Predicting MCI to AD Conversation Using Integrated sMRI and rs-fMRI: Machine Learning and Graph Theory Approach

Zhang, Tingting; Liao, Qian; Zhang, Danmei; Zhang, Chao; Yan, Juntao; Ngetich, Ronald; Jin, Zhenlan; Li, Ling

doi:10.3389/fnagi.2021.688926

Cited by 46 publications

(35 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pretangle Tau, thought to be the toxic form of tau, has now been detected in MCI and AD and has been found to be one of the earliest tau lesions that correlates with cognitive status (Mufson et al, 2014). Synapse loss (Bastin et al, 2020;Buchanan et al, 2020;Mecca et al, 2020;Pereira et al, 2021), changes in hormone levels (Cheng et al, 2021), changes in blood biomarker levels (Guzman-Martinez et al, 2019;Montoliu-Gaya et al, 2021), electroencephalogram (EEG) readings (Hulbert and Adeli, 2013;Lin et al, 2021), retinal assays (Ashok et al, 2020;Mirzaei et al, 2020), and changes in specific protein levels (Buchanan et al, 2020;Colom-Cadena et al, 2020) are some of the myriad assays being developed to try to detect AD earlier and predict when and if the change from mild cognitive impairment (MCI) to AD will occur (Zhang T. et al, 2021). All of these new developments are focused toward enabling earlier therapeutic intervention when chances for success would be greatest.…”

Section: Discussionmentioning

confidence: 99%

The Therapeutic and Diagnostic Potential of Amyloid β Oligomers Selective Antibodies to Treat Alzheimer’s Disease

et al. 2022

View full text Add to dashboard Cite

Improvements have been made in the diagnosis of Alzheimer’s disease (AD), manifesting mostly in the development of in vivo imaging methods that allow for the detection of pathological changes in AD by magnetic resonance imaging (MRI) and positron emission tomography (PET) scans. Many of these imaging methods, however, use agents that probe amyloid fibrils and plaques–species that do not correlate well with disease progression and are not present at the earliest stages of the disease. Amyloid β oligomers (AβOs), rather, are now widely accepted as the Aβ species most germane to AD onset and progression. Here we report evidence further supporting the role of AβOs as pathological instigators of AD and introduce promising anti-AβO diagnostic probes capable of distinguishing the 5xFAD mouse model from wild type mice by PET and MRI. In a developmental study, Aβ oligomers in 5xFAD mice were found to appear at 3 months of age, just prior to the onset of memory dysfunction, and spread as memory worsened. The increase of AβOs is prominent in the subiculum and correlates with concomitant development of reactive astrocytosis. The impact of these AβOs on memory is in harmony with findings that intraventricular injection of synthetic AβOs into wild type mice induced hippocampal dependent memory dysfunction within 24 h. Compelling support for the conclusion that endogenous AβOs cause memory loss was found in experiments showing that intranasal inoculation of AβO-selective antibodies into 5xFAD mice completely restored memory function, measured 30–40 days post-inoculation. These antibodies, which were modified to give MRI and PET imaging probes, were able to distinguish 5xFAD mice from wild type littermates. These results provide strong support for the role of AβOs in instigating memory loss and salient AD neuropathology, and they demonstrate that AβO selective antibodies have potential both for therapeutics and for diagnostics.

show abstract

Section: Discussionmentioning

confidence: 99%

The Therapeutic and Diagnostic Potential of Amyloid β Oligomers Selective Antibodies to Treat Alzheimer’s Disease

et al. 2022

View full text Add to dashboard Cite

show abstract

“…AD progresses gradually through the prodromal stage of MCI, and finally, to AD dementia. According to studies, people with MCI acquire AD at a rate of 10-15% every year [3]. Early identification of patients with MCI can delay or prevent the progression of the disease from the MCI stage to AD.…”

Section: Introductionmentioning

confidence: 99%

“…Early identification of patients with MCI can delay or prevent the progression of the disease from the MCI stage to AD. The morphological differences in the brain lesions in patients with intermediate stages of MCI are very small [3]. Furthermore, they have similar clinical manifestations; thus, to act early in the diagnosis and treatment of AD, the diagnosis and prognosis of MCI disease have been analyzed using magnetic resonance imaging (MRI) studies [4], which can capture alterations in the brain anatomy and function [5].…”

Section: Introductionmentioning

confidence: 99%

An Intelligent System for Early Recognition of Alzheimer’s Disease Using Neuroimaging

Odusami

Maskeliūnas

Damaševičius

2022

Sensors

View full text Add to dashboard Cite

Alzheimer’s disease (AD) is a neurodegenerative disease that affects brain cells, and mild cognitive impairment (MCI) has been defined as the early phase that describes the onset of AD. Early detection of MCI can be used to save patient brain cells from further damage and direct additional medical treatment to prevent its progression. Lately, the use of deep learning for the early identification of AD has generated a lot of interest. However, one of the limitations of such algorithms is their inability to identify changes in the functional connectivity in the functional brain network of patients with MCI. In this paper, we attempt to elucidate this issue with randomized concatenated deep features obtained from two pre-trained models, which simultaneously learn deep features from brain functional networks from magnetic resonance imaging (MRI) images. We experimented with ResNet18 and DenseNet201 to perform the task of AD multiclass classification. A gradient class activation map was used to mark the discriminating region of the image for the proposed model prediction. Accuracy, precision, and recall were used to assess the performance of the proposed system. The experimental analysis showed that the proposed model was able to achieve 98.86% accuracy, 98.94% precision, and 98.89% recall in multiclass classification. The findings indicate that advanced deep learning with MRI images can be used to classify and predict neurodegenerative brain diseases such as AD.

show abstract

“…We compared DCL+XGBoost with several other well-established methods that were designed for the multi neuropsychiatric disorders classification: mMLDA (Janousova et al, 2015 ), MFMK-SVM (Liu J. et al, 2018 ), KFCM (Baskar et al, 2019 ), MK-SVM (Zhuang et al, 2019 ), and mRMR-SVM (Zhang et al, 2021 ). These methods used one or both types of MRI data as input of the model for multi neuropsychiatric disorder classification.…”

Section: Ablation Experiments and Discussionmentioning

confidence: 99%

Decomposition-Based Correlation Learning for Multi-Modal MRI-Based Classification of Neuropsychiatric Disorders

et al. 2022

View full text Add to dashboard Cite

Multi-modal magnetic resonance imaging (MRI) is widely used for diagnosing brain disease in clinical practice. However, the high-dimensionality of MRI images is challenging when training a convolution neural network. In addition, utilizing multiple MRI modalities jointly is even more challenging. We developed a method using decomposition-based correlation learning (DCL). To overcome the above challenges, we used a strategy to capture the complex relationship between structural MRI and functional MRI data. Under the guidance of matrix decomposition, DCL takes into account the spike magnitude of leading eigenvalues, the number of samples, and the dimensionality of the matrix. A canonical correlation analysis (CCA) was used to analyze the correlation and construct matrices. We evaluated DCL in the classification of multiple neuropsychiatric disorders listed in the Consortium for Neuropsychiatric Phenomics (CNP) dataset. In experiments, our method had a higher accuracy than several existing methods. Moreover, we found interesting feature connections from brain matrices based on DCL that can differentiate disease and normal cases and different subtypes of the disease. Furthermore, we extended experiments on a large sample size dataset and a small sample size dataset, compared with several other well-established methods that were designed for the multi neuropsychiatric disorder classification; our proposed method achieved state-of-the-art performance on all three datasets.

show abstract

Predicting MCI to AD Conversation Using Integrated sMRI and rs-fMRI: Machine Learning and Graph Theory Approach

Cited by 46 publications

References 85 publications

The Therapeutic and Diagnostic Potential of Amyloid β Oligomers Selective Antibodies to Treat Alzheimer’s Disease

The Therapeutic and Diagnostic Potential of Amyloid β Oligomers Selective Antibodies to Treat Alzheimer’s Disease

An Intelligent System for Early Recognition of Alzheimer’s Disease Using Neuroimaging

Decomposition-Based Correlation Learning for Multi-Modal MRI-Based Classification of Neuropsychiatric Disorders

Contact Info

Product

Resources

About