Skip to main content

Alex Leow

Followers

9

Following

3

Co-authors

2

Public Views

University of Pittsburgh

National Brain Research Centre

Christopher Timmermann

Imperial College London

Shunsuke Kamiya

The University of Tokyo

Varun Madan Mohan

SAMIR CHOWDHURY

Interests

Uploads

Papers by Alex Leow

Inferring excitation-inhibition dynamics using a maximum entropy model unifying brain structure and function

Network Neuroscience, 2021

Neural activity coordinated across different scales from neuronal circuits to large-scale brain n... more 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 interactions constrained by structural connectivity. We demonstrate that the structurally informed network outperforms the unconstrained model in simulating brain dynamics, wherein by constraining the inference model with the network structure we may improve the estimation of pairwise BOLD signal interactions. Further, we simulate brain network dynamics using Monte Carlo simulations with the new hybrid connectome to probe connectome-level differences in excitation-inhibition balance between apolipoprotein E (APOE)-ε4 carriers and noncarriers. Our results reveal sex differences among APOE-ε4 carriers in functional dynamics at criticality; sp...

Predicting Mood Disturbance Severity with Mobile Phone Keystroke Metadata: A BiAffect Digital Phenotyping Study (Preprint)

BACKGROUND Mood disorders are common and associated with significant morbidity and mortality. Bet... more BACKGROUND Mood disorders are common and associated with significant morbidity and mortality. Better tools are needed for their diagnosis and treatment. Deeper phenotypic understanding of these disorders is integral to the development of such tools. This study is the first effort to use passively collected mobile phone keyboard activity to build deep digital phenotypes of depression and mania. OBJECTIVE The objective of our study was to investigate the relationship between mobile phone keyboard activity and mood disturbance in subjects with bipolar disorders and to demonstrate the feasibility of using passively collected mobile phone keyboard metadata features to predict manic and depressive signs and symptoms as measured via clinician-administered rating scales. METHODS Using a within-subject design of 8 weeks, subjects were provided a mobile phone loaded with a customized keyboard that passively collected keystroke metadata. Subjects were administered the Hamilton Depression Ratin...

Thought Chart: Tracking Dynamic EEG Brain Connectivity with Unsupervised Manifold Learning

Assuming that the topological space containing all possible brain states forms a very high-dimens... more

Improved EEG Classification by factoring in sensor topography

ArXiv, 2019

Electroencephalography (EEG) serves as an effective diagnostic tool for mental disorders and neur... more Electroencephalography (EEG) serves as an effective diagnostic tool for mental disorders and neurological abnormalities. Enhanced analysis and classification of EEG signals can help improve detection performance. This work presents a new approach that seeks to exploit the knowledge of EEG sensor spatial configuration to achieve higher detection accuracy. Two classification models, one which ignores the configuration (model 1) and one that exploits it with different interpolation methods (model 2), are studied. The analysis is based on the information content of these signals represented in two different ways: concatenation of the channels of the frequency bands and an image-like 2D representation of the EEG channel locations. Performance of these models is examined on two tasks, social anxiety disorder (SAD) detection, and emotion recognition using DEAP dataset. Validity of our hypothesis that model 2 will significantly outperform model 1 is borne out in the results, with accuracy $...

Phase Angle Spatial Embedding (PhASE) - A Kernel Method for Studying the Topology of the Human Functional Connectome

Modern resting-state functional magnetic resonance imaging (rs-fMRI) provides a wealth of informa... more Modern resting-state functional magnetic resonance imaging (rs-fMRI) provides a wealth of information about the inherent functional connectivity of the human brain. However, understanding the role of negative correlations and the nonlinear topology of rs-fMRI remains a challenge. To address these challenges, we propose a novel graph embedding technique, phase angle spatial embedding (PhASE), to study the “intrinsic geometry” of the functional connectome. PhASE both incorporates negative correlations as well as reformulates the connectome modularity problem as a kernel two-sample test, using a kernel method that induces a maximum mean discrepancy (MMD) in a reproducing kernel Hilbert space (RKHS). By solving a graph partition that maximizes this MMD, PhASE identifies the most functionally distinct brain modules. As a test case, we analyzed a public rs-fMRI dataset to compare male and female connectomes using PhASE and minimum spanning tree inferential statistics. These results show s...

The power of negative thinking

Health news, 2002

Computer Engineering Program, University of Wisconsin-Stout, Menomonie, WI, USA Department of Psy... more Computer Engineering Program, University of Wisconsin-Stout, Menomonie, WI, USA Department of Psychiatry, University of Illinois, Chicago, IL, USA Department of Computer Science, University of Illinois, Chicago, IL, USA Department of Bioengineering, University of Illinois, Chicago, IL, USA Imaging Genetics Center, and Institute for Neuroimaging and Informatics, Keck School of Medicine of USC, CA, USA Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, WI, USA

Immersive Analytics for Clinical Neuroscience

This paper introduces NeuroCave, an open-source immersive analytics software tool for exploring a... more This paper introduces NeuroCave, an open-source immersive analytics software tool for exploring and making sense of both structural and functional connectomes describing the interconnectivity between brain regions. The software supports visual analysis tasks for clinical neuroscientists, facilitating explorations of connectome datasets used in comparative group studies. Researchers can enter and leave virtual reality as desired in order to visualize and reason about connectome datasets from a range of different perspectives.

Tensor Distribution Function Demixes Fibers in Multi-Shell High Angular Resolution Diffusion Images

Introduction: Diffusion tensor imaging (DTI) reveals white matter microstructure and fiber pathwa... more Introduction: Diffusion tensor imaging (DTI) reveals white matter microstructure and fiber pathways in the living brain by examining the 3D diffusion profile of water molecules in brain tissue. Even so, DTIderived measures are incorrect where fibers cross or mix, as the single tensor model cannot resolve these more complicated white matter configurations. Diffusion spectrum imaging (DSI) avoids this issue by direct model-free Fourier inversion of the diffusion signal, but is time intensive, as it measures the signal using 6D Cartesian sampling [1]. An alternative approach based on sampling only on one or multiple spherical shells in q-space has been proposed, referred to as high angular resolution diffusion imaging [2]. Each spherical shell is a 2D manifold with a specific b-value [3], and the required sampling grows quadratically with the desired angular resolution, as opposed to cubically with the spatial and q-space resolutions in DSI [4].

The Importance of Being Negative: A serious treatment of non-trivial edges in brain functional connectome

Understanding the modularity of fMRI-derived brain networks or connectomes can inform the study o... more Understanding the modularity of fMRI-derived brain networks or connectomes can inform the study of brain function organization. However, fMRI connectomes additionally involve negative edges, which are not rigorously accounted for by existing approaches to modularity that either ignores or arbitrarily weight these connections. Furthermore, most Q maximization-based modularity algorithms yield variable results with suboptimal reproducibility. Here we present an alternative, reproducible approach that exploits how frequent the BOLD-signal correlation between two nodes is negative. We validated this novel probability-based modularity approach on two independent publicly-available resting-state connectome dataset (the Human Connectome Project and the 1000 Functional Connectomes) and demonstrated that negative correlations alone are sufficient in understanding resting-state modularity. In fact, this approach a) permits a dual formulation, leading to equivalent solutions regardless of whet...

Unbiased Volumetric Registration via Nonlinear Elastic Regularization

In this paper, we propose a new large-deformation nonlinear image registration model in three dim... more In this paper, we propose a new large-deformation nonlinear image registration model in three dimensions, based on nonlinear elastic regularization and unbiased registration. Both the nonlinear elastic and the unbiased functionals are simplified introducing, in the modeling, a second unknown that mimics the Jacobian matrix of the displacement vector field, reducing the minimization to involve linear differential equations. In contrast to recently proposed unbiased fluid registration method, the new model is written in a unified variational form and is minimized using gradient descent on the corresponding Euler-Lagrange equations. As a result, the new unbiased nonlinear elasticity model is computationally more efficient and easier to implement than the unbiased fluid registration. The model was tested using three-dimensional serial MRI images and shown to have some advantages for computational neuroimaging.

Real-Time Monitoring: A Key Element in Personalized Health and Precision Health

FOCUS

Current management of psychiatric disorders relies heavily on retrospective, subjective reports p... more Current management of psychiatric disorders relies heavily on retrospective, subjective reports provided by patients and their families. Consequently, psychiatric services are often provisioned inefficiently and with suboptimal outcomes. Recent advances in computing and sensor technologies have enabled the development of real-time monitoring systems for the diagnosis and management of psychiatric disorders. The state of these technologies is rapidly evolving, with passive monitoring and predictive modeling as two areas that have great potential to affect psychiatric care. Although outpatient psychiatry probably stands to benefit the most from the use of real-time monitoring technologies, there are also several ways in which inpatient psychiatry may also benefit. As the capabilities of these technologies increase and their use becomes more common, many ethical and legal issues will need to be considered. The role of governmental regulatory bodies and nongovernmental organizations in providing oversight of the implementation of these technologies is an active area of discussion.

Passive Sensing of Affective and Cognitive Functioning in Mood Disorders by Analyzing Keystroke Kinematics and Speech Dynamics

Studies in Neuroscience, Psychology and Behavioral Economics

Mood disorders can be difficult to diagnose, evaluate, and treat. They involve affective and cogn... more Mood disorders can be difficult to diagnose, evaluate, and treat. They involve affective and cognitive components, both of which need to be closely monitored over the course of the illness. Current methods like interviews and rating scales can be cumbersome, sometimes ineffective, and oftentimes infrequently administered. Even ecological momentary assessments, when used alone, are susceptible to many of the same limitations and still require active participation from the subject. Passive, continuous, frictionless, and ubiquitous means of recording and analyzing mood and cognition obviate the need for more frequent and lengthier doctor’s visits, can help identify misdiagnoses, and would potentially serve as an early warning system to better manage medication adherence and prevent hospitalizations. Activity trackers and smartwatches have long provided exactly such a tool for evaluating physical fitness. What if smartphones, voice assistants, and eventually Internet of Things devices and ambient computing systems could similarly serve as fitness trackers for the brain, without imposing any additional burden on the user? In this chapter, we explore two such early approaches—an in-depth analytical technique based on examining meta-features of virtual keyboard usage and corresponding typing kinematics, and another method which analyzes the acoustic features of recorded speech—to passively and unobtrusively understand mood and cognition in people with bipolar disorder. We review innovative studies that have used these methods to build mathematical models and machine learning frameworks that can provide deep insights into users’ mood and cognitive states. We then outline future research considerations and close by discussing the opportunities and challenges afforded by these modes of researching mood disorders and passive sensing approaches in general.

Exact Combinatorial Inference for Brain Images

Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

The permutation test is known as the exact test procedure in statistics. However, often it is not... more The permutation test is known as the exact test procedure in statistics. However, often it is not exact in practice and only an approximate method since only a small fraction of every possible permutation is generated. Even for a small sample size, it often requires to generate tens of thousands permutations, which can be a serious computational bottleneck. In this paper, we propose a novel combinatorial inference procedure that enumerates all possible permutations combinatorially without any resampling. The proposed method is validated against the standard permutation test in simulation studies with the ground truth. The method is further applied in twin DTI study in determining the genetic contribution of the minimum spanning tree of the structural brain connectivity.

EEG Classification based on Image Configuration in Social Anxiety Disorder

2019 9th International IEEE/EMBS Conference on Neural Engineering (NER), Mar 1, 2019

The problem of detecting the presence of Social Anxiety Disorder (SAD) using Electroencephalograp... more The problem of detecting the presence of Social Anxiety Disorder (SAD) using Electroencephalography (EEG) for classification has seen limited study and is addressed with a new approach that seeks to exploit the knowledge of EEG sensor spatial configuration. Two classification models, one which ignores the configuration (model 1) and one that exploits it with different interpolation methods (model 2), are studied. Performance of these two models is examined for analyzing 34 EEG data channels each consisting of five frequency bands and further decomposed with a filter bank. The data are collected from 64 subjects consisting of healthy controls and patients with SAD. Validity of our hypothesis that model 2 will significantly outperform model 1 is borne out in the results, with accuracy 6-7% higher for model 2 for each machine learning algorithm we investigated. Convolutional Neural Networks (CNN) were found to provide much better performance than SVM and kNNs.

dpMood: Exploiting Local and Periodic Typing Dynamics for Personalized Mood Prediction

2018 IEEE International Conference on Data Mining (ICDM), Nov 1, 2018

Mood disorders are common and associated with significant morbidity and mortality. Early diagnosi... more Mood disorders are common and associated with significant morbidity and mortality. Early diagnosis has the potential to greatly alleviate the burden of mental illness and the ever increasing costs to families and society. Mobile devices provide us a promising opportunity to detect the users' mood in an unobtrusive manner. In this study, we use a custom keyboard which collects keystrokes' meta-data and accelerometer values. Based on the collected time series data in multiple modalities, we propose a deep personalized mood prediction approach, called dpMood, by integrating convolutional and recurrent deep architectures as well as exploring each individual's circadian rhythm. Experimental results not only demonstrate the feasibility and effectiveness of using smart-phone meta-data to predict the presence and severity of mood disturbances in bipolar subjects, but also show the potential of personalized medical treatment for mood disorders.

Sequential Keystroke Behavioral Biometrics for Mobile User Identification via Multi-view Deep Learning

Lecture Notes in Computer Science, 2017

With the rapid growth in smartphone usage, more organizations begin to focus on providing better ... more With the rapid growth in smartphone usage, more organizations begin to focus on providing better services for mobile users. User identification can help these organizations to identify their customers and then cater services that have been customized for them. Currently, the use of cookies is the most common form to identify users. However, cookies are not easily transportable (e.g., when a user uses a different login account, cookies do not follow the user). This limitation motivates the need to use behavior biometric for user identification. In this paper, we propose DEEPSERVICE, a new technique that can identify mobile users based on user's keystroke information captured by a special keyboard or web browser. Our evaluation results indicate that DEEPSERVICE is highly accurate in identifying mobile users (over 93% accuracy). The technique is also efficient and only takes less than 1 ms to perform identification.

Predicting Mood Disturbance Severity with Mobile Phone Keystroke Metadata: A BiAffect Digital Phenotyping Study

Journal of medical Internet research, Jan 20, 2018

Mood disorders are common and associated with significant morbidity and mortality. Better tools a... more Mood disorders are common and associated with significant morbidity and mortality. Better tools are needed for their diagnosis and treatment. Deeper phenotypic understanding of these disorders is integral to the development of such tools. This study is the first effort to use passively collected mobile phone keyboard activity to build deep digital phenotypes of depression and mania. The objective of our study was to investigate the relationship between mobile phone keyboard activity and mood disturbance in subjects with bipolar disorders and to demonstrate the feasibility of using passively collected mobile phone keyboard metadata features to predict manic and depressive signs and symptoms as measured via clinician-administered rating scales. Using a within-subject design of 8 weeks, subjects were provided a mobile phone loaded with a customized keyboard that passively collected keystroke metadata. Subjects were administered the Hamilton Depression Rating Scale (HDRS) and Young Mani...

BRAINtrinsic: A Virtual Reality-Compatible Tool for Exploring Intrinsic Topologies of the Human Brain Connectome

Lecture Notes in Computer Science, 2015

Thanks to advances in non-invasive technologies such as functional Magnetic Resonance Imaging (fM... more Thanks to advances in non-invasive technologies such as functional Magnetic Resonance Imaging (fMRI) and Diffusion Tensor Imaging (DTI), highly-detailed maps of brain structure and function can now be collected. In this context, brain connectomics have emerged as a fast growing field that aims at understanding these comprehensive maps of brain connectivity using sophisticated computational models. In this paper we present BRAINtrinsic, an innovative web-based 3D visual analytics tool that allows users to intuitively and iteratively interact with connectome data. Moreover, BRAINtrinsic implements a novel visualization platform that reconstructs connectomes' intrinsic geometry, i.e., the topological space as informed by brain connectivity, via dimensionality reduction. BRAINtrinsic is implemented with virtual reality in mind and is fully compatible with the Oculus Rift technology. Last, we demonstrate its effectiveness through a series of case studies involving both structural and resting-state MR imaging data.

Brain Dynamics Through the Lens of Statistical Mechanics by Unifying Structure and Function

This paper introduces a novel method that unifies structural connectivity and functional time ser... more 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 statistical mechanics, hereby bypassing traditional BOLD correlations. The spin model is a function of a coupling interaction (traditionally positive or negative) and spin-states of paired brain regions. Observed functional time series represent brain states over time. A maximum pseudolikelihood with a constraint is used to estimate the coupling interaction. The constraint is introduced as a penalty function such that the learned interactions are scaled relative to structural connectivity; the sign of the interactions may infer inhibition or excitation over an underlying structure. We evaluate our method by comparing a group of otherwise healthy APO...

$Research paper thumbnail of Shared white matter alterations across emotional disorders: A voxel-based meta-analysis of fractional anisotropy$

Shared white matter alterations across emotional disorders: A voxel-based meta-analysis of fractional anisotropy

by Lisanne Jenkins and Alex Leow

NeuroImage: Clinical, 2016

Inferring excitation-inhibition dynamics using a maximum entropy model unifying brain structure and function

Network Neuroscience, 2021

Neural activity coordinated across different scales from neuronal circuits to large-scale brain n... more 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 interactions constrained by structural connectivity. We demonstrate that the structurally informed network outperforms the unconstrained model in simulating brain dynamics, wherein by constraining the inference model with the network structure we may improve the estimation of pairwise BOLD signal interactions. Further, we simulate brain network dynamics using Monte Carlo simulations with the new hybrid connectome to probe connectome-level differences in excitation-inhibition balance between apolipoprotein E (APOE)-ε4 carriers and noncarriers. Our results reveal sex differences among APOE-ε4 carriers in functional dynamics at criticality; sp...

Predicting Mood Disturbance Severity with Mobile Phone Keystroke Metadata: A BiAffect Digital Phenotyping Study (Preprint)

BACKGROUND Mood disorders are common and associated with significant morbidity and mortality. Bet... more BACKGROUND Mood disorders are common and associated with significant morbidity and mortality. Better tools are needed for their diagnosis and treatment. Deeper phenotypic understanding of these disorders is integral to the development of such tools. This study is the first effort to use passively collected mobile phone keyboard activity to build deep digital phenotypes of depression and mania. OBJECTIVE The objective of our study was to investigate the relationship between mobile phone keyboard activity and mood disturbance in subjects with bipolar disorders and to demonstrate the feasibility of using passively collected mobile phone keyboard metadata features to predict manic and depressive signs and symptoms as measured via clinician-administered rating scales. METHODS Using a within-subject design of 8 weeks, subjects were provided a mobile phone loaded with a customized keyboard that passively collected keystroke metadata. Subjects were administered the Hamilton Depression Ratin...

Thought Chart: Tracking Dynamic EEG Brain Connectivity with Unsupervised Manifold Learning

Assuming that the topological space containing all possible brain states forms a very high-dimens... more

Improved EEG Classification by factoring in sensor topography

ArXiv, 2019

Electroencephalography (EEG) serves as an effective diagnostic tool for mental disorders and neur... more Electroencephalography (EEG) serves as an effective diagnostic tool for mental disorders and neurological abnormalities. Enhanced analysis and classification of EEG signals can help improve detection performance. This work presents a new approach that seeks to exploit the knowledge of EEG sensor spatial configuration to achieve higher detection accuracy. Two classification models, one which ignores the configuration (model 1) and one that exploits it with different interpolation methods (model 2), are studied. The analysis is based on the information content of these signals represented in two different ways: concatenation of the channels of the frequency bands and an image-like 2D representation of the EEG channel locations. Performance of these models is examined on two tasks, social anxiety disorder (SAD) detection, and emotion recognition using DEAP dataset. Validity of our hypothesis that model 2 will significantly outperform model 1 is borne out in the results, with accuracy $...

Phase Angle Spatial Embedding (PhASE) - A Kernel Method for Studying the Topology of the Human Functional Connectome

Modern resting-state functional magnetic resonance imaging (rs-fMRI) provides a wealth of informa... more Modern resting-state functional magnetic resonance imaging (rs-fMRI) provides a wealth of information about the inherent functional connectivity of the human brain. However, understanding the role of negative correlations and the nonlinear topology of rs-fMRI remains a challenge. To address these challenges, we propose a novel graph embedding technique, phase angle spatial embedding (PhASE), to study the “intrinsic geometry” of the functional connectome. PhASE both incorporates negative correlations as well as reformulates the connectome modularity problem as a kernel two-sample test, using a kernel method that induces a maximum mean discrepancy (MMD) in a reproducing kernel Hilbert space (RKHS). By solving a graph partition that maximizes this MMD, PhASE identifies the most functionally distinct brain modules. As a test case, we analyzed a public rs-fMRI dataset to compare male and female connectomes using PhASE and minimum spanning tree inferential statistics. These results show s...

The power of negative thinking

Health news, 2002

Computer Engineering Program, University of Wisconsin-Stout, Menomonie, WI, USA Department of Psy... more Computer Engineering Program, University of Wisconsin-Stout, Menomonie, WI, USA Department of Psychiatry, University of Illinois, Chicago, IL, USA Department of Computer Science, University of Illinois, Chicago, IL, USA Department of Bioengineering, University of Illinois, Chicago, IL, USA Imaging Genetics Center, and Institute for Neuroimaging and Informatics, Keck School of Medicine of USC, CA, USA Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, WI, USA

Immersive Analytics for Clinical Neuroscience

This paper introduces NeuroCave, an open-source immersive analytics software tool for exploring a... more This paper introduces NeuroCave, an open-source immersive analytics software tool for exploring and making sense of both structural and functional connectomes describing the interconnectivity between brain regions. The software supports visual analysis tasks for clinical neuroscientists, facilitating explorations of connectome datasets used in comparative group studies. Researchers can enter and leave virtual reality as desired in order to visualize and reason about connectome datasets from a range of different perspectives.

Tensor Distribution Function Demixes Fibers in Multi-Shell High Angular Resolution Diffusion Images

Introduction: Diffusion tensor imaging (DTI) reveals white matter microstructure and fiber pathwa... more Introduction: Diffusion tensor imaging (DTI) reveals white matter microstructure and fiber pathways in the living brain by examining the 3D diffusion profile of water molecules in brain tissue. Even so, DTIderived measures are incorrect where fibers cross or mix, as the single tensor model cannot resolve these more complicated white matter configurations. Diffusion spectrum imaging (DSI) avoids this issue by direct model-free Fourier inversion of the diffusion signal, but is time intensive, as it measures the signal using 6D Cartesian sampling [1]. An alternative approach based on sampling only on one or multiple spherical shells in q-space has been proposed, referred to as high angular resolution diffusion imaging [2]. Each spherical shell is a 2D manifold with a specific b-value [3], and the required sampling grows quadratically with the desired angular resolution, as opposed to cubically with the spatial and q-space resolutions in DSI [4].

The Importance of Being Negative: A serious treatment of non-trivial edges in brain functional connectome

Understanding the modularity of fMRI-derived brain networks or connectomes can inform the study o... more Understanding the modularity of fMRI-derived brain networks or connectomes can inform the study of brain function organization. However, fMRI connectomes additionally involve negative edges, which are not rigorously accounted for by existing approaches to modularity that either ignores or arbitrarily weight these connections. Furthermore, most Q maximization-based modularity algorithms yield variable results with suboptimal reproducibility. Here we present an alternative, reproducible approach that exploits how frequent the BOLD-signal correlation between two nodes is negative. We validated this novel probability-based modularity approach on two independent publicly-available resting-state connectome dataset (the Human Connectome Project and the 1000 Functional Connectomes) and demonstrated that negative correlations alone are sufficient in understanding resting-state modularity. In fact, this approach a) permits a dual formulation, leading to equivalent solutions regardless of whet...

Unbiased Volumetric Registration via Nonlinear Elastic Regularization

In this paper, we propose a new large-deformation nonlinear image registration model in three dim... more In this paper, we propose a new large-deformation nonlinear image registration model in three dimensions, based on nonlinear elastic regularization and unbiased registration. Both the nonlinear elastic and the unbiased functionals are simplified introducing, in the modeling, a second unknown that mimics the Jacobian matrix of the displacement vector field, reducing the minimization to involve linear differential equations. In contrast to recently proposed unbiased fluid registration method, the new model is written in a unified variational form and is minimized using gradient descent on the corresponding Euler-Lagrange equations. As a result, the new unbiased nonlinear elasticity model is computationally more efficient and easier to implement than the unbiased fluid registration. The model was tested using three-dimensional serial MRI images and shown to have some advantages for computational neuroimaging.

Real-Time Monitoring: A Key Element in Personalized Health and Precision Health

FOCUS

Current management of psychiatric disorders relies heavily on retrospective, subjective reports p... more Current management of psychiatric disorders relies heavily on retrospective, subjective reports provided by patients and their families. Consequently, psychiatric services are often provisioned inefficiently and with suboptimal outcomes. Recent advances in computing and sensor technologies have enabled the development of real-time monitoring systems for the diagnosis and management of psychiatric disorders. The state of these technologies is rapidly evolving, with passive monitoring and predictive modeling as two areas that have great potential to affect psychiatric care. Although outpatient psychiatry probably stands to benefit the most from the use of real-time monitoring technologies, there are also several ways in which inpatient psychiatry may also benefit. As the capabilities of these technologies increase and their use becomes more common, many ethical and legal issues will need to be considered. The role of governmental regulatory bodies and nongovernmental organizations in providing oversight of the implementation of these technologies is an active area of discussion.

Passive Sensing of Affective and Cognitive Functioning in Mood Disorders by Analyzing Keystroke Kinematics and Speech Dynamics

Studies in Neuroscience, Psychology and Behavioral Economics

Mood disorders can be difficult to diagnose, evaluate, and treat. They involve affective and cogn... more Mood disorders can be difficult to diagnose, evaluate, and treat. They involve affective and cognitive components, both of which need to be closely monitored over the course of the illness. Current methods like interviews and rating scales can be cumbersome, sometimes ineffective, and oftentimes infrequently administered. Even ecological momentary assessments, when used alone, are susceptible to many of the same limitations and still require active participation from the subject. Passive, continuous, frictionless, and ubiquitous means of recording and analyzing mood and cognition obviate the need for more frequent and lengthier doctor’s visits, can help identify misdiagnoses, and would potentially serve as an early warning system to better manage medication adherence and prevent hospitalizations. Activity trackers and smartwatches have long provided exactly such a tool for evaluating physical fitness. What if smartphones, voice assistants, and eventually Internet of Things devices and ambient computing systems could similarly serve as fitness trackers for the brain, without imposing any additional burden on the user? In this chapter, we explore two such early approaches—an in-depth analytical technique based on examining meta-features of virtual keyboard usage and corresponding typing kinematics, and another method which analyzes the acoustic features of recorded speech—to passively and unobtrusively understand mood and cognition in people with bipolar disorder. We review innovative studies that have used these methods to build mathematical models and machine learning frameworks that can provide deep insights into users’ mood and cognitive states. We then outline future research considerations and close by discussing the opportunities and challenges afforded by these modes of researching mood disorders and passive sensing approaches in general.

Exact Combinatorial Inference for Brain Images

Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

The permutation test is known as the exact test procedure in statistics. However, often it is not... more The permutation test is known as the exact test procedure in statistics. However, often it is not exact in practice and only an approximate method since only a small fraction of every possible permutation is generated. Even for a small sample size, it often requires to generate tens of thousands permutations, which can be a serious computational bottleneck. In this paper, we propose a novel combinatorial inference procedure that enumerates all possible permutations combinatorially without any resampling. The proposed method is validated against the standard permutation test in simulation studies with the ground truth. The method is further applied in twin DTI study in determining the genetic contribution of the minimum spanning tree of the structural brain connectivity.

EEG Classification based on Image Configuration in Social Anxiety Disorder

2019 9th International IEEE/EMBS Conference on Neural Engineering (NER), Mar 1, 2019

The problem of detecting the presence of Social Anxiety Disorder (SAD) using Electroencephalograp... more The problem of detecting the presence of Social Anxiety Disorder (SAD) using Electroencephalography (EEG) for classification has seen limited study and is addressed with a new approach that seeks to exploit the knowledge of EEG sensor spatial configuration. Two classification models, one which ignores the configuration (model 1) and one that exploits it with different interpolation methods (model 2), are studied. Performance of these two models is examined for analyzing 34 EEG data channels each consisting of five frequency bands and further decomposed with a filter bank. The data are collected from 64 subjects consisting of healthy controls and patients with SAD. Validity of our hypothesis that model 2 will significantly outperform model 1 is borne out in the results, with accuracy 6-7% higher for model 2 for each machine learning algorithm we investigated. Convolutional Neural Networks (CNN) were found to provide much better performance than SVM and kNNs.

dpMood: Exploiting Local and Periodic Typing Dynamics for Personalized Mood Prediction

2018 IEEE International Conference on Data Mining (ICDM), Nov 1, 2018

Mood disorders are common and associated with significant morbidity and mortality. Early diagnosi... more Mood disorders are common and associated with significant morbidity and mortality. Early diagnosis has the potential to greatly alleviate the burden of mental illness and the ever increasing costs to families and society. Mobile devices provide us a promising opportunity to detect the users' mood in an unobtrusive manner. In this study, we use a custom keyboard which collects keystrokes' meta-data and accelerometer values. Based on the collected time series data in multiple modalities, we propose a deep personalized mood prediction approach, called dpMood, by integrating convolutional and recurrent deep architectures as well as exploring each individual's circadian rhythm. Experimental results not only demonstrate the feasibility and effectiveness of using smart-phone meta-data to predict the presence and severity of mood disturbances in bipolar subjects, but also show the potential of personalized medical treatment for mood disorders.

Sequential Keystroke Behavioral Biometrics for Mobile User Identification via Multi-view Deep Learning

Lecture Notes in Computer Science, 2017

With the rapid growth in smartphone usage, more organizations begin to focus on providing better ... more With the rapid growth in smartphone usage, more organizations begin to focus on providing better services for mobile users. User identification can help these organizations to identify their customers and then cater services that have been customized for them. Currently, the use of cookies is the most common form to identify users. However, cookies are not easily transportable (e.g., when a user uses a different login account, cookies do not follow the user). This limitation motivates the need to use behavior biometric for user identification. In this paper, we propose DEEPSERVICE, a new technique that can identify mobile users based on user's keystroke information captured by a special keyboard or web browser. Our evaluation results indicate that DEEPSERVICE is highly accurate in identifying mobile users (over 93% accuracy). The technique is also efficient and only takes less than 1 ms to perform identification.

Predicting Mood Disturbance Severity with Mobile Phone Keystroke Metadata: A BiAffect Digital Phenotyping Study

Journal of medical Internet research, Jan 20, 2018

Mood disorders are common and associated with significant morbidity and mortality. Better tools a... more Mood disorders are common and associated with significant morbidity and mortality. Better tools are needed for their diagnosis and treatment. Deeper phenotypic understanding of these disorders is integral to the development of such tools. This study is the first effort to use passively collected mobile phone keyboard activity to build deep digital phenotypes of depression and mania. The objective of our study was to investigate the relationship between mobile phone keyboard activity and mood disturbance in subjects with bipolar disorders and to demonstrate the feasibility of using passively collected mobile phone keyboard metadata features to predict manic and depressive signs and symptoms as measured via clinician-administered rating scales. Using a within-subject design of 8 weeks, subjects were provided a mobile phone loaded with a customized keyboard that passively collected keystroke metadata. Subjects were administered the Hamilton Depression Rating Scale (HDRS) and Young Mani...

BRAINtrinsic: A Virtual Reality-Compatible Tool for Exploring Intrinsic Topologies of the Human Brain Connectome

Lecture Notes in Computer Science, 2015

Thanks to advances in non-invasive technologies such as functional Magnetic Resonance Imaging (fM... more Thanks to advances in non-invasive technologies such as functional Magnetic Resonance Imaging (fMRI) and Diffusion Tensor Imaging (DTI), highly-detailed maps of brain structure and function can now be collected. In this context, brain connectomics have emerged as a fast growing field that aims at understanding these comprehensive maps of brain connectivity using sophisticated computational models. In this paper we present BRAINtrinsic, an innovative web-based 3D visual analytics tool that allows users to intuitively and iteratively interact with connectome data. Moreover, BRAINtrinsic implements a novel visualization platform that reconstructs connectomes' intrinsic geometry, i.e., the topological space as informed by brain connectivity, via dimensionality reduction. BRAINtrinsic is implemented with virtual reality in mind and is fully compatible with the Oculus Rift technology. Last, we demonstrate its effectiveness through a series of case studies involving both structural and resting-state MR imaging data.

Brain Dynamics Through the Lens of Statistical Mechanics by Unifying Structure and Function

This paper introduces a novel method that unifies structural connectivity and functional time ser... more 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 statistical mechanics, hereby bypassing traditional BOLD correlations. The spin model is a function of a coupling interaction (traditionally positive or negative) and spin-states of paired brain regions. Observed functional time series represent brain states over time. A maximum pseudolikelihood with a constraint is used to estimate the coupling interaction. The constraint is introduced as a penalty function such that the learned interactions are scaled relative to structural connectivity; the sign of the interactions may infer inhibition or excitation over an underlying structure. We evaluate our method by comparing a group of otherwise healthy APO...

$Research paper thumbnail of Shared white matter alterations across emotional disorders: A voxel-based meta-analysis of fractional anisotropy$

Shared white matter alterations across emotional disorders: A voxel-based meta-analysis of fractional anisotropy

by Lisanne Jenkins and Alex Leow

NeuroImage: Clinical, 2016