scholarly journals Multimodal Hippocampal Subfield Grading For Alzheimer’s Disease Classification

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Kilian Hett ◽  
◽  
Vinh-Thong Ta ◽  
Gwenaëlle Catheline ◽  
Thomas Tourdias ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Mean Diffusivity ◽  
Disease Classification ◽  
Hippocampal Subfields ◽  
Microstructural Alterations ◽  
Current Classification ◽  
Magnetic Resonance Imaging Mri ◽  
And Diffusion ◽  
New Framework

Abstract Numerous studies have proposed biomarkers based on magnetic resonance imaging (MRI) to detect and predict the risk of evolution toward Alzheimer’s disease (AD). Most of these methods have focused on the hippocampus, which is known to be one of the earliest structures impacted by the disease. To date, patch-based grading approaches provide among the best biomarkers based on the hippocampus. However, this structure is complex and is divided into different subfields, not equally impacted by AD. Former in-vivo imaging studies mainly investigated structural alterations of these subfields using volumetric measurements and microstructural modifications with mean diffusivity measurements. The aim of our work is to improve the current classification performances based on the hippocampus with a new multimodal patch-based framework combining structural and diffusivity MRI. The combination of these two MRI modalities enables the capture of subtle structural and microstructural alterations. Moreover, we propose to study the efficiency of this new framework applied to the hippocampal subfields. To this end, we compare the classification accuracy provided by the different hippocampal subfields using volume, mean diffusivity, and our novel multimodal patch-based grading framework combining structural and diffusion MRI. The experiments conducted in this work show that our new multimodal patch-based method applied to the whole hippocampus provides the most discriminating biomarker for advanced AD detection while our new framework applied into subiculum obtains the best results for AD prediction, improving by two percentage points the accuracy compared to the whole hippocampus.

scholarly journals Multimodal Hippocampal Subfield Grading For Alzheimer’s Disease Classification

2018 ◽  
Author(s):  
Kilian Hett ◽  
Vinh-Thong Ta ◽  
Gwenaëlle Catheline ◽  
Thomas Tourdias ◽  
José V. Manjón ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Diffusion Mri ◽  
Mean Diffusivity ◽  
Disease Classification ◽  
Structural Alterations ◽  
Hippocampal Subfields ◽  
Microstructural Alterations ◽  
Diffusivity Measurements

ABSTRACTNumerous studies have proposed biomarkers based on magnetic resonance imaging (MRI) to detect and predict the risk of evolution toward Alzheimer’s disease (AD). While anatomical MRI captures structural alterations, studies demonstrated the ability of diffusion MRI to capture microstructural modifications at an earlier stage. Several methods have focused on hippocampus structure to detect AD. To date, the patch-based grading framework provides the best biomarker based on the hippocampus. However, this structure is complex since the hippocampus is divided into several heterogeneous subfields not equally impacted by AD. Former in-vivo imaging studies only investigated structural alterations of these subfields using volumetric measurements and microstructural modifications with mean diffusivity measurements. The aim of our work is to study the efficiency of hippocampal subfields compared to the whole hippocampus structure with a multimodal patch-based framework that enables to capture subtler structural and microstructural alterations. To this end, we analyze the significance of the different hippocampal subfields for AD diagnosis and prognosis with volumetric, diffusivity measurements and a novel multimodal patch-based grading framework that combines structural and diffusion MRI. The experiments conducted in this work showed that the whole hippocampus provides the most discriminant biomarkers for advanced AD detection while biomarkers applied into subiculum obtain the best results for AD prediction, improving by 2% the accuracy compared to the whole hippocampus.

Subcortical nuclei in Alzheimer’s disease: a volumetric and diffusion kurtosis imaging study

2018 ◽  
Vol 59 (11) ◽  
pp. 1365-1371 ◽  
Author(s):  
Ming-Liang Wang ◽  
Xiao-Er Wei ◽  
Jian-Liang Fu ◽  
Wei Li ◽  
Meng-Meng Yu ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Mmse Score ◽  
Mean Diffusivity ◽  
Volume Reduction ◽  
Diffusion Kurtosis Imaging ◽  
Left Hippocampus ◽  
Subcortical Nuclei ◽  
Diffusion Kurtosis ◽  
And Diffusion

Background Previous studies revealed that subcortical nuclei were harmed in the process of Alzheimer’s disease (AD). Purpose To investigate the volumetric and diffusion kurtosis imaging (DKI) parameter changes of subcortical nuclei in AD and their relationship with cognitive function. Materials and Methods A total of 17 mild AD patients, 15 moderate to severe AD patients, and 16 controls underwent neuropsychological tests and magnetic resonance imaging (MRI) scans. Volume, mean kurtosis (MK), mean diffusivity (MD), and fractional anisotropy (FA) were measured in hippocampus, thalamus, caudate, putamen, pallidum, and amygdala. MRI parameters were compared. Correlation analysis was performed between subcortical nuclei volume, DKI parameters, and MMSE score. Results Significant volume reduction was seen in the left hippocampus in mild AD, and the bilateral hippocampus, thalamus, putamen, left caudate, and right amygdala in moderate to severe AD ( P < 0.05). Increased MD values were observed in the left hippocampus, left amygdala, and right caudate in mild AD, and the bilateral hippocampus and right amygdala in moderate to severe AD ( P < 0.05). Decreased MK values were observed only in the bilateral hippocampus in moderate to severe AD ( P < 0.05). No group significances were found in FA value. MMSE score was positively correlated with the volume of the bilateral hippocampus, thalamus, and putamen, and MK value of the left hippocampus ( P < 0.05). A negative correlation was found with the MD value of the bilateral hippocampus and left amygdala ( P < 0.05). Conclusion Mild AD mainly has microscopic subcortical changes revealed by increased MD value, and moderate to severe AD mainly has macroscopic subcortical changes revealed by volume reduction. MK is more sensitive in severe AD than mild AD.

scholarly journals Tau isoforms are differentially expressed across the hippocampus in chronic traumatic encephalopathy and Alzheimer’s disease

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Jonathan D. Cherry ◽  
Camille D. Esnault ◽  
Zachary H. Baucom ◽  
Yorghos Tripodis ◽  
Bertrand R. Huber ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Chronic Traumatic Encephalopathy ◽  
Temporal Cortex ◽  
Head Impacts ◽  
Hippocampal Subfields ◽  
Mild Disease ◽  
Tau Isoforms ◽  
Ghost Tangles

AbstractChronic traumatic encephalopathy (CTE) is a progressive neurodegenerative disease, characterized by hyperphosphorylated tau, found in individuals with a history of exposure to repetitive head impacts. While the neuropathologic hallmark of CTE is found in the cortex, hippocampal tau has proven to be an important neuropathologic feature to examine the extent of disease severity. However, the hippocampus is also heavily affected in many other tauopathies, such as Alzheimer’s disease (AD). How CTE and AD differentially affect the hippocampus is unclear. Using immunofluorescent analysis, a detailed histologic characterization of 3R and 4R tau isoforms and their differential accumulation in the temporal cortex in CTE and AD was performed. CTE and AD were both observed to contain mixed 3R and 4R tau isoforms, with 4R predominating in mild disease and 3R increasing proportionally as pathological severity increased. CTE demonstrated high levels of tau in hippocampal subfields CA2 and CA3 compared to CA1. There were also low levels of tau in the subiculum compared to CA1 in CTE. In contrast, AD had higher levels of tau in CA1 and subiculum compared to CA2/3. Direct comparison of the tau burden between AD and CTE demonstrated that CTE had higher tau densities in CA4 and CA2/3, while AD had elevated tau in the subiculum. Amyloid beta pathology did not contribute to tau isoform levels. Finally, it was demonstrated that higher levels of 3R tau correlated to more severe extracellular tau (ghost tangles) pathology. These findings suggest that mixed 3R/4R tauopathies begin as 4R predominant then transition to 3R predominant as pathological severity increases and ghost tangles develop. Overall, this work demonstrates that the relative deposition of tau isoforms among hippocampal subfields can aid in differential diagnosis of AD and CTE, and might help improve specificity of biomarkers for in vivo diagnosis.

scholarly journals Joint Assessment of Structural, Perfusion, and Diffusion MRI in Alzheimer's Disease and Frontotemporal Dementia

2011 ◽  
Vol 2011 ◽  
pp. 1-11 ◽  
Author(s):  
Yu Zhang ◽  
Norbert Schuff ◽  
Christopher Ching ◽  
Duygu Tosun ◽  
Wang Zhan ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Frontotemporal Dementia ◽  
Diffusion Tensor ◽  
Healthy Control ◽  
Multimodal Mri ◽  
Imaging Markers ◽  
And Diffusion ◽  
Joint Assessment ◽  
Diffusion Tensor Imaging Dti

Most MRI studies of Alzheimer's disease (AD) and frontotemporal dementia (FTD) have assessed structural, perfusion and diffusion abnormalities separately while ignoring the relationships across imaging modalities. This paper aimed to assess brain gray (GM) and white matter (WM) abnormalities jointly to elucidate differences in abnormal MRI patterns between the diseases. Twenty AD, 20 FTD patients, and 21 healthy control subjects were imaged using a 4 Tesla MRI. GM loss and GM hypoperfusion were measured using high-resolution T1 and arterial spin labeling MRI (ASL-MRI). WM degradation was measured with diffusion tensor imaging (DTI). Using a new analytical approach, the study found greater WM degenerations in FTD than AD at mild abnormality levels. Furthermore, the GM loss and WM degeneration exceeded the reduced perfusion in FTD whereas, in AD, structural and functional damages were similar. Joint assessments of multimodal MRI have potential value to provide new imaging markers for improved differential diagnoses between FTD and AD.

O2-04-05: Relationships between hippocampal microstructural alterations and regional brain metabolism in early Alzheimer's disease: A combined DTI-PET study

2010 ◽  
Vol 6 ◽  
pp. S104-S105
Author(s):  
Andreas Fellgiebel ◽  
Matthias Schreckenberger ◽  
Matthias J. Müller ◽  
Ingrid Schermuly ◽  
Peter Stoeter ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Brain Metabolism ◽  
Microstructural Alterations ◽  
Regional Brain ◽  
Early Alzheimer’S Disease

Lightweight deep residual network for alzheimer’s disease classification using sMRI slices

2021 ◽  
pp. 1-9
Author(s):  
Yanteng Zhang ◽  
Qizhi Teng ◽  
Linbo Qing ◽  
Yan Liu ◽  
Xiaohai He
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Computational Cost ◽  
Disease Classification ◽  
Learning Networks ◽  
Feature Maps ◽  
Medical Field ◽  
Widespread Application ◽  
Healthy Control

Alzheimer’s disease (AD) is a degenerative brain disease and the most common cause of dementia. In recent years, with the widespread application of artificial intelligence in the medical field, various deep learning-based methods have been applied for AD detection using sMRI images. Many of these networks achieved AD vs HC (Healthy Control) classification accuracy of up to 90%but with a large number of computational parameters and floating point operations (FLOPs). In this paper, we adopt a novel ghost module, which uses a series of cheap operations of linear transformation to generate more feature maps, embedded into our designed ResNet architecture for task of AD vs HC classification. According to experiments on the OASIS dataset, our lightweight network achieves an optimistic accuracy of 97.92%and its total parameters are dozens of times smaller than state-of-the-art deep learning networks. Our proposed AD classification network achieves better performance while the computational cost is reduced significantly.

Alzheimer’s Disease Classification Using Genetic Data

2021 ◽  
Author(s):  
Subash Khanal ◽  
Jin Chen ◽  
Nathan Jacobs ◽  
Ai-Ling Lin
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Genetic Data ◽  
Disease Classification
Sign in / Sign up

Export Citation Format

Share Document