The early diagnosis of Alzheimer’s Disease (AD) is critical for the development and success of interventions. However, the pathophysiological process of AD initiates several years before the clinical symptoms arise.
Quantitative neuroimaging biomarkers derived from Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) are one of the most promising areas in the early detection of AD and are currently the main research focus mainly because radiologists cannot perceive subtle changes of neurodegeneration with the “naked” eye. Although atrophy is currently considered one of the most used signatures of dementia in quantitative imaging, it does not provide consistent results for early diagnosis and heterogeneity. However, radiomics may provide an earlier diagnosis and detect smaller-scale changes in neurodegeneration. On the other hand, recent developments in molecular imaging, and novel PET imaging ligands, have allowed imaging in vivo amyloid deposits in the brain such as decreased uptake of 18F-FDG and amyloid deposits in the brain in AD subjects. In addition, recent studies have suggested Quantitative Susceptibility Mapping (QSM) as a potential biomarker to be used for AD pathogenesis. The latter has been adopted in a few studies combined to 18F-FDG.
Furthermore, the integration of large-scale, high-dimensional, and multimodal data from rapidly advancing neuroimaging techniques imposes difficulty for contemporary methods to identify the disease.
The goal of this Research Topic is to investigate the impact of quantitative imaging in the assessment of AD by using structural MRI or molecular neuroimaging such as PET as results from cognitive tests greatly contribute to the false prediction.
Another goal is to evaluate the performance of deep learning methods in the classification and prediction of AD. Through this Research Topic, we aim to publish rigorously peer-reviewed research focusing on the use of quantitative multimodal neuroimaging and advanced computational approaches in the field for the assessment of AD.
A key interest of this Topic is to investigate mainly the neurodegeneration of the medial temporal lobe structures where the disease initiates and whole brain studies are also welcome.
We encourage studies that utilize multi-modal approaches (e.g., combining neuroimaging and clinical and/or genetics data).
Longitudinal studies, replication efforts, meta-analyses, and multi-lab collaborations are also welcome.
Due to the vast data and biomarkers available from quantitative imaging we are looking forward to computational machine learning methods for integrative data analysis as this is the new trend in the assessment of AD.
The early diagnosis of Alzheimer’s Disease (AD) is critical for the development and success of interventions. However, the pathophysiological process of AD initiates several years before the clinical symptoms arise.
Quantitative neuroimaging biomarkers derived from Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) are one of the most promising areas in the early detection of AD and are currently the main research focus mainly because radiologists cannot perceive subtle changes of neurodegeneration with the “naked” eye. Although atrophy is currently considered one of the most used signatures of dementia in quantitative imaging, it does not provide consistent results for early diagnosis and heterogeneity. However, radiomics may provide an earlier diagnosis and detect smaller-scale changes in neurodegeneration. On the other hand, recent developments in molecular imaging, and novel PET imaging ligands, have allowed imaging in vivo amyloid deposits in the brain such as decreased uptake of 18F-FDG and amyloid deposits in the brain in AD subjects. In addition, recent studies have suggested Quantitative Susceptibility Mapping (QSM) as a potential biomarker to be used for AD pathogenesis. The latter has been adopted in a few studies combined to 18F-FDG.
Furthermore, the integration of large-scale, high-dimensional, and multimodal data from rapidly advancing neuroimaging techniques imposes difficulty for contemporary methods to identify the disease.
The goal of this Research Topic is to investigate the impact of quantitative imaging in the assessment of AD by using structural MRI or molecular neuroimaging such as PET as results from cognitive tests greatly contribute to the false prediction.
Another goal is to evaluate the performance of deep learning methods in the classification and prediction of AD. Through this Research Topic, we aim to publish rigorously peer-reviewed research focusing on the use of quantitative multimodal neuroimaging and advanced computational approaches in the field for the assessment of AD.
A key interest of this Topic is to investigate mainly the neurodegeneration of the medial temporal lobe structures where the disease initiates and whole brain studies are also welcome.
We encourage studies that utilize multi-modal approaches (e.g., combining neuroimaging and clinical and/or genetics data).
Longitudinal studies, replication efforts, meta-analyses, and multi-lab collaborations are also welcome.
Due to the vast data and biomarkers available from quantitative imaging we are looking forward to computational machine learning methods for integrative data analysis as this is the new trend in the assessment of AD.