Search

Multimodal neuroimaging modeling has becomes a widely used approach but confronts considerable challenges due to heterogeneity, which encompasses variability in data types, scales, and formats across modalities. This variability necessitates the deployment of advanced computational methods to integrate and interpret these diverse datasets within a cohesive analytical framework. In our research, we amalgamate functional magnetic resonance imaging, diffusion tensor imaging, and structural MRI into a cohesive framework. This integration capitalizes on the unique strengths of each modality and their inherent interconnections, aiming for a comprehensive understanding of the brain's connectivity and anatomical characteristics. Utilizing the Glasser atlas for parcellation, we integrate imaging derived features from various modalities: functional connectivity from fMRI, structural connectivity from DTI, and anatomical features from sMRI within consistent regions. Our approach incorporates a masking strategy to differentially weight neural connections, thereby facilitating a holistic amalgamation of multimodal imaging data. This technique enhances interpretability at connectivity level, transcending traditional analyses centered on singular regional attributes. The model is applied to the Human Connectome Project's Development study to elucidate the associations between multimodal imaging and cognitive functions throughout youth. The analysis demonstrates improved predictive accuracy and uncovers crucial anatomical features and essential neural connections, deepening our understanding of brain structure and function.

Alzheimer's disease (AD) progresses from asymptomatic changes to clinical symptoms, emphasizing the importance of early detection for proper treatment. Functional magnetic resonance imaging (fMRI), particularly dynamic functional network connectivity (dFNC), has emerged as an important biomarker for AD. Nevertheless, studies probing at-risk subjects in the pre-symptomatic stage using dFNC are limited. To identify at-risk subjects and understand alterations of dFNC in different stages, we leverage deep learning advancements and introduce a transformer-convolution framework for predicting at-risk subjects based on dFNC, incorporating spatial-temporal self-attention to capture brain network dependencies and temporal dynamics. Our model significantly outperforms other popular machine learning methods. By analyzing individuals with diagnosed AD and mild cognitive impairment (MCI), we studied the AD progression and observed a higher similarity between MCI and asymptomatic AD. The interpretable analysis highlights the cognitive-control network's diagnostic importance, with the model focusing on intra-visual domain dFNC when predicting asymptomatic AD subjects., Comment: Accepted by EMBC 2024

Schizophrenia (SZ) is a severe brain disorder marked by diverse cognitive impairments, abnormalities in brain structure, function, and genetic factors. Its complex symptoms and overlap with other psychiatric conditions challenge traditional diagnostic methods, necessitating advanced systems to improve precision. Existing research studies have mostly focused on imaging data, such as structural and functional MRI, for SZ diagnosis. There has been less focus on the integration of genomic features despite their potential in identifying heritable SZ traits. In this study, we introduce a Multi-modal Imaging Genomics Transformer (MIGTrans), that attentively integrates genomics with structural and functional imaging data to capture SZ-related neuroanatomical and connectome abnormalities. MIGTrans demonstrated improved SZ classification performance with an accuracy of 86.05% (+/- 0.02), offering clear interpretations and identifying significant genomic locations and brain morphological/connectivity patterns associated with SZ., Comment: Accepted for presentation at the AI for Imaging Genomic Learning (AIIG) Workshop, MICCAI 2024

Amyloid-$\beta$ (A$\beta$) plaques in conjunction with hyperphosphorylated tau proteins in the form of neurofibrillary tangles are the two neuropathological hallmarks of Alzheimer's disease (AD). In particular, the accumulation of A$\beta$ plaques, as evinced by the A/T/N (amyloid/tau/neurodegeneration) framework, marks the initial stage. Thus, the identification of individuals with A$\beta$ positivity could enable early diagnosis and potentially lead to more effective interventions. Deep learning methods relying mainly on amyloid PET images have been employed to this end. However, PET imaging has some disadvantages, including the need of radiotracers and expensive acquisitions. Hence, in this work, we propose a novel multimodal approach that integrates information from structural, functional, and diffusion MRI data to discriminate A$\beta$ status in the AD continuum. Our method achieved an accuracy of $0.762\pm0.04$. Furthermore, a \textit{post-hoc} explainability analysis (guided backpropagation) was performed to retrieve the brain regions that most influenced the model predictions. This analysis identified some key regions that were common across modalities, some of which were well-established AD-discriminative biomarkers and related to A$\beta$ deposition, such as the hippocampus, thalamus, precuneus, and cingulate gyrus. Hence, our study demonstrates the potential viability of MRI-based characterization of A$\beta$ status, paving the way for further research in this domain., Comment: 15 pages, 3 figures, submitted to a journal

Alzheimer's disease (AD) is the most prevalent form of dementia with a progressive decline in cognitive abilities. The AD continuum encompasses a prodormal stage known as Mild Cognitive Impairment (MCI), where patients may either progress to AD or remain stable. In this study, we leveraged structural and functional MRI to investigate the disease-induced grey matter and functional network connectivity changes. Moreover, considering AD's strong genetic component, we introduce SNPs as a third channel. Given such diverse inputs, missing one or more modalities is a typical concern of multimodal methods. We hence propose a novel deep learning-based classification framework where generative module employing Cycle GANs was adopted to impute missing data within the latent space. Additionally, we adopted an Explainable AI method, Integrated Gradients, to extract input features relevance, enhancing our understanding of the learned representations. Two critical tasks were addressed: AD detection and MCI conversion prediction. Experimental results showed that our model was able to reach the SOA in the classification of CN/AD reaching an average test accuracy of $0.926\pm0.02$. For the MCI task, we achieved an average prediction accuracy of $0.711\pm0.01$ using the pre-trained model for CN/AD. The interpretability analysis revealed significant grey matter modulations in cortical and subcortical brain areas well known for their association with AD. Moreover, impairments in sensory-motor and visual resting state network connectivity along the disease continuum, as well as mutations in SNPs defining biological processes linked to amyloid-beta and cholesterol formation clearance and regulation, were identified as contributors to the achieved performance. Overall, our integrative deep learning approach shows promise for AD detection and MCI prediction, while shading light on important biological insights., Comment: 27 pages, 7 figures, submitted to a journal

Neural networks, whice have had a profound effect on how researchers study complex phenomena, do so through a complex, nonlinear mathematical structure which can be difficult for human researchers to interpret. This obstacle can be especially salient when researchers want to better understand the emergence of particular model behaviors such as bias, overfitting, overparametrization, and more. In Neuroimaging, the understanding of how such phenomena emerge is fundamental to preventing and informing users of the potential risks involved in practice. In this work, we present a novel introspection framework for Deep Learning on Neuroimaging data, which exploits the natural structure of gradient computations via the singular value decomposition of gradient components during reverse-mode auto-differentiation. Unlike post-hoc introspection techniques, which require fully-trained models for evaluation, our method allows for the study of training dynamics on the fly, and even more interestingly, allow for the decomposition of gradients based on which samples belong to particular groups of interest. We demonstrate how the gradient spectra for several common deep learning models differ between schizophrenia and control participants from the COBRE study, and illustrate how these trajectories may reveal specific training dynamics helpful for further analysis.

Objective: fMRI and derived measures such as functional connectivity (FC) have been used to predict brain age, general fluid intelligence, psychiatric disease status, and preclinical neurodegenerative disease. However, it is not always clear that all demographic confounds, such as age, sex, and race, have been removed from fMRI data. Additionally, many fMRI datasets are restricted to authorized researchers, making dissemination of these valuable data sources challenging. Methods: We create a variational autoencoder (VAE)-based model, DemoVAE, to decorrelate fMRI features from demographics and generate high-quality synthetic fMRI data based on user-supplied demographics. We train and validate our model using two large, widely used datasets, the Philadelphia Neurodevelopmental Cohort (PNC) and Bipolar and Schizophrenia Network for Intermediate Phenotypes (BSNIP). Results: We find that DemoVAE recapitulates group differences in fMRI data while capturing the full breadth of individual variations. Significantly, we also find that most clinical and computerized battery fields that are correlated with fMRI data are not correlated with DemoVAE latents. An exception are several fields related to schizophrenia medication and symptom severity. Conclusion: Our model generates fMRI data that captures the full distribution of FC better than traditional VAE or GAN models. We also find that most prediction using fMRI data is dependent on correlation with, and prediction of, demographics. Significance: Our DemoVAE model allows for generation of high quality synthetic data conditioned on subject demographics as well as the removal of the confounding effects of demographics. We identify that FC-based prediction tasks are highly influenced by demographic confounds., Comment: 12 pages

Generative approaches for cross-modality transformation have recently gained significant attention in neuroimaging. While most previous work has focused on case-control data, the application of generative models to disorder-specific datasets and their ability to preserve diagnostic patterns remain relatively unexplored. Hence, in this study, we investigated the use of a generative adversarial network (GAN) in the context of Alzheimer's disease (AD) to generate functional network connectivity (FNC) and T1-weighted structural magnetic resonance imaging data from each other. We employed a cycle-GAN to synthesize data in an unpaired data transition and enhanced the transition by integrating weak supervision in cases where paired data were available. Our findings revealed that our model could offer remarkable capability, achieving a structural similarity index measure (SSIM) of $0.89 \pm 0.003$ for T1s and a correlation of $0.71 \pm 0.004$ for FNCs. Moreover, our qualitative analysis revealed similar patterns between generated and actual data when comparing AD to cognitively normal (CN) individuals. In particular, we observed significantly increased functional connectivity in cerebellar-sensory motor and cerebellar-visual networks and reduced connectivity in cerebellar-subcortical, auditory-sensory motor, sensory motor-visual, and cerebellar-cognitive control networks. Additionally, the T1 images generated by our model showed a similar pattern of atrophy in the hippocampal and other temporal regions of Alzheimer's patients.

Brain-computer interface systems and the recording of brain activity has garnered significant attention across a diverse spectrum of applications. EEG signals have emerged as a modality for recording neural electrical activity. Among the methodologies designed for feature extraction from EEG data, the method of RCSP has proven to be an approach, particularly in the context of MI tasks. RCSP exhibits efficacy in the discrimination and classification of EEG signals. In optimizing the performance of this method, our research extends to a comparative analysis with conventional CSP techniques, as well as optimized methodologies designed for similar applications. Notably, we employ the meta-heuristic multi-objective Strength Pareto Evolutionary Algorithm II (SPEA-II) as a pivotal component of our research paradigm. This is a state-of-the-art approach in the selection of an subset of channels from a multichannel EEG signal with MI tasks. Our main objective is to formulate an optimum channel selection strategy aimed at identifying the most pertinent subset of channels from the multi-dimensional electroencephalogram (EEG) signals. One of the primary objectives inherent to channel selection in the EEG signal analysis pertains to the reduction of the channel count, an approach that enhances user comfort when utilizing gel-based EEG electrodes. Additionally, within this research, we took benefit of ensemble learning models as a component of our decision-making. This technique serves to mitigate the challenges associated with overfitting, especially when confronted with an extensive array of potentially redundant EEG channels and data noise. Our findings not only affirm the performance of RCSP in MI-based BCI systems, but also underscore the significance of channel selection strategies and ensemble learning techniques in optimizing the performance of EEG signal classification.

Both functional and structural magnetic resonance imaging (fMRI and sMRI) are widely used for the diagnosis of mental disorder. However, combining complementary information from these two modalities is challenging due to their heterogeneity. Many existing methods fall short of capturing the interaction between these modalities, frequently defaulting to a simple combination of latent features. In this paper, we propose a novel Cross-Attentive Multi-modal Fusion framework (CAMF), which aims to capture both intra-modal and inter-modal relationships between fMRI and sMRI, enhancing multi-modal data representation. Specifically, our CAMF framework employs self-attention modules to identify interactions within each modality while cross-attention modules identify interactions between modalities. Subsequently, our approach optimizes the integration of latent features from both modalities. This approach significantly improves classification accuracy, as demonstrated by our evaluations on two extensive multi-modal brain imaging datasets, where CAMF consistently outperforms existing methods. Furthermore, the gradient-guided Score-CAM is applied to interpret critical functional networks and brain regions involved in schizophrenia. The bio-markers identified by CAMF align with established research, potentially offering new insights into the diagnosis and pathological endophenotypes of schizophrenia.

In the clinical treatment of mood disorders, the complex behavioral symptoms presented by patients and variability of patient response to particular medication classes can create difficulties in providing fast and reliable treatment when standard diagnostic and prescription methods are used. Increasingly, the incorporation of physiological information such as neuroimaging scans and derivatives into the clinical process promises to alleviate some of the uncertainty surrounding this process. Particularly, if neural features can help to identify patients who may not respond to standard courses of anti-depressants or mood stabilizers, clinicians may elect to avoid lengthy and side-effect-laden treatments and seek out a different, more effective course that might otherwise not have been under consideration. Previously, approaches for the derivation of relevant neuroimaging features work at only one scale in the data, potentially limiting the depth of information available for clinical decision support. In this work, we show that the utilization of multi spatial scale neuroimaging features - particularly resting state functional networks and functional network connectivity measures - provide a rich and robust basis for the identification of relevant medication class and non-responders in the treatment of mood disorders. We demonstrate that the generated features, along with a novel approach for fast and automated feature selection, can support high accuracy rates in the identification of medication class and non-responders as well as the identification of novel, multi-scale biomarkers.

Our understanding of learning dynamics of deep neural networks (DNNs) remains incomplete. Recent research has begun to uncover the mathematical principles underlying these networks, including the phenomenon of "Neural Collapse", where linear classifiers within DNNs converge to specific geometrical structures during late-stage training. However, the role of geometric constraints in learning extends beyond this terminal phase. For instance, gradients in fully-connected layers naturally develop a low-rank structure due to the accumulation of rank-one outer products over a training batch. Despite the attention given to methods that exploit this structure for memory saving or regularization, the emergence of low-rank learning as an inherent aspect of certain DNN architectures has been under-explored. In this paper, we conduct a comprehensive study of gradient rank in DNNs, examining how architectural choices and structure of the data effect gradient rank bounds. Our theoretical analysis provides these bounds for training fully-connected, recurrent, and convolutional neural networks. We also demonstrate, both theoretically and empirically, how design choices like activation function linearity, bottleneck layer introduction, convolutional stride, and sequence truncation influence these bounds. Our findings not only contribute to the understanding of learning dynamics in DNNs, but also provide practical guidance for deep learning engineers to make informed design decisions.

The high dimensionality and complexity of neuroimaging data necessitate large datasets to develop robust and high-performing deep learning models. However, the neuroimaging field is notably hampered by the scarcity of such datasets. In this work, we proposed a data augmentation and validation framework that utilizes dynamic forecasting with Long Short-Term Memory (LSTM) networks to enrich datasets. We extended multivariate time series data by predicting the time courses of independent component networks (ICNs) in both one-step and recursive configurations. The effectiveness of these augmented datasets was then compared with the original data using various deep learning models designed for chronological age prediction tasks. The results suggest that our approach improves model performance, providing a robust solution to overcome the challenges presented by the limited size of neuroimaging datasets., Comment: 4 PAGES, 3 FIGURES, CONFERENCE

Independent component analysis (ICA) is now a widely used solution for the analysis of multi-subject functional magnetic resonance imaging (fMRI) data. Independent vector analysis (IVA) generalizes ICA to multiple datasets, i.e., to multi-subject data, and in addition to higher-order statistical information in ICA, it leverages the statistical dependence across the datasets as an additional type of statistical diversity. As such, it preserves variability in the estimation of single-subject maps but its performance might suffer when the number of datasets increases. Constrained IVA is an effective way to bypass computational issues and improve the quality of separation by incorporating available prior information. Existing constrained IVA approaches often rely on user-defined threshold values to define the constraints. However, an improperly selected threshold can have a negative impact on the final results. This paper proposes two novel methods for constrained IVA: one using an adaptive-reverse scheme to select variable thresholds for the constraints and a second one based on a threshold-free formulation by leveraging the unique structure of IVA. We demonstrate that our solutions provide an attractive solution to multi-subject fMRI analysis both by simulations and through analysis of resting state fMRI data collected from 98 subjects -- the highest number of subjects ever used by IVA algorithms. Our results show that both proposed approaches obtain significantly better separation quality and model match while providing computationally efficient and highly reproducible solutions., Comment: 11 pages

The human brain has a complex, intricate functional architecture. While many studies primarily emphasize pairwise interactions, delving into high-order associations is crucial for a comprehensive understanding of how functional brain networks intricately interact beyond simple pairwise connections. Analyzing high-order statistics allows us to explore the nuanced and complex relationships across the brain, unraveling the heterogeneity and uncovering patterns of multilevel overlap on the psychosis continuum. Here, we employed high-order independent component analysis (ICA) plus multivariate information-theoretical metrics ($O$-information and $S$-information) to estimate high-order interaction to examine schizophrenia using resting-state fMRI. The results show that multiple brain regions networks may be altered in schizophrenia, such as temporal, subcortical, and higher-cognitive brain regions, and meanwhile, it also shows that revealed synergy gives more information than redundancy in diagnosing schizophrenia. All in all, we showed that high-order dependencies were altered in schizophrenia. Identification of these aberrant patterns will give us a new window to diagnose schizophrenia., Comment: 7 pages, 4 figures, Accepted to InfoCog@NeurIPS 2023 (https://sites.google.com/view/infocog-neurips-2023/home)

The Brain Imaging Data Structure (BIDS) is a community-driven standard for the organization of data and metadata from a growing range of neuroscience modalities. This paper is meant as a history of how the standard has developed and grown over time. We outline the principles behind the project, the mechanisms by which it has been extended, and some of the challenges being addressed as it evolves. We also discuss the lessons learned through the project, with the aim of enabling researchers in other domains to learn from the success of BIDS.

We present Predictive Sparse Manifold Transform (PSMT), a minimalistic, interpretable and biologically plausible framework for learning and predicting natural dynamics. PSMT incorporates two layers where the first sparse coding layer represents the input sequence as sparse coefficients over an overcomplete dictionary and the second manifold learning layer learns a geometric embedding space that captures topological similarity and dynamic temporal linearity in sparse coefficients. We apply PSMT on a natural video dataset and evaluate the reconstruction performance with respect to contextual variability, the number of sparse coding basis functions and training samples. We then interpret the dynamic topological organization in the embedding space. We next utilize PSMT to predict future frames compared with two baseline methods with a static embedding space. We demonstrate that PSMT with a dynamic embedding space can achieve better prediction performance compared to static baselines. Our work establishes that PSMT is an efficient unsupervised generative framework for prediction of future visual stimuli., Comment: Paper presented at the 1st Workshop on High-dimensional Learning Dynamics (HLD) at the 40th International Conference on Machine Learning (ICML) 2023, Honolulu, Hawaii, USA (https://sites.google.com/view/hidimlearning), 10 pages

Deep learning (DL) models have been popular due to their ability to learn directly from the raw data in an end-to-end paradigm, alleviating the concern of a separate error-prone feature extraction phase. Recent DL-based neuroimaging studies have also witnessed a noticeable performance advancement over traditional machine learning algorithms. But the challenges of deep learning models still exist because of the lack of transparency in these models for their successful deployment in real-world applications. In recent years, Explainable AI (XAI) has undergone a surge of developments mainly to get intuitions of how the models reached the decisions, which is essential for safety-critical domains such as healthcare, finance, and law enforcement agencies. While the interpretability domain is advancing noticeably, researchers are still unclear about what aspect of model learning a post hoc method reveals and how to validate its reliability. This paper comprehensively reviews interpretable deep learning models in the neuroimaging domain. Firstly, we summarize the current status of interpretability resources in general, focusing on the progression of methods, associated challenges, and opinions. Secondly, we discuss how multiple recent neuroimaging studies leveraged model interpretability to capture anatomical and functional brain alterations most relevant to model predictions. Finally, we discuss the limitations of the current practices and offer some valuable insights and guidance on how we can steer our future research directions to make deep learning models substantially interpretable and thus advance scientific understanding of brain disorders., Comment: 109 pages, 21 figures

Pairwise metrics are often employed to estimate statistical dependencies between brain regions, however they do not capture higher-order information interactions. It is critical to explore higher-order interactions that go beyond paired brain areas in order to better understand information processing in the human brain. To address this problem, we applied multivariate mutual information, specifically, Total Correlation and Dual Total Correlation to reveal higher-order information in the brain. In this paper, we estimate these metrics using matrix-based R\'enyi's entropy, which offers a direct and easily interpretable approach that is not limited by direct assumptions about probability distribution functions of multivariate time series. We applied these metrics to resting-state fMRI data in order to examine higher-order interactions in the brain. Our results showed that the higher-order information interactions captured increase gradually as the interaction order increases. Furthermore, we observed a gradual increase in the correlation between the Total Correlation and Dual Total Correlation as the interaction order increased. In addition, the significance of Dual Total Correlation values compared to Total Correlation values also indicate that the human brain exhibits synergy dominance during the resting state., Comment: 5 pages, 3 figures; Accepted to Data Science and Learning Workshop: Unraveling the Brain. A satellite workshop of ICASSP 2023

Independent component analysis (ICA) of multi-subject functional magnetic resonance imaging (fMRI) data has proven useful in providing a fully multivariate summary that can be used for multiple purposes. ICA can identify patterns that can discriminate between healthy controls (HC) and patients with various mental disorders such as schizophrenia (Sz). Temporal functional network connectivity (tFNC) obtained from ICA can effectively explain the interactions between brain networks. On the other hand, dictionary learning (DL) enables the discovery of hidden information in data using learnable basis signals through the use of sparsity. In this paper, we present a new method that leverages ICA and DL for the identification of directly interpretable patterns to discriminate between the HC and Sz groups. We use multi-subject resting-state fMRI data from $358$ subjects and form subject-specific tFNC feature vectors from ICA results. Then, we learn sparse representations of the tFNCs and introduce a new set of sparse features as well as new interpretable patterns from the learned atoms. Our experimental results show that the new representation not only leads to effective classification between HC and Sz groups using sparse features, but can also identify new interpretable patterns from the learned atoms that can help understand the complexities of mental diseases such as schizophrenia.

Recent neuroimaging studies that focus on predicting brain disorders via modern machine learning approaches commonly include a single modality and rely on supervised over-parameterized models.However, a single modality provides only a limited view of the highly complex brain. Critically, supervised models in clinical settings lack accurate diagnostic labels for training. Coarse labels do not capture the long-tailed spectrum of brain disorder phenotypes, which leads to a loss of generalizability of the model that makes them less useful in diagnostic settings. This work presents a novel multi-scale coordinated framework for learning multiple representations from multimodal neuroimaging data. We propose a general taxonomy of informative inductive biases to capture unique and joint information in multimodal self-supervised fusion. The taxonomy forms a family of decoder-free models with reduced computational complexity and a propensity to capture multi-scale relationships between local and global representations of the multimodal inputs. We conduct a comprehensive evaluation of the taxonomy using functional and structural magnetic resonance imaging (MRI) data across a spectrum of Alzheimer's disease phenotypes and show that self-supervised models reveal disorder-relevant brain regions and multimodal links without access to the labels during pre-training. The proposed multimodal self-supervised learning yields representations with improved classification performance for both modalities. The concomitant rich and flexible unsupervised deep learning framework captures complex multimodal relationships and provides predictive performance that meets or exceeds that of a more narrow supervised classification analysis. We present elaborate quantitative evidence of how this framework can significantly advance our search for missing links in complex brain disorders.

Objective: Endophenotypes such as brain age and fluid intelligence are important biomarkers of disease status. However, brain imaging studies to identify these biomarkers often encounter limited numbers of subjects and high dimensional imaging features, hindering reproducibility. Therefore, we develop an interpretable, multivariate classification/regression algorithm, called Latent Similarity (LatSim), suitable for small sample size, high feature dimension datasets. Methods: LatSim combines metric learning with a kernel similarity function and softmax aggregation to identify task-related similarities between subjects. Inter-subject similarity is utilized to improve performance on three prediction tasks using multi-paradigm fMRI data. A greedy selection algorithm, made possible by LatSim's computational efficiency, is developed as an interpretability method. Results: LatSim achieved significantly higher predictive accuracy at small sample sizes on the Philadelphia Neurodevelopmental Cohort (PNC) dataset. Connections identified by LatSim gave superior discriminative power compared to those identified by other methods. We identified 4 functional brain networks enriched in connections for predicting brain age, sex, and intelligence. Conclusion: We find that most information for a predictive task comes from only a few (1-5) connections. Additionally, we find that the default mode network is over-represented in the top connections of all predictive tasks. Significance: We propose a novel algorithm for small sample, high feature dimension datasets and use it to identify connections in task fMRI data. Our work should lead to new insights in both algorithm design and neuroscience research. Code and demo are available at https://github.com/aorliche/LatentSimilarity/., Comment: 12 pages