Liang Zhan

• Ph.D
• Professor (Associate) at University of Pittsburgh

Recently, SSVEP-based brain–computer interfaces (BCIs) have received increasing attention from researchers due to their high signal-to-noise ratios (SNR), high information transfer rates (ITR), and low user training. Therefore, various methods have been proposed to recognize the frequency of SSVEPs. This paper reviewed the state-of-the-art frequenc...

Large Language Models (LLMs) excel at many tasks but struggle with ambiguous scenarios where multiple valid responses exist, often yielding unreliable results. Conversely, Small Language Models (SLMs) demonstrate robustness in such scenarios but are susceptible to misleading or adversarial inputs. We observed that LLMs handle negative examples effe...

Brain imaging analysis is fundamental in neuroscience, providing valuable insights into brain structure and function. Traditional workflows follow a sequential pipeline—brain extraction, registration, segmentation, parcellation, network generation, and classification—treating each step as an independent task. These methods rely heavily on task-spec...

Medical image segmentation has achieved remarkable success through the continuous advancement of UNet-based and Transformer-based foundation backbones. However, clinical diagnosis in the real world often requires integrating domain knowledge, especially textual information. Conducting multimodal learning involves visual and text modalities shown as...

Neuronal hyperexcitation affects memory and neural processing across the Alzheimer’s disease (AD) cognitive continuum. Levetiracetam, an antiepileptic, shows promise in improving cognitive impairment by restoring the neural excitation/inhibition balance in AD patients. We previously identified a hyper-excitable phenotype in cognitively unimpaired f...

Brain imaging analysis is fundamental in neuroscience, providing valuable insights into brain structure and function. Traditional workflows follow a sequential pipeline-brain extraction, registration, segmentation, parcellation, network generation, and classification-treating each step as an independent task. These methods rely heavily on task-spec...

In recent years, the application of deep convolutional neural networks (DCNNs) to medical image segmentation has shown significant promise in computer-aided detection and diagnosis (CAD). Leveraging features from different spaces (i.e. Euclidean, non-Euclidean, and spectrum spaces) and multi-modalities of data have the potential to improve the info...

Functional brain connectome is crucial for deciphering the neural mechanisms underlying cognitive functions and neurological disorders. Graph deep learning models have recently gained tremendous popularity in this field. However, their actual effectiveness in modeling the brain connectome remains unclear. In this study, we re-examine graph deep lea...

As the leading cause of dementia worldwide, Alzheimer’s Disease (AD) has prompted significant interest in developing Deep Learning (DL) approaches for its classification. However, it currently remains unclear whether these models rely on established biological indicators. This work compares a novel DL model using structural connectivity (namely, BC...

Background Research indicates that the brain operates near a critical excitation/inhibition (E/I) balance point, which, when disrupted, correlates with Alzheimer’s Disease (AD) risk factors such as APOE genotype and sex. Utilizing our established multimodal imaging method (Fortel, Igor, et al. Network Neuroscience 6.2 (2022): 420‐444.), we investig...

Background Research indicates that the brain operates near a critical excitation/inhibition (E/I) balance point, which, when disrupted, correlates with Alzheimer’s Disease (AD) risk factors such as APOE genotype and sex. Utilizing our established multimodal imaging method (Fortel, Igor, et al. Network Neuroscience 6.2 (2022): 420‐444.), we investig...

This study introduces instantaneous frequency (IF) analysis as a novel method for characterizing dynamic brain causal networks from fMRI blood-oxygen-level-dependent (BOLD) signals. Effective connectivity, estimated using dynamic causal modeling (DCM), is analyzed to derive IF sequences, with the average IF across brain regions serving as a potenti...

Graph neural networks (GNNs) are powerful machine learning models designed to handle irregularly structured data. However, their generic design often proves inadequate for analyzing brain connectomes in Alzheimer's Disease (AD), highlighting the need to incorporate domain knowledge for optimal performance. Infusing AD-related knowledge into GNNs is...

In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and misinformation detection. Meanwhile, the need to systematically understand how LLMs can further revolutionize the field also becomes urgent. In this work, we--a multidiscipl...

Brain connectivity alternations associated with brain disorders have been widely reported in resting-state functional imaging (rs-fMRI) and diffusion tensor imaging (DTI). While many dual-modal fusion methods based on graph neural networks (GNNs) have been proposed, they generally follow homogenous fusion ways ignoring rich heterogeneity of dual-mo...

Independent and identically distributed (i.i.d.) data is essential to many data analysis and modeling techniques. In the medical domain, collecting data from multiple sites or institutions is a common strategy that guarantees sufficient clinical diversity, determined by the decentralized nature of medical data. However, data from various sites are...

Radiology Report Generation (RRG) has achieved significant progress with the advancements of multimodal generative models. However, the evaluation in the domain suffers from a lack of fair and robust metrics. We reveal that, high performance on RRG with existing lexical-based metrics (e.g. BLEU) might be more of a mirage - a model can get a high BL...

The long-standing one-to-many problem of gold standard responses in open-domain dialogue systems presents challenges for automatic evaluation metrics. Though prior works have demonstrated some success by applying powerful Large Language Models (LLMs), existing approaches still struggle with the one-to-many problem, and exhibit subpar performance in...

Independent and identically distributed (i.i.d.) data is essential to many data analysis and modeling techniques. In the medical domain, collecting data from multiple sites or institutions is a common strategy that guarantees sufficient clinical diversity, determined by the decentralized nature of medical data. However, data from various sites are...

The MRI-derived brain network serves as a pivotal instrument in elucidating both the structural and functional aspects of the brain, encompassing the ramifications of diseases and developmental processes. However, prevailing methodologies, often focusing on synchronous BOLD signals from functional MRI (fMRI), may not capture directional influences...

The Evidential Regression Network (ERN) represents a novel approach that integrates deep learning with Dempster-Shafer's theory to predict a target and quantify the associated uncertainty. Guided by the underlying theory, specific activation functions must be employed to enforce non-negative values, which is a constraint that compromises model perf...

The hippocampus is a crucial brain structure involved in memory formation, spatial navigation, emotional regulation, and learning. An accurate MRI image segmentation of the human hippocampus plays an important role in multiple neuro-imaging research and clinical practice, such as diagnosing neurological diseases and guiding surgical interventions....

Alzheimer’s disease (AD) is the most common form of dementia and results in neurodegeneration and cognitive impairment. White matter (WM) is affected in AD and has implications for neural circuitry and cognitive function. The trajectory of these changes across age, however, is still not well understood, especially at earlier stages in life. To addr...

Objective Neighborhood perceptions are associated with physical and mental health outcomes; however, the biological associates of this relationship remain to be fully understood. Here, we evaluate the relationship between neighborhood perceptions and amygdala activity and connectivity with salience network (i.e. insula, anterior cingulate, thalamus...

Background Dysfunctional excitation‐inhibition balance (EIB) is hypothesized to precede cognitive impairment in Alzheimer’s disease (AD); however, overlapping neuropathology (like amyloid plaques) can develop in cognitively normal (CN) and impaired (CI) individuals. We investigate EIB trajectories for individuals with significant amyloid (Aβ+). Me...

Background Studies suggested that the comorbidity between Neuropsychiatric Symptoms (NPS) and dementia highlights the prognostic value in prodromal phases. Our central hypothesis is that the accurate prediction of NPS can improve the Alzheimer’s diagnosis. We adopt deep learning techniques to simultaneously predict MCI and depression, one of the mo...

The human brain, composed of billions of neurons and synaptic connections, is an intricate network coordinating a sophisticated balance of excitatory and inhibitory activities between brain regions. The dynamical balance between excitation and inhibition is vital for adjusting neural input/output relationships in cortical networks and regulating th...

Recent years have shown great merits in utilizing neuroimaging data to understand brain structural and functional changes, as well as its relationship to different neurodegenerative diseases and other clinical phenotypes. Brain networks, derived from different neuroimaging modalities, have attracted increasing attention due to their potential to ga...

Positron emission tomography (PET) can detect brain amyloid-β (Aβ) deposits, a diagnostic hallmark of Alzheimer’s disease and a target for disease modifying treatment. However, PET-Aβ is expensive, not widely available, and, unlike magnetic resonance imaging (MRI), exposes the patient to ionizing radiation. Here we propose a novel 3D multimodal gen...

The modeling of the interaction between brain structure and function using deep learning techniques has yielded remarkable success in identifying potential biomarkers for different clinical phenotypes and brain diseases. However, most existing studies focus on one-way mapping, either projecting brain function to brain structure or inversely. This t...

Background Sex differences impact Alzheimer’s disease (AD) neuropathology, but cell-to-network level dysfunctions in the prodromal phase are unclear. Alterations in hippocampal excitation-inhibition balance (EIB) have recently been linked to early AD pathology. Objective Examine how AD risk factors (age, APOE ɛ4, amyloid-β) relate to hippocampal E...

Background: Sex differences impact Alzheimer's disease (AD) neuropathology, but cell-to-network level dysfunctions in the prodromal phase are unclear. Alterations in hippocampal excitation-inhibition balance (EIB) have recently been linked to early AD pathology. Objective: Examine how AD risk factors (age, APOE-ɛ4, amyloid-β) relate to hippocampal...

Recent advancements in the acquisition of various brain data sources have created new opportunities for integrating multimodal brain data to assist in early detection of complex brain disorders. However, current data integration approaches typically need a complete set of biomedical data modalities, which may not always be feasible, as some modalit...

Brain–computer interface (BCI) provides a new communication pathway for severely disabled people and enables them to communicate with external world using only their brain activity. P300-based BCI speller helps patients spell words using their brain signals. Until now, binary-classification-based approaches have been used for P300 detection. This s...

The human brain, composed of billions of neurons and synaptic connections, is an intricate network coordinating a sophisticated balance of excitatory and inhibitory activity between brain regions. The dynamical balance between excitation and inhibition is vital for adjusting neural input/output relationships in cortical networks and regulating the...

The COVID-19 pandemic has extremely threatened human health, and automated algorithms are needed to segment infected regions in the lung using computed tomography (CT). Although several deep convolutional neural networks (DCNNs) have proposed for this purpose, their performance on this task is suppressed due to the limited local receptive field and...

Introduction: Alzheimer's disease (AD) is a progressive neurodegenerative disease. The early processes of AD, however, are not fully understood and likely begin years before symptoms manifest. Importantly, disruption of the default mode network, including the hippocampus, has been implicated in AD. Methods: To examine the role of functional netw...

As one of the popular deep learning methods, deep convolutional neural networks (DCNNs) have been widely adopted in segmentation tasks and have received positive feedback. However, in segmentation tasks, DCNN-based frameworks are known for their incompetence in dealing with global relations within imaging features. Although several techniques have...

Mild cognitive impairment is the prodromal stage of Alzheimer's disease. Its detection has been a critical task for establishing cohort studies and developing therapeutic interventions for Alzheimer's. Various types of markers have been developed for detection. For example, imaging markers from neuroimaging have shown great sensitivity, while its c...

Recently, brain networks have been widely adopted to study brain dynamics, brain development, and brain diseases. Graph representation learning techniques on brain functional networks can facilitate the discovery of novel biomarkers for clinical phenotypes and neurodegenerative diseases. However, current graph learning techniques have several issue...

Mapping the connectome of the human brain using structural or functional connectivity has become one of the most pervasive paradigms for neuroimaging analysis. Recently, Graph Neural Networks (GNNs) motivated from geometric deep learning have attracted broad interest due to their established power for modeling complex networked data. Despite their...

MRI-derived brain networks have been widely used to understand functional and structural interactions among brain regions, and factors that affect them, such as brain development and diseases. Graph mining on brain networks can facilitate the discovery of novel biomarkers for clinical phenotypes and neurodegenerative diseases. Since brain functiona...

The assessment of Alzheimer's Disease (AD) and Mild Cognitive Impairment (MCI) associated with brain changes remains a challenging task. Recent studies have demonstrated that combination of multi-modality imaging techniques can better reflect pathological characteristics and contribute to more accurate diagnosis of AD and MCI. In this paper, we pro...

The assessment of Alzheimer's Disease (AD) and Mild Cognitive Impairment (MCI) associated with brain changes remains a challenging task. Recent studies have demonstrated that combination of multi-modality imaging techniques can better reflect pathological characteristics and contribute to more accurate diagnosis of AD and MCI. In this paper, we pro...

Brain large-scale dynamics is constrained by the heterogeneity of intrinsic anatomical substrate. Little is known how the spatio-temporal dynamics adapt for the heterogeneous structural connectivity (SC). Modern neuroimaging modalities make it possible to study the intrinsic brain activity at the scale of seconds to minutes. Diffusion magnetic reso...

Understanding the intrinsic patterns of human brain is important to make inferences about the mind and brain-behavior association. Electrophysiological methods (i.e. MEG/EEG) provide direct measures of neural activity without the effect of vascular confounds. The blood oxygenated level-dependent (BOLD) signal of functional MRI (fMRI) reveals the sp...

The transformation and transmission of brain stimuli reflect the dynamical brain activity in space and time. Compared with functional magnetic resonance imaging (fMRI), magneto- or electroencephalography (M/EEG) fast couples to the neural activity through generated magnetic fields. However, the MEG signal is inhomogeneous throughout the whole brain...

Graph theoretical analyses have become standard tools in modeling functional and anatomical connectivity in the brain. With the advent of connectomics, the primary graphs or networks of interest are structural connectome (derived from DTI tractography) and functional connectome (derived from resting-state fMRI). However, most published connectome s...

Brain networks have attracted increasing attention due to the potential to better characterize brain dynamics and abnormalities in neurological and psychiatric conditions. Recent years have witnessed enormous successes in deep learning. Many AI algorithms, especially graph learning methods, have been proposed to analyze brain networks. An important...

Graph theoretical analyses have become standard tools in modeling functional and anatomical connectivity in the brain. With the advent of connectomics, the primary graphs or networks of interest are structural connectome (derived from DTI tractography) and functional connectome (derived from resting-state fMRI). However, most published connectome s...

Neural activity coordinated across different scales from neuronal circuits to large-scale brain networks gives rise to complex cognitive functions. Bridging the gap between micro- and macroscale processes, we present a novel framework based on the maximum entropy model to infer a hybrid resting-state structural connectome, representing functional i...

MRI-based modeling of brain networks has been widely used to understand functional and structural interactions and connections among brain regions, and factors that affect them, such as brain development and disease. Graph mining on brain networks may facilitate the discovery of novel biomarkers for clinical phenotypes and neurodegenerative disease...

Brain networks have been extensively studied in neuroscience, to better understand human behavior, and to identify and characterize distributed brain abnormalities in neurological and psychiatric conditions. Several deep graph learning models have been proposed for brain network analysis, yet most current models lack interpretability, which makes i...

Mapping the connectome of the human brain using structural or functional connectivity has become one of the most pervasive paradigms for neuroimaging analysis. Recently, Graph Neural Networks (GNNs) motivated from geometric deep learning have attracted broad interest due to their established power for modeling complex networked data. Despite their...

Peripheral inflammation has been implicated in cognitive dysfunction and dementia. While studies outline the relationship between elevated inflammation and individual gray or white matter alterations, less work has examined inflammation as related to connectivity between gray and white matter or variability in these associations by race. We examine...

Recent years have witnessed the emergence and flourishing of hierarchical graph pooling neural networks (HGPNNs) which are effective graph representation learning approaches for graph level tasks such as graph classification. However, current HGPNNs do not take full advantage of the graph’s intrinsic structures (e.g., community structure). Moreover...

Diffusion MRI-derived brain structural connectomes or brain networks are widely used in the brain research. However, constructing brain networks is highly dependent on various tractography algorithms, which leads to difficulties in deciding the optimal view concerning the downstream analysis. In this paper, we propose to learn a unified representat...

Automated and accurate segmentation of the infected regions in computed tomography (CT) images is critical for the prediction of the pathological stage and treatment response of COVID-19. Several deep convolutional neural networks (DCNNs) have been designed for this task, whose performance, however, tends to be suppressed by their limited local rec...

In this paper, we propose a Boundary-aware Graph Reasoning (BGR) module to learn long-range contextual features for semantic segmentation. Rather than directly construct the graph based on the backbone features, our BGR module explores a reasonable way to combine segmentation erroneous regions with the graph construction scenario. Motivated by the...

In this paper, we propose MGNet, a simple and effective multiplex graph convolutional network (GCN) model for multimodal brain network analysis. The proposed method integrates tensor representation into the multiplex GCN model to extract the latent structures of a set of multimodal brain networks, which allows an intuitive 'grasping' of the common...

Resting-state functional magnetic resonance imaging (rs-fMRI) is widely used in connectomics for studying the functional relationships between regions of the human brain. rs-fMRI connectomics, however, has inherent analytical challenges, such as how to properly model negative correlations between BOLD time series. In addition, functional relationsh...

Recent years have witnessed the emergence and flourishing of hierarchical graph pooling neural networks (HGPNNs) which are effective graph representation learning approaches for graph level tasks such as graph classification. However, current HGPNNs do not take full advantage of the graph's intrinsic structures (e.g., community structure). Moreover...

Background Multimodal neuroimaging modalities may improve detection of early brain changes associated with Alzheimer’s disease (AD). We investigated cognitively intact middle‐aged individuals to determine whether male and female APOE‐ε4 carriers demonstrate altered connectivity using a novel multimodal connectomics technique to probe excitation‐inh...

Objectives: Non-Latino Black adults have greater risk for Alzheimer's dementia compared to non-Latino White adults, possibly due to factors disproportionally affecting Black adults including cardiovascular disease (CVD). Chronic peripheral inflammation is implicated in both Alzheimer's dementia and CVD and is known to impact cognition and cerebral...

Applying network science approaches to investigate the functions and anatomy of the human brain is prevalent in modern medical imaging analysis. Due to the complex network topology, for an individual brain, mining a discriminative network representation from the multimodal brain networks is non-trivial. The recent success of deep learning technique...

Addiction to drugs between young people is one of the most severe problems in the real world, and it imposes a huge financial and emotional burden on their families and societies. Therefore, predicting potential inclination to drugs at earlier ages can prevent lots of detriments. In this paper, we propose a new semi-supervised deep ordinal regressi...

Applying network science approaches to investigate the functions and anatomy of the human brain is prevalent in modern medical imaging analysis. Due to the complex network topology, for an individual brain, mining a discriminative network representation from the multimodal brain networks is non-trivial. The recent success of deep learning technique...

Synaptic dysfunction is hypothesized to be one of the earliest brain changes in Alzheimer's disease, leading to "hyperexcitability" in neuronal circuits. In this study, we evaluated a novel hyperexcitation indicator (HI) for each brain region using a hybrid resting-state structural connectome to probe connectome-level excitation-inhibition balance...

Recent years have witnessed the emergence and development of graph neural networks (GNNs), which have been shown as a powerful approach for graph representation learning in many tasks, such as node classification and graph classification. The research on the robustness of these models has also started to attract attentions in the machine learning f...

Resting-state functional magnetic resonance imaging (rs-fMRI) is widely used in connectomics for studying the functional relationships between regions of the human brain. rs-fMRI connectomics, however, has inherent analytical challenges, such as accounting for negative correlations. In addition, functional relationships between brain regions do not...

A threshold-free feature in brain network analysis can help circumvent the curse of arbitrary network thresholding for binary network conversions. Here, Persistent Homology is the inspiration for defining a new aggregation cost based on the number of cycles, or for tracking the first Betti number in a nested filtration network within the graph. Our...

Diffusion MRI-derived brain structural network has been widely used in brain research and community or modular structure is one of popular network features, which can be extracted from network edge-derived pathlengths. Conceptually, brain structural network edges represent the connecting strength between pair of nodes, thus non-negative. The pathle...

Objective: We sought to determine whether the aspects of white matter connectivity implicated in major depression also relate to mild depressive symptoms in family dementia caregivers (dCGs). Methods: Forty-one dCGs (average age=69 years, standard deviation=6.4) underwent a 7 Tesla 64-direction (12-minute) diffusion-weighted imaging sequence. We...

Past research shows that major depression is associated with lower white matter integrity in fronto-limbic and other areas. But it is not known whether the integrity of these white matter connections is associated with subsyndromal depression symptoms, a marker of risk for major depression, in family dementia caregivers (dCGs) who reported stress....

Human brain networks convey important insights in understanding the mechanism of many mental disorders. However, it is difficult to determine a universal optimal among various tractography methods for general diagnosis tasks. To address this issue, tentative studies, aiming at the identification of some mental disorders, make an effective concessio...

This paper introduces a novel method that unifies structural connectivity and functional time series to form a signed coupling interaction network or “signed resting state structural connectome” (signed rs-SC) to describe neural excitation and inhibition. We employ an energy representation of neural activity based on the Ising model from statistica...

Mild Cognitive Impairment (MCI) is a clinically intermediate stage in the course of Alzheimer’s disease (AD). MCI does not always lead to dementia. Some MCI patients may stay in the MCI status for the rest of their life, while others will develop AD eventually. Therefore, classification methods that help to distinguish MCI from earlier or later sta...

The oblique effect (OE) describes the visuospatial advantage for identifying stimuli oriented horizontally or vertically rather than diagonally; little is known about brain aging and the OE. We investigated this relationship using the Judgment of Line Orientation (JLO) in 107 older adults (∼age = 67.8 ± 6.6; 51% female) together with neuropsycholog...

Alzheimer’s Disease (AD) is the main cause for age-related dementia. Many machine learning methods have been proposed to identify important genetic bases which are associated to phenotypes indicating the progress of AD. However, the biological knowledge is seldom considered in spite of the success of previous research. Built upon neuroimaging high-...

Cardiovascular disease risk factors (CVD-RFs) are associated with decreased gray and white matter integrity and cognitive impairment in older adults. Less is known regarding the interplay between CVD-RFs, brain structural connectome integrity, and cognition. We examined whether CVD-RFs were associated with measures of tract-based structural connect...

Background: Accumulating evidence suggests that higher Mediterranean diet (MedDiet) adherence is associated with higher global cognitive performance and brain structural integrity as well as decreased risk of Alzheimer disease (AD) and vascular dementia (VaD). Objectives: We directly examined cross-sectional associations between the MedDiet and...