Associating Multi-Modal Brain Imaging Phenotypes and Genetic Risk Factors via a Dirty Multi-Task Learning Method

Exploring Brain Imaging and Genetic Risk Factors in Different Progression States of Alzheimer's Disease Through OSnetNMF-Based Methods

Alzheimer's disease (AD) is a neurodegenerative disease with no effective treatment, often preceded by mild cognitive impairment (MCI). Multimodal imaging genetics integrates imaging and genetic data to gain a deeper understanding of disease progression and individual variations. This study focuses on exploring the mechanisms that drive the transition from normal cognition to MCI and ultimately to AD. As an effective joint feature extraction and dimensionality reduction method, non-negative matrix factorization (NMF) and its improved variants, particularly the network-based non-negative matrix factorization (netNMF), have been widely used in multimodal analysis to mine brain imaging and genetic data by considering the interactions between different features. However, many of these methods overlook the importance of the coefficient matrix and do not address issues related to data accuracy and feature redundancy. To address these limitations, we propose an orthogonal sparse network non-negative matrix factorization (OSnetNMF) algorithm, which introduces orthogonal and sparse constraints based on netNMF. By establishing linear relationships between structural magnetic resonance imaging (sMRI) and corresponding gene expression data, OSnetNMF reduces feature redundancy and decreases correlation between data, resulting in more accurate and reliable biomarker extraction. Experiments demonstrate that the OSnetNMF algorithm can accurately identify risk regions of interest (ROIs) and key genes that characterize AD progression, revealing significant trends in ROI pairs such as l4thVen-HIF1A, rBst-MPO, and rBst-PTK2B. Comparative experiments show that the improved algorithm outperforms traditional methods, identifying more disease-related biomarkers and achieving better reconstruction performance.

CE-GAN: Community Evolutionary Generative Adversarial Network for Alzheimer's Disease Risk Prediction

In the studies of neurodegenerative diseases such as Alzheimer's Disease (AD), researchers often focus on the associations among multi-omics pathogeny based on imaging genetics data. However, current studies overlook the communities in brain networks, leading to inaccurate models of disease development. This paper explores the developmental patterns of AD from the perspective of community evolution. We first establish a mathematical model to describe functional degeneration in the brain as the community evolution driven by entropy information propagation. Next, we propose an interpretable Community Evolutionary Generative Adversarial Network (CE-GAN) to predict disease risk. In the generator of CE-GAN, community evolutionary convolutions are designed to capture the evolutionary patterns of AD. The experiments are conducted using functional magnetic resonance imaging (fMRI) data and single nucleotide polymorphism (SNP) data. CE-GAN achieves 91.67% accuracy and 91.83% area under curve (AUC) in AD risk prediction tasks, surpassing advanced methods on the same dataset. In addition, we validated the effectiveness of CE-GAN for pathogeny extraction. The source code of this work is available at https://github.com/fmri123456/CE-GAN.

Deep Self-Reconstruction Fusion Similarity Hashing for the Diagnosis of Alzheimer's Disease on Multi-Modal Data

The pathogenesis of Alzheimer's disease (AD) is extremely intricate, which makes AD patients almost incurable. Recent studies have demonstrated that analyzing multi-modal data can offer a comprehensive perspective on the different stages of AD progression, which is beneficial for early diagnosis of AD. In this paper, we propose a deep self-reconstruction fusion similarity hashing (DS-FSH) method to effectively capture the AD-related biomarkers from the multi-modal data and leverage them to diagnose AD. Given that most existing methods ignore the topological structure of the data, a deep self-reconstruction model based on random walk graph regularization is designed to reconstruct the multi-modal data, thereby learning the nonlinear relationship between samples. Additionally, a fused similarity hash based on anchor graph is proposed to generate discriminative binary hash codes for multi-modal reconstructed data. This allows sample fused similarity to be effectively modeled by a fusion similarity matrix based on anchor graph while modal correlation can be approximated by Hamming distance. Especially, extracted features from the multi-modal data are classified using deep sparse autoencoders classifier. Finally, experiments conduct on the AD Neuroimaging Initiative database show that DS-FSH outperforms comparable methods of AD classification. To conclude, DS-FSH identifies multi-modal features closely associated with AD, which are expected to contribute significantly to understanding of the pathogenesis of AD.

Hypergraph Structural Information Aggregation Generative Adversarial Networks for Diagnosis and Pathogenetic Factors Identification of Alzheimer's Disease With Imaging Genetic Data

Alzheimer's disease (AD) is a neurodegenerative disease with profound pathogenetic causes. Imaging genetic data analysis can provide comprehensive insights into its causes. To fully utilize the multi-level information in the data, this article proposes a hypergraph structural information aggregation model, and constructs a novel deep learning method named hypergraph structural information aggregation generative adversarial networks (HSIA-GANs) for the automatic sample classification and accurate feature extraction. Specifically, HSIA-GAN is composed of generator and discriminator. The generator has three main functions. First, vertex graph and edge graph are constructed based on the input hypergraph to present the low-order relations. Second, the low-order structural information of hypergraph is extracted by the designed vertex convolution layers and edge convolution layers. Finally, the synthetic hypergraph is generated as the input of the discriminator. The discriminator can extract the high-order structural information directly from hypergraph through vertex-edge convolution, fuse the high and low-order structural information, and finalize the results through the full connection (FC) layers. Based on the data acquired from AD neuroimaging initiative, HSIA-GAN shows significant advantages in three classification tasks, and extracts discriminant features conducive to better disease classification.

Identifying frequency-dependent imaging genetic associations via hypergraph-structured multi-task sparse canonical correlation analysis

Identifying complex associations between genetic variations and imaging phenotypes is a challenging task in the research of brain imaging genetics. The previous study has proved that neuronal oscillations within distinct frequency bands are derived from frequency-dependent genetic modulation. Thus it is meaningful to explore frequency-dependent imaging genetic associations, which may give important insights into the pathogenesis of brain disorders. In this work, the hypergraph-structured multi-task sparse canonical correlation analysis (HS-MTSCCA) was developed to explore the associations between multi-frequency imaging phenotypes and single-nucleotide polymorphisms (SNPs). Specifically, we first created a hypergraph for the imaging phenotypes of each frequency and the SNPs, respectively. Then, a new hypergraph-structured constraint was proposed to learn high-order relationships among features in each hypergraph, which can introduce biologically meaningful information into the model. The frequency-shared and frequency-specific imaging phenotypes and SNPs could be identified using the multi-task learning framework. We also proposed a useful strategy to tackle this algorithm and then demonstrated its convergence. The proposed method was evaluated on four simulation datasets and a real schizophrenia dataset. The experimental results on synthetic data showed that HS-MTSCCA outperforms the other competing methods according to canonical correlation coefficients, canonical weights, and cosine similarity. And the results on real data showed that HS-MTSCCA could obtain superior canonical coefficients and canonical weights. Furthermore, the identified frequency-shared and frequency-specific biomarkers could provide more interesting and meaningful information, demonstrating that HS-MTSCCA is a powerful method for brain imaging genetics.

Graph-Based Fusion of Imaging, Genetic and Clinical Data for Degenerative Disease Diagnosis

Graph learning methods have achieved noteworthy performance in disease diagnosis due to their ability to represent unstructured information such as inter-subject relationships. While it has been shown that imaging, genetic and clinical data are crucial for degenerative disease diagnosis, existing methods rarely consider how best to use their relationships. How best to utilize information from imaging, genetic and clinical data remains a challenging problem. This study proposes a novel graph-based fusion (GBF) approach to meet this challenge. To extract effective imaging-genetic features, we propose an imaging-genetic fusion module which uses an attention mechanism to obtain modality-specific and joint representations within and between imaging and genetic data. Then, considering the effectiveness of clinical information for diagnosing degenerative diseases, we propose a multi-graph fusion module to further fuse imaging-genetic and clinical features, which adopts a learnable graph construction strategy and a graph ensemble method. Experimental results on two benchmarks for degenerative disease diagnosis (Alzheimers Disease Neuroimaging Initiative and Parkinson's Progression Markers Initiative) demonstrate its effectiveness compared to state-of-the-art graph-based methods. Our findings should help guide further development of graph-based models for dealing with imaging, genetic and clinical data.

Deep multimodality-disentangled association analysis network for imaging genetics in neurodegenerative diseases

Imaging genetics is a crucial tool that is applied to explore potentially disease-related biomarkers, particularly for neurodegenerative diseases (NDs). With the development of imaging technology, the association analysis between multimodal imaging data and genetic data is gradually being concerned by a wide range of imaging genetics studies. However, multimodal data are fused first and then correlated with genetic data in traditional methods, which leads to an incomplete exploration of their common and complementary information. In addition, the inaccurate formulation in the complex relationships between imaging and genetic data and information loss caused by missing multimodal data are still open problems in imaging genetics studies. Therefore, in this study, a deep multimodality-disentangled association analysis network (DMAAN) is proposed to solve the aforementioned issues and detect the disease-related biomarkers of NDs simultaneously. First, the imaging data are nonlinearly projected into a latent space and imaging representations can be achieved. The imaging representations are further disentangled into common and specific parts by using a multimodal-disentangled module. Second, the genetic data are encoded to achieve genetic representations, and then, the achieved genetic representations are nonlinearly mapped to the common and specific imaging representations to build nonlinear associations between imaging and genetic data through an association analysis module. Moreover, modality mask vectors are synchronously synthesized to integrate the genetic and imaging data, which helps the following disease diagnosis. Finally, the proposed method achieves reasonable diagnosis performance via a disease diagnosis module and utilizes the label information to detect the disease-related modality-shared and modality-specific biomarkers. Furthermore, the genetic representation can be used to impute the missing multimodal data with our learning strategy. Two publicly available datasets with different NDs are used to demonstrate the effectiveness of the proposed DMAAN. The experimental results show that the proposed DMAAN can identify the disease-related biomarkers, which suggests the proposed DMAAN may provide new insights into the pathological mechanism and early diagnosis of NDs. The codes are publicly available at https://github.com/Meiyan88/DMAAN.

A multi-task SCCA method for brain imaging genetics and its application in neurodegenerative diseases

BACKGROUND AND OBJECTIVES

In brain imaging genetics, multi-task sparse canonical correlation analysis (MTSCCA) is effective to study the bi-multivariate associations between genetic variations such as single nucleotide polymorphisms (SNPs) and multi-modal imaging quantitative traits (QTs). However, most existing MTSCCA methods are neither supervised nor capable of distinguishing the shared patterns of multi-modal imaging QTs from the specific patterns.

METHODS

A new diagnosis-guided MTSCCA (DDG-MTSCCA) with parameter decomposition and graph-guided pairwise group lasso penalty was proposed. Specifically, the multi-tasking modeling paradigm enables us to comprehensively identify risk genetic loci by jointly incorporating multi-modal imaging QTs. The regression sub-task was raised to guide the selection of diagnosis-related imaging QTs. To reveal the diverse genetic mechanisms, the parameter decomposition and different constraints were utilized to facilitate the identification of modality-consistent and -specific genotypic variations. Besides, a network constraint was added to find out meaningful brain networks. The proposed method was applied to synthetic data and two real neuroimaging data sets respectively from Alzheimer's disease neuroimaging initiative (ADNI) and Parkinson's progression marker initiative (PPMI) databases.

RESULTS

Compared with the competitive methods, the proposed method exhibited higher or comparable canonical correlation coefficients (CCCs) and better feature selection results. In particular, in the simulation study, DDG-MTSCCA showed the best anti-noise ability and achieved the highest average hit rate, about 25% higher than MTSCCA. On the real data of Alzheimer's disease (AD) and Parkinson's disease (PD), our method obtained the highest average testing CCCs, about 40% ∼ 50% higher than MTSCCA. Especially, our method could select more comprehensive feature subsets, and the top five SNPs and imaging QTs were all disease-related. The ablation experimental results also demonstrated the significance of each component in the model, i.e., the diagnosis guidance, parameter decomposition, and network constraint.

CONCLUSIONS

These results on simulated data, ADNI and PPMI cohorts suggested the effectiveness and generalizability of our method in identifying meaningful disease-related markers. DDG-MTSCCA could be a powerful tool in brain imaging genetics, worthy of in-depth study.

Associating brain imaging phenotypes and genetic risk factors via a hypergraph based netNMF method

Abstract

Alzheimer's disease (AD) is a severe neurodegenerative disease for which there is currently no effective treatment. Mild cognitive impairment (MCI) is an early disease that may progress to AD. The effective diagnosis of AD and MCI in the early stage has important clinical significance.

Methods

To this end, this paper proposed a hypergraph-based netNMF (HG-netNMF) algorithm for integrating structural magnetic resonance imaging (sMRI) of AD and MCI with corresponding gene expression profiles.

Results

Hypergraph regularization assumes that regions of interest (ROIs) and genes were located on a non-linear low-dimensional manifold and can capture the inherent prevalence of two modalities of data and mined high-order correlation features of the two data. Further, this paper used the HG-netNMF algorithm to construct a brain structure connection network and a protein interaction network (PPI) with potential role relationships, mine the risk (ROI) and key genes of both, and conduct a series of bioinformatics analyses.

Conclusion

Finally, this paper used the risk ROI and key genes of the AD and MCI groups to construct diagnostic models. The AUC of the AD group and MCI group were 0.8 and 0.797, respectively.

A novel generation adversarial network framework with characteristics aggregation and diffusion for brain disease classification and feature selection

Imaging genetics provides unique insights into the pathological studies of complex brain diseases by integrating the characteristics of multi-level medical data. However, most current imaging genetics research performs incomplete data fusion. Also, there is a lack of effective deep learning methods to analyze neuroimaging and genetic data jointly. Therefore, this paper first constructs the brain region-gene networks to intuitively represent the association pattern of pathogenetic factors. Second, a novel feature information aggregation model is constructed to accurately describe the information aggregation process among brain region nodes and gene nodes. Finally, a deep learning method called feature information aggregation and diffusion generative adversarial network (FIAD-GAN) is proposed to efficiently classify samples and select features. We focus on improving the generator with the proposed convolution and deconvolution operations, with which the interpretability of the deep learning framework has been dramatically improved. The experimental results indicate that FIAD-GAN can not only achieve superior results in various disease classification tasks but also extract brain regions and genes closely related to AD. This work provides a novel method for intelligent clinical decisions. The relevant biomedical discoveries provide a reliable reference and technical basis for the clinical diagnosis, treatment and pathological analysis of disease.

A framework for deep multitask learning with multiparametric magnetic resonance imaging for the joint prediction of histological characteristics in breast cancer

The clinical management and decision-making process related to breast cancer are based on multiple histological indicators. This study aims to jointly predict the Ki-67 expression level, luminal A subtype and histological grade molecular biomarkers using a new deep multitask learning method with multiparametric magnetic resonance imaging. A multitask learning network structure was proposed by introducing a common-task layer and task-specific layers to learn the high-level features that are common to all tasks and related to a specific task, respectively. A network pretrained with knowledge from the ImageNet dataset was used and fine-tuned with MRI data. Information from multiparametric MR images was fused using the strategy at the feature and decision levels. The area under the receiver operating characteristic curve (AUC) was used to measure model performance. For single-task learning using a single image series, the deep learning model generated AUCs of 0.752, 0.722, and 0.596 for the Ki-67, luminal A and histological grade prediction tasks, respectively. The performance was improved by freezing the first 5 convolutional layers, using 20% shared layers and fusing multiparametric series at the feature level, which achieved AUCs of 0.819, 0.799 and 0.747 for Ki-67, luminal A and histological grade prediction tasks, respectively. Our study showed advantages in jointly predicting correlated clinical biomarkers using a deep multitask learning framework with an appropriate number of fine-tuned convolutional layers by taking full advantage of common and complementary imaging features. Multiparametric image series-based multitask learning could be a promising approach for the multiple clinical indicator-based management of breast cancer.

Imaging Genetics in Epilepsy: Current Knowledge and New Perspectives

Epilepsy is a neurological network disease with genetics playing a much greater role than was previously appreciated. Unfortunately, the relationship between genetic basis and imaging phenotype is by no means simple. Imaging genetics integrates multidimensional datasets within a unified framework, providing a unique opportunity to pursue a global vision for epilepsy. This review delineates the current knowledge of underlying genetic mechanisms for brain networks in different epilepsy syndromes, particularly from a neural developmental perspective. Further, endophenotypes and their potential value are discussed. Finally, we highlight current challenges and provide perspectives for the future development of imaging genetics in epilepsy.

A review ofimaging genetics in Alzheimer's disease

Determining the association between genetic variation and phenotype is a key step to study the mechanism of Alzheimer's disease (AD), laying the foundation for studying drug therapies and biomarkers. AD is the most common type of dementia in the aged population. At present, three early-onset AD genes (APP, PSEN1, PSEN2) and one late-onset AD susceptibility gene apolipoprotein E (APOE) have been determined. However, the pathogenesis of AD remains unknown. Imaging genetics, an emerging interdisciplinary field, is able to reveal the complex mechanisms from the genetic level to human cognition and mental disorders via macroscopic intermediates. This paper reviews methods of establishing genotype-phenotype to explore correlations, including sparse canonical correlation analysis, sparse reduced rank regression, sparse partial least squares and so on. We found that most research work did poorly in supervised learning and exploring the nonlinear relationship between SNP-QT.

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.

Detecting Biomarkers of Alzheimer's Disease Based on Multi-constrained Uncertainty-Aware Adaptive Sparse Multi-view Canonical Correlation Analysis

Image genetics mainly explores the pathogenesis of Alzheimer's disease (AD) by studying the relationship between genetic data (such as SNP, gene expression data, and DNA methylation) and imaging data (such as structural MRI (sMRI), fMRI, and PET). Most of the existing research on brain imaging genomics uses two-way or three-way bi-multivariate methods to explore the correlation analysis between genes and brain imaging. However, many of these methods are still affected by the gradient domination or cannot take into account the effect of feature redundancy on the results, so that the typical correlation coefficient and program running speed are not significantly improved. In order to solve the above problems, this paper proposes a multi-constrained uncertainty-aware adaptive sparse multi-view canonical correlation analysis method (MC-unAdaSMCCA) to explore associations among SNPs, gene expression data, and sMRI; that is, based on traditional unAdaSMCCA, orthogonal constraints are imposed on the weights of the three data features through linear programming, which can reduce the redundancy of feature weights to improve the correlation between the data and reduce the complexity of the algorithm to significantly speed up the running speed of the program. Three adaptive sparse multi-view canonical correlation analysis methods are used as benchmarks to evaluate the difference between real neuroimaging data and synthetic data. Compared with the other three methods, our proposed method has obtained better or comparable typical correlation coefficients and typical weights. Moreover, the following experimental results show that the MC-unAdaSMCCA method cannot only identify biomarkers related to AD and mild cognitive impairment (MCI), but also has a strong ability to resist noise and process high-dimensional data. Therefore, our proposed method provides a reliable approach to multi-modal imaging genetic researches.

Detecting Risk Gene and Pathogenic Brain Region in EMCI Using a Novel GERF Algorithm Based on Brain Imaging and Genetic Data

Fusion analysis of disease-related multi-modal data is becoming increasingly important to illuminate the pathogenesis of complex brain diseases. However, owing to the small amount and high dimension of multi-modal data, current machine learning methods do not fully achieve the high veracity and reliability of fusion feature selection. In this paper, we propose a genetic-evolutionary random forest (GERF) algorithm to discover the risk genes and disease-related brain regions of early mild cognitive impairment (EMCI) based on the genetic data and resting-state functional magnetic resonance imaging (rs-fMRI) data. Classical correlation analysis method is used to explore the association between brain regions and genes, and fusion features are constructed. The genetic-evolutionary idea is introduced to enhance the classification performance, and to extract the optimal features effectively. The proposed GERF algorithm is evaluated by the public Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and the results show that the algorithm achieves satisfactory classification accuracy in small sample learning. Moreover, we compare the GERF algorithm with other methods to prove its superiority. Furthermore, we propose the overall framework of detecting pathogenic factors, which can be accurately and efficiently applied to the multi-modal data analysis of EMCI and be able to extend to other diseases. This work provides a novel insight for early diagnosis and clinicopathologic analysis of EMCI, which facilitates clinical medicine to control further deterioration of diseases and is good for the accurate electric shock using transcranial magnetic stimulation.

Relation-Induced Multi-Modal Shared Representation Learning for Alzheimer's Disease Diagnosis

The fusion of multi-modal data (e.g., magnetic resonance imaging (MRI) and positron emission tomography (PET)) has been prevalent for accurate identification of Alzheimer's disease (AD) by providing complementary structural and functional information. However, most of the existing methods simply concatenate multi-modal features in the original space and ignore their underlying associations which may provide more discriminative characteristics for AD identification. Meanwhile, how to overcome the overfitting issue caused by high-dimensional multi-modal data remains appealing. To this end, we propose a relation-induced multi-modal shared representation learning method for AD diagnosis. The proposed method integrates representation learning, dimension reduction, and classifier modeling into a unified framework. Specifically, the framework first obtains multi-modal shared representations by learning a bi-directional mapping between original space and shared space. Within this shared space, we utilize several relational regularizers (including feature-feature, feature-label, and sample-sample regularizers) and auxiliary regularizers to encourage learning underlying associations inherent in multi-modal data and alleviate overfitting, respectively. Next, we project the shared representations into the target space for AD diagnosis. To validate the effectiveness of our proposed approach, we conduct extensive experiments on two independent datasets (i.e., ADNI-1 and ADNI-2), and the experimental results demonstrate that our proposed method outperforms several state-of-the-art methods.

Identifying associations among genomic, proteomic and imaging biomarkers via adaptive sparse multi-view canonical correlation analysis

To uncover the genetic underpinnings of brain disorders, brain imaging genomics usually jointly analyzes genetic variations and imaging measurements. Meanwhile, other biomarkers such as proteomic expressions can also carry valuable complementary information. Therefore, it is necessary yet challenging to investigate the underlying relationships among genetic variations, proteomic expressions, and neuroimaging measurements, which stands a chance of gaining new insights into the pathogenesis of brain disorders. Given multiple types of biomarkers, using sparse multi-view canonical correlation analysis (SMCCA) and its variants to identify the multi-way associations is straightforward. However, due to the gradient domination issue caused by the naive fusion of multiple SCCA objectives, SMCCA is suboptimal. In this paper, we proposed two adaptive SMCCA (AdaSMCCA) methods, i.e. the robustness-aware AdaSMCCA and the uncertainty-aware AdaSMCCA, to analyze the complicated associations among genetic, proteomic, and neuroimaging biomarkers. We also imposed a data-driven feature grouping penalty to the genetic data with aim to uncover the joint inheritance of neighboring genetic variations. An efficient optimization algorithm, which is guaranteed to converge, was provided. Using two state-of-the-art SMCCA as benchmarks, we evaluated robustness-aware AdaSMCCA and uncertainty-aware AdaSMCCA on both synthetic data and real neuroimaging, proteomics, and genetic data. Both proposed methods obtained higher associations and cleaner canonical weight profiles than comparison methods, indicating their promising capability for association identification and feature selection. In addition, the subsequent analysis showed that the identified biomarkers were related to Alzheimer's disease, demonstrating the power of our methods in identifying multi-way bi-multivariate associations among multiple heterogeneous biomarkers.