remained higher to ASL. Our findings support that applying 18F-FDG PET may be preferable for diagnosing AD and aMCI.

Application of Deep Learning for Prediction of Alzheimer's Disease in PET/MR Imaging

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that affects millions of people worldwide. Positron emission tomography/magnetic resonance (PET/MR) imaging is a promising technique that combines the advantages of PET and MR to provide both functional and structural information of the brain. Deep learning (DL) is a subfield of machine learning (ML) and artificial intelligence (AI) that focuses on developing algorithms and models inspired by the structure and function of the human brain's neural networks. DL has been applied to various aspects of PET/MR imaging in AD, such as image segmentation, image reconstruction, diagnosis and prediction, and visualization of pathological features. In this review, we introduce the basic concepts and types of DL algorithms, such as feed forward neural networks, convolutional neural networks, recurrent neural networks, and autoencoders. We then summarize the current applications and challenges of DL in PET/MR imaging in AD, and discuss the future directions and opportunities for automated diagnosis, predictions of models, and personalized medicine. We conclude that DL has great potential to improve the quality and efficiency of PET/MR imaging in AD, and to provide new insights into the pathophysiology and treatment of this devastating disease.