Identification of early mild cognitive impairment using multi-modal data and graph convolutional networks

Machine learning based algorithms for virtual early detection and screening of neurodegenerative and neurocognitive disorders: a systematic-review

Background and aim

Neurodegenerative disorders (e.g., Alzheimer's, Parkinson's) lead to neuronal loss; neurocognitive disorders (e.g., delirium, dementia) show cognitive decline. Early detection is crucial for effective management. Machine learning aids in more precise disease identification, potentially transforming healthcare. This comprehensive systematic review discusses how machine learning (ML), can enhance early detection of these disorders, surpassing traditional diagnostics' constraints.

Methods

In this review, databases were examined up to August 15th, 2023, for ML data on neurodegenerative and neurocognitive diseases using PubMed, Scopus, Google Scholar, and Web of Science. Two investigators used the RAYYAN intelligence tool for systematic reviews to conduct the screening. Six blinded reviewers reviewed titles/abstracts. Cochrane risk of bias tool was used for quality assessment.

Results

Our search found 7,069 research studies, of which 1,365 items were duplicates and thus removed. Four thousand three hundred and thirty four studies were screened, and 108 articles met the criteria for inclusion after preprocessing. Twelve ML algorithms were observed for dementia, showing promise in early detection. Eighteen ML algorithms were identified for Parkinson's, each effective in detection and diagnosis. Studies emphasized that ML algorithms are necessary for Alzheimer's to be successful. Fourteen ML algorithms were discovered for mild cognitive impairment, with LASSO logistic regression being the only one with unpromising results.

Conclusion

This review emphasizes the pressing necessity of integrating verified digital health resources into conventional medical practice. This integration may signify a new era in the early detection of neurodegenerative and neurocognitive illnesses, potentially changing the course of these conditions for millions globally. This study showcases specific and statistically significant findings to illustrate the progress in the area and the prospective influence of these advancements on the global management of neurocognitive and neurodegenerative illnesses.

Recurrence quantification analysis of rs-fMRI data: A method to detect subtle changes in the TgF344-AD rat model

BACKGROUND AND OBJECTIVE

Alzheimer's disease (AD) is one of the leading causes of dementia, affecting the world's population at a growing rate. The preclinical stage of AD lasts over a decade, hence understanding AD-related early neuropathological effects on brain function at this stage facilitates early detection of the disease.

METHODS

Resting-state functional magnetic resonance imaging (rs-fMRI) has been a powerful tool for understanding brain function, and it has been widely used in AD research. In this study, we apply Recurrence Quantification Analysis (RQA) on rs-fMRI images of 4-months (4 m) and 6-months-old (6 m) TgF344-AD rats and WT littermates to identify changes related to the AD phenotype and aging. RQA has been focused on areas of the default mode-like network (DMLN) and was performed based on Recurrence Plots (RP). RP is a mathematical representation of any dynamical system that evolves over time as a set of its state recurrences. In this paper, RPs were extracted in order to identify the affected regions of the DMLN at very early stages of AD.

RESULTS

Using the RQA approach, we identified significant changes related to the AD phenotype at 4 m and/or 6 m in several areas of the rat DMLN including the BFB, Hippocampal fields CA1 and CA3, CG1, CG2, PrL, PtA, RSC, TeA, V1, V2. In addition, with age, brain activity of WT rats showed less predictability, while the AD rats presented reduced decline of predictability.

CONCLUSIONS

The results of this study demonstrate that RQA of rs-fMRI data is a potent approach that can detect subtle changes which might be missed by other methodologies due to the brain's non-linear dynamics. Moreover, this study provides helpful information about specific areas involved in AD pathology at very early stages of the disease in a very promising rat model of AD. Our results provide valuable information for the development of early detection methods and novel diagnosis tools for AD.

Identification of mild cognitive impairment using multimodal 3D imaging data and graph convolutional networks

Objective.Mild cognitive impairment (MCI) is a precursor stage of dementia characterized by mild cognitive decline in one or more cognitive domains, without meeting the criteria for dementia. MCI is considered a prodromal form of Alzheimer's disease (AD). Early identification of MCI is crucial for both intervention and prevention of AD. To accurately identify MCI, a novel multimodal 3D imaging data integration graph convolutional network (GCN) model is designed in this paper.Approach.The proposed model utilizes 3D-VGGNet to extract three-dimensional features from multimodal imaging data (such as structural magnetic resonance imaging and fluorodeoxyglucose positron emission tomography), which are then fused into feature vectors as the node features of a population graph. Non-imaging features of participants are combined with the multimodal imaging data to construct a population sparse graph. Additionally, in order to optimize the connectivity of the graph, we employed the pairwise attribute estimation （PAE） method to compute the edge weights based on non-imaging data, thereby enhancing the effectiveness of the graph structure. Subsequently, a population-based GCN integrates the structural and functional features of different modal images into the features of each participant for MCI classification.Main results.Experiments on the AD Neuroimaging Initiative demonstrated accuracies of 98.57%, 96.03%, and 96.83% for the normal controls (NC)-early MCI (EMCI), NC-late MCI (LMCI), and EMCI-LMCI classification tasks, respectively. The AUC, specificity, sensitivity, and F1-score are also superior to state-of-the-art models, demonstrating the effectiveness of the proposed model. Furthermore, the proposed model is applied to the ABIDE dataset for autism diagnosis, achieving an accuracy of 91.43% and outperforming the state-of-the-art models, indicating excellent generalization capabilities of the proposed model.Significance.This study demonstratesthe proposed model's ability to integrate multimodal imaging data and its excellent ability to recognize MCI. This will help achieve early warning for AD and intelligent diagnosis of other brain neurodegenerative diseases.

Differences between Alzheimer's disease and mild cognitive impairment using brain networks from magnetic resonance texture analysis

Several studies have aimed at identifying biomarkers in the initial phases of Alzheimer's disease (AD). Conversely, texture features, such as those from gray-level co-occurrence matrices (GLCMs), have highlighted important information from several types of medical images. More recently, texture-based brain networks have been shown to provide useful information in characterizing healthy individuals. However, no studies have yet explored the use of this type of network in the context of AD. This work aimed to employ texture brain networks to investigate the distinction between groups of patients with amnestic mild cognitive impairment (aMCI) and mild dementia due to AD, and a group of healthy subjects. Magnetic resonance (MR) images from the three groups acquired at two instances were used. Images were segmented and GLCM texture parameters were calculated for each region. Structural brain networks were generated using regions as nodes and the similarity among texture parameters as links, and graph theory was used to compute five network measures. An ANCOVA was performed for each network measure to assess statistical differences between groups. The thalamus showed significant differences between aMCI and AD patients for four network measures for the right hemisphere and one network measure for the left hemisphere. There were also significant differences between controls and AD patients for the left hippocampus, right superior parietal lobule, and right thalamus-one network measure each. These findings represent changes in the texture of these regions which can be associated with the cortical volume and thickness atrophies reported in the literature for AD. The texture networks showed potential to differentiate between aMCI and AD patients, as well as between controls and AD patients, offering a new tool to help understand these conditions and eventually aid early intervention and personalized treatment, thereby improving patient outcomes and advancing AD research.

The Combination of a Graph Neural Network Technique and Brain Imaging to Diagnose Neurological Disorders: A Review and Outlook

Neurological disorders (NDs), such as Alzheimer's disease, have been a threat to human health all over the world. It is of great importance to diagnose ND through combining artificial intelligence technology and brain imaging. A graph neural network (GNN) can model and analyze the brain, imaging from morphology, anatomical structure, function features, and other aspects, thus becoming one of the best deep learning models in the diagnosis of ND. Some researchers have investigated the application of GNN in the medical field, but the scope is broad, and its application to NDs is less frequent and not detailed enough. This review focuses on the research progress of GNNs in the diagnosis of ND. Firstly, we systematically investigated the GNN framework of ND, including graph construction, graph convolution, graph pooling, and graph prediction. Secondly, we investigated common NDs using the GNN diagnostic model in terms of data modality, number of subjects, and diagnostic accuracy. Thirdly, we discussed some research challenges and future research directions. The results of this review may be a valuable contribution to the ongoing intersection of artificial intelligence technology and brain imaging.

Texture-based brain networks for characterization of healthy subjects from MRI

Brain networks have been widely used to study the relationships between brain regions based on their dynamics using, e.g. fMRI or EEG, and to characterize their real physical connections using DTI. However, few studies have investigated brain networks derived from structural properties; and those have been based on cortical thickness or gray matter volume. The main objective of this work was to investigate the feasibility of obtaining useful information from brain networks derived from structural MRI, using texture features. We also wanted to verify if texture brain networks had any relation with established functional networks. T1-MR images were segmented using AAL and texture parameters from the gray-level co-occurrence matrix were computed for each region, for 760 subjects. Individual texture networks were used to evaluate the structural connections between regions of well-established functional networks; assess possible gender differences; investigate the dependence of texture network measures with age; and single out brain regions with different texture-network characteristics. Although around 70% of texture connections between regions belonging to the default mode, attention, and visual network were greater than the mean connection value, this effect was small (only between 7 and 15% of these connections were larger than one standard deviation), implying that texture-based morphology does not seem to subside function. This differs from cortical thickness-based morphology, which has been shown to relate to functional networks. Seventy-five out of 86 evaluated regions showed significant (ANCOVA, p < 0.05) differences between genders. Forty-four out of 86 regions showed significant (ANCOVA, p < 0.05) dependence with age; however, the R2 indicates that this is not a linear relation. Thalamus and putamen showed a very unique texture-wise structure compared to other analyzed regions. Texture networks were able to provide useful information regarding gender and age-related differences, as well as for singling out specific brain regions. We did not find a morphological texture-based subsidy for the evaluated functional brain networks. In the future, this approach will be extended to neurological patients to investigate the possibility of extracting biomarkers to help monitor disease evolution or treatment effectiveness.

Brain disease research based on functional magnetic resonance imaging data and machine learning: a review

Brain diseases, including neurodegenerative diseases and neuropsychiatric diseases, have long plagued the lives of the affected populations and caused a huge burden on public health. Functional magnetic resonance imaging (fMRI) is an excellent neuroimaging technology for measuring brain activity, which provides new insight for clinicians to help diagnose brain diseases. In recent years, machine learning methods have displayed superior performance in diagnosing brain diseases compared to conventional methods, attracting great attention from researchers. This paper reviews the representative research of machine learning methods in brain disease diagnosis based on fMRI data in the recent three years, focusing on the most frequent four active brain disease studies, including Alzheimer's disease/mild cognitive impairment, autism spectrum disorders, schizophrenia, and Parkinson's disease. We summarize these 55 articles from multiple perspectives, including the effect of the size of subjects, extracted features, feature selection methods, classification models, validation methods, and corresponding accuracies. Finally, we analyze these articles and introduce future research directions to provide neuroimaging scientists and researchers in the interdisciplinary fields of computing and medicine with new ideas for AI-aided brain disease diagnosis.

Human-Guided Functional Connectivity Network Estimation for Chronic Tinnitus Identification: A Modularity View

The functional connectivity network (FCN) has been used to achieve several remarkable advancements in the diagnosis of neuro-degenerative disorders. Therefore, it is imperative to accurately estimate biologically meaningful FCNs. Several efforts have been dedicated to this purpose by encoding biological priors. However, owing to the high complexity of the human brain, the estimation of an 'ideal' FCN remains an open problem. To the best of our knowledge, almost all existing studies lack the integration of domain expert knowledge, which limits their performance. In this study, we focused on incorporating domain expert knowledge into the FCN estimation from a modularity perspective. To achieve this, we presented a human-guided modular representation (MR) FCN estimation framework. Specifically, we designed an adversarial low-rank constraint to describe the module structure of FCNs under the guidance of domain expert knowledge (i.e., a predefined participant index). The chronic tinnitus (TIN) identification task based on the estimated FCNs was conducted to examine the proposed MR methods. Remarkably, MR significantly outperformed the baseline and state-of-the-art(SOTA) methods, achieving an accuracy of 92.11%. Moreover, post-hoc analysis revealed that the FCNs estimated by the proposed MR could highlight more biologically meaningful connections, which is beneficial for exploring the underlying mechanisms of TIN and diagnosing early TIN.

Early detection of COPD based on graph convolutional network and small and weakly labeled data

Chronic obstructive pulmonary disease (COPD) is a common disease with high morbidity and mortality, where early detection benefits the population. However, the early diagnosis rate of COPD is low due to the absence or slight early symptoms. In this paper, a novel method based on graph convolution network (GCN) for early detection of COPD is proposed, which uses small and weakly labeled chest computed tomography image data from the publicly available Danish Lung Cancer Screening Trial database. The key idea is to construct a graph using regions of interest randomly selected from the segmented lung parenchyma and then input it into the GCN model for COPD detection. In this way, the model can not only extract the feature information of each region of interest but also the topological structure information between regions of interest, that is, graph structure information. The proposed GCN model achieves an acceptable performance with an accuracy of 0.77 and an area under a curve of 0.81, which is higher than the previous studies on the same dataset. GCN model also outperforms several state-of-the-art methods trained at the same time. As far as we know, it is also the first time using the GCN model on this dataset for COPD detection.

IHGC-GAN: influence hypergraph convolutional generative adversarial network for risk prediction of late mild cognitive impairment based on imaging genetic data

Predicting disease progression in the initial stage to implement early intervention and treatment can effectively prevent the further deterioration of the condition. Traditional methods for medical data analysis usually fail to perform well because of their incapability for mining the correlation pattern of pathogenies. Therefore, many calculation methods have been excavated from the field of deep learning. In this study, we propose a novel method of influence hypergraph convolutional generative adversarial network (IHGC-GAN) for disease risk prediction. First, a hypergraph is constructed with genes and brain regions as nodes. Then, an influence transmission model is built to portray the associations between nodes and the transmission rule of disease information. Third, an IHGC-GAN method is constructed based on this model. This method innovatively combines the graph convolutional network (GCN) and GAN. The GCN is used as the generator in GAN to spread and update the lesion information of nodes in the brain region-gene hypergraph. Finally, the prediction accuracy of the method is improved by the mutual competition and repeated iteration between generator and discriminator. This method can not only capture the evolutionary pattern from early mild cognitive impairment (EMCI) to late MCI (LMCI) but also extract the pathogenic factors and predict the deterioration risk from EMCI to LMCI. The results on the two datasets indicate that the IHGC-GAN method has better prediction performance than the advanced methods in a variety of indicators.

Predicting Brain Amyloid-β PET Grades with Graph Convolutional Networks Based on Functional MRI and Multi-Level Functional Connectivity

BACKGROUND

The detection of amyloid-β (Aβ) deposition in the brain provides crucial evidence in the clinical diagnosis of Alzheimer's disease (AD). However, the current positron emission tomography (PET)-based brain Aβ examination suffers from the problems of coarse visual inspection (in many cases, with 2-class stratification) and high scanning cost.

OBJECTIVE

1) To characterize the non-binary Aβ deposition levels in the AD continuum based on clustering of PET data, and 2) to explore the feasibility of predicting individual Aβ deposition grades with non-invasive functional magnetic resonance imaging (fMRI).

METHODS

1) Individual whole-brain Aβ-PET images from the OASIS-3 dataset (N = 258) were grouped into three clusters (grades) with t-SNE and k-means. The demographical data as well as global and regional standard uptake value ratios (SUVRs) were compared among the three clusters with Chi-square tests or ANOVA tests. 2) From resting-state fMRI, both conventional functional connectivity (FC) and high-order FC networks were constructed and the topological architectures of the two networks were jointly learned with graph convolutional networks (GCNs) to predict the Aβ-PET grades for each individual.

RESULTS

We found three clearly separated clusters, indicating three Aβ-PET grades. There were significant differences in gender, age, cognitive ability, APOE type, as well as global and regional SUVRs among the three grades we found. The prediction of Aβ-PET grades with GCNs on FC for the 258 participants in the AD continuum reached a satisfactory averaged accuracy (78.8%) in the two-class classification tasks.

CONCLUSION

The results demonstrated the feasibility of using deep learning on a non-invasive brain functional imaging technique to approximate PET-based Aβ deposition grading.

Multimodal Brain Connectomics-Based Prediction of Parkinson’s Disease Using Graph Attention Networks

Background

A multimodal connectomic analysis using diffusion and functional MRI can provide complementary information on the structure–function network dynamics involved in complex neurodegenerative network disorders such as Parkinson’s disease (PD). Deep learning-based graph neural network models generate higher-level embeddings that could capture intricate structural and functional regional interactions related to PD.

Objective

This study aimed at investigating the role of structure–function connections in predicting PD, by employing an end-to-end graph attention network (GAT) on multimodal brain connectomes along with an interpretability framework.

Methods

The proposed GAT model was implemented to generate node embeddings from the structural connectivity matrix and multimodal feature set containing morphological features and structural and functional network features of PD patients and healthy controls. Graph classification was performed by extracting topmost node embeddings, and the interpretability framework was implemented using saliency analysis and attention maps. Moreover, we also compared our model with unimodal models as well as other state-of-the-art models.

Results

Our proposed GAT model with a multimodal feature set demonstrated superior classification performance over a unimodal feature set. Our model demonstrated superior classification performance over other comparative models, with 10-fold CV accuracy and an F1 score of 86% and a moderate test accuracy of 73%. The interpretability framework highlighted the structural and functional topological influence of motor network and cortico-subcortical brain regions, among which structural features were correlated with onset of PD. The attention maps showed dependency between large-scale brain regions based on their structural and functional characteristics.

Conclusion

Multimodal brain connectomic markers and GAT architecture can facilitate robust prediction of PD pathology and provide an attention mechanism-based interpretability framework that can highlight the pathology-specific relation between brain regions.

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

With the advances of data-driven machine learning research, a wide variety of prediction problems have been tackled. It has become critical to explore how machine learning and specifically deep learning methods can be exploited to analyse healthcare data. A major limitation of existing methods has been the focus on grid-like data; however, the structure of physiological recordings are often irregular and unordered, which makes it difficult to conceptualise them as a matrix. As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interacting nodes connected by edges whose weights can be determined by either temporal associations or anatomical junctions. In this survey, we thoroughly review the different types of graph architectures and their applications in healthcare. We provide an overview of these methods in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure, and electrical-based analysis. We also outline the limitations of existing techniques and discuss potential directions for future research.