Hippocampus segmentation and classification for dementia analysis using pre-trained neural network models

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Ahana Priyanka ◽  
Kavitha Ganesan
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Network Models ◽  
Curve Evolution ◽  
Neural Network Models ◽  
Brain Images ◽  
Whole Brain ◽  
Shape Constraint ◽  
Mr Brain Images ◽  
Trained Neural Network

Abstract The diagnostic and clinical overlap of early mild cognitive impairment (EMCI), mild cognitive impairment (MCI), late mild cognitive impairment (LMCI) and Alzheimer disease (AD) is a vital oncological issue in dementia disorder. This study is designed to examine Whole brain (WB), grey matter (GM) and Hippocampus (HC) morphological variation and identify the prominent biomarkers in MR brain images of demented subjects to understand the severity progression. Curve evolution based on shape constraint is carried out to segment the complex brain structure such as HC and GM. Pre-trained models are used to observe the severity variation in these regions. This work is evaluated on ADNI database. The outcome of the proposed work shows that curve evolution method could segment HC and GM regions with better correlation. Pre-trained models are able to show significant severity difference among WB, GM and HC regions for the considered classes. Further, prominent variation is observed between AD vs. EMCI, AD vs. MCI and AD vs. LMCI in the whole brain, GM and HC. It is concluded that AlexNet model for HC region result in better classification for AD vs. EMCI, AD vs. MCI and AD vs. LMCI with an accuracy of 93, 78.3 and 91% respectively.

scholarly journals Differentiation of Alzheimer Conditions in MR Brain Images Using a Single Inception Module Network

2021 ◽  
Author(s):  
Sreelakshmi Shaji ◽  
Nagarajan Ganapathy ◽  
Ramakrishnan Swaminathan
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Input Image ◽  
Mr Images ◽  
Brain Images ◽  
Medical Expertise ◽  
Module Network ◽  
Mr Brain Images ◽  
Mr Brain ◽  
Normal Controls

In this study, an attempt has been made to differentiate Alzheimer’s Disease (AD) stages in structural Magnetic Resonance (MR) images using single inception module network. For this, T1-weighted MR brain images of AD, mild cognitive impairment and Normal Controls (NC) are obtained from a public database. From the images, significant features are extracted and classified using an inception module network. The performance of the model is computed and analyzed for different input image sizes. Results show that the single inception module is able to classify AD stages using MR images. The end-to-end network differentiates AD from NC with 85% precision. The model is found to be effective for varied sizes of input images. Since the proposed approach is able to categorize AD stages, single inception module networks could be used for the automated AD diagnosis with minimum medical expertise.

The Anterior-posterior Functional Connectivity Disconnection in the Elderly with Subjective Memory Impairment and Amnestic Mild Cognitive Impairment

2020 ◽  
Vol 17 (4) ◽  
pp. 373-381
Author(s):  
Wuhai Tao ◽  
Jinping Sun ◽  
Xin Li ◽  
Wen Shao ◽  
Jing Pei ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Functional Connectivity ◽  
Memory Impairment ◽  
Amnestic Mild Cognitive Impairment ◽  
Magnetic Resonance Imaging Scan ◽  
Subjective Memory ◽  
Long Distance ◽  
Whole Brain ◽  
Subjective Memory Impairment

Background: Subjective Memory Impairment (SMI) may tremendously increase the risk of Alzheimer’s Disease (AD). The full understanding of the neuromechanism of SMI will shed light on the early intervention of AD. Methods: In the current study, 23 Healthy Controls (HC), 22 SMI subjects and 24 amnestic Mild Cognitive Impairment (aMCI) subjects underwent the comprehensive neuropsychological assessment and the resting-state functional magnetic resonance imaging scan. The difference in the connectivity of the Default Mode Network (DMN) and Functional Connectivity (FC) from the Region of Interest (ROI) to the whole brain were compared, respectively. Results: The results showed that HC and SMI subjects had significantly higher connectivity in the region of the precuneus area compared to aMCI subjects. However, from this region to the whole brain, SMI and aMCI subjects had significant FC decrease in the right anterior cingulum, left superior frontal and left medial superior frontal gyrus compared to HC. In addition, this FC change was significantly correlated with the cognitive function decline in participants. Conclusion: Our study indicated that SMI subjects had relatively intact DMN connectivity but impaired FC between the anterior and posterior brain. The findings suggest that long-distance FC is more vulnerable than the short ones in the people with SMI.

scholarly journals Using Regional Homogeneity to Reveal Altered Spontaneous Activity in Patients with Mild Cognitive Impairment

2015 ◽  
Vol 2015 ◽  
pp. 1-8 ◽  
Author(s):  
Yumei Wang ◽  
Xiaochuan Zhao ◽  
Shunjiang Xu ◽  
Lulu Yu ◽  
Lan Wang ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Spontaneous Activity ◽  
Healthy Aging ◽  
Early Stage ◽  
Brain Activity ◽  
Regional Homogeneity ◽  
Whole Brain ◽  
Spontaneous Brain Activity ◽  
Regional Brain Activity

Most patients with mild cognitive impairment (MCI) are thought to be in an early stage of Alzheimer’s disease (AD). Resting-state functional magnetic resonance imaging reflects spontaneous brain activity and/or the endogenous/background neurophysiological process of the human brain. Regional homogeneity (ReHo) rapidly maps regional brain activity across the whole brain. In the present study, we used the ReHo index to explore whole brain spontaneous activity pattern in MCI. Our results showed that MCI subjects displayed an increased ReHo index in the paracentral lobe, precuneus, and postcentral and a decreased ReHo index in the medial temporal gyrus and hippocampus. Impairments in the medial temporal gyrus and hippocampus may serve as important markers distinguishing MCI from healthy aging. Moreover, the increased ReHo index observed in the postcentral and paracentral lobes might indicate compensation for the cognitive function losses in individuals with MCI.

scholarly journals Altered Weibull Degree Distribution in Resting-State Functional Brain Networks Is Associated With Cognitive Decline in Mild Cognitive Impairment

2021 ◽  
Vol 12 ◽  
Author(s):  
Yifei Zhang ◽  
Xiaodan Chen ◽  
Xinyuan Liang ◽  
Zhijiang Wang ◽  
Teng Xie ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Human Brain ◽  
Cognitive Performance ◽  
Power Law ◽  
Resting State ◽  
Brain Networks ◽  
Functional Networks ◽  
Whole Brain ◽  
Connectivity Degree

The topological organization of human brain networks can be mathematically characterized by the connectivity degree distribution of network nodes. However, there is no clear consensus on whether the topological structure of brain networks follows a power law or other probability distributions, and whether it is altered in Alzheimer's disease (AD). Here we employed resting-state functional MRI and graph theory approaches to investigate the fitting of degree distributions of the whole-brain functional networks and seven subnetworks in healthy subjects and individuals with amnestic mild cognitive impairment (aMCI), i.e., the prodromal stage of AD, and whether they are altered and correlated with cognitive performance in patients. Forty-one elderly cognitively healthy controls and 30 aMCI subjects were included. We constructed functional connectivity matrices among brain voxels and examined nodal degree distributions that were fitted by maximum likelihood estimation. In the whole-brain networks and all functional subnetworks, the connectivity degree distributions were fitted better by the Weibull distribution [f(x)~x(β−1)e(−λxβ)] than power law or power law with exponential cutoff. Compared with the healthy control group, the aMCI group showed lower Weibull β parameters (shape factor) in both the whole-brain networks and all seven subnetworks (false-discovery rate-corrected, p < 0.05). These decreases of the Weibull β parameters in the whole-brain networks and all subnetworks except for ventral attention were associated with reduced cognitive performance in individuals with aMCI. Thus, we provided a short-tailed model to capture intrinsic connectivity structure of the human brain functional networks in health and disease.

Increasing Diagnostic Accuracy of Mild Cognitive Impairment due to Alzheimer’s Disease by User-Independent, Web-Based Whole-Brain Volumetry

2018 ◽  
Vol 65 (4) ◽  
pp. 1459-1467 ◽  
Author(s):  
Dennis M. Hedderich ◽  
Judith E. Spiro ◽  
Oliver Goldhardt ◽  
Johannes Kaesmacher ◽  
Benedikt Wiestler ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Diagnostic Accuracy ◽  
Whole Brain ◽  
Web Based ◽  
Brain Volumetry

scholarly journals Prediction and Characterization of Missing Proteomic Data inDesulfovibrio vulgaris

2011 ◽  
Vol 2011 ◽  
pp. 1-16 ◽  
Author(s):  
Feng Li ◽  
Lei Nie ◽  
Gang Wu ◽  
Jianjun Qiao ◽  
Weiwen Zhang
Keyword(s):  
Neural Network ◽  
Multivariate Logistic Regression Analysis ◽  
Network Models ◽  
Mrna Abundance ◽  
Biological Information ◽  
Desulfovibrio Vulgaris ◽  
Neural Network Models ◽  
Proteomic Data ◽  
Aliphatic Index ◽  
Trained Neural Network

Proteomic datasets are often incomplete due to identification range and sensitivity issues. It becomes important to develop methodologies to estimate missing proteomic data, allowing better interpretation of proteomic datasets and metabolic mechanisms underlying complex biological systems. In this study, we applied an artificial neural network to approximate the relationships between cognate transcriptomic and proteomic datasets ofDesulfovibrio vulgaris, and to predict protein abundance for the proteins not experimentally detected, based on several relevant predictors, such as mRNA abundance, cellular role and triple codon counts. The results showed that the coefficients of determination for the trained neural network models ranged from 0.47 to 0.68, providing better modeling than several previous regression models. The validity of the trained neural network model was evaluated using biological information (i.e. operons). To seek understanding of mechanisms causing missing proteomic data, we used a multivariate logistic regression analysis and the result suggested that some key factors, such as protein instability index, aliphatic index, mRNA abundance, effective number of codons () and codon adaptation index (CAI) values may be ascribed to whether a given expressed protein can be detected. In addition, we demonstrated that biological interpretation can be improved by use of imputed proteomic datasets.

Sign in / Sign up

Export Citation Format

Share Document