1
|
Durstewitz D, Koppe G, Thurm MI. Reconstructing computational system dynamics from neural data with recurrent neural networks. Nat Rev Neurosci 2023; 24:693-710. [PMID: 37794121 DOI: 10.1038/s41583-023-00740-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/18/2023] [Indexed: 10/06/2023]
Abstract
Computational models in neuroscience usually take the form of systems of differential equations. The behaviour of such systems is the subject of dynamical systems theory. Dynamical systems theory provides a powerful mathematical toolbox for analysing neurobiological processes and has been a mainstay of computational neuroscience for decades. Recently, recurrent neural networks (RNNs) have become a popular machine learning tool for studying the non-linear dynamics of neural and behavioural processes by emulating an underlying system of differential equations. RNNs have been routinely trained on similar behavioural tasks to those used for animal subjects to generate hypotheses about the underlying computational mechanisms. By contrast, RNNs can also be trained on the measured physiological and behavioural data, thereby directly inheriting their temporal and geometrical properties. In this way they become a formal surrogate for the experimentally probed system that can be further analysed, perturbed and simulated. This powerful approach is called dynamical system reconstruction. In this Perspective, we focus on recent trends in artificial intelligence and machine learning in this exciting and rapidly expanding field, which may be less well known in neuroscience. We discuss formal prerequisites, different model architectures and training approaches for RNN-based dynamical system reconstructions, ways to evaluate and validate model performance, how to interpret trained models in a neuroscience context, and current challenges.
Collapse
Affiliation(s)
- Daniel Durstewitz
- Dept. of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany.
- Interdisciplinary Center for Scientific Computing, Heidelberg University, Heidelberg, Germany.
- Faculty of Physics and Astronomy, Heidelberg University, Heidelberg, Germany.
| | - Georgia Koppe
- Dept. of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
- Dept. of Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
- Hector Institute for Artificial Intelligence in Psychiatry, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| | - Max Ingo Thurm
- Dept. of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany
| |
Collapse
|
2
|
Zhang Z, Li K, Hu X. Mapping nonlinear brain dynamics by phase space embedding with fMRI data. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104521] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/09/2023]
|
3
|
Hanganu-Opatz IL, Klausberger T, Sigurdsson T, Nieder A, Jacob SN, Bartos M, Sauer JF, Durstewitz D, Leibold C, Diester I. Resolving the prefrontal mechanisms of adaptive cognitive behaviors: A cross-species perspective. Neuron 2023; 111:1020-1036. [PMID: 37023708 DOI: 10.1016/j.neuron.2023.03.017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2022] [Revised: 02/15/2023] [Accepted: 03/10/2023] [Indexed: 04/08/2023]
Abstract
The prefrontal cortex (PFC) enables a staggering variety of complex behaviors, such as planning actions, solving problems, and adapting to new situations according to external information and internal states. These higher-order abilities, collectively defined as adaptive cognitive behavior, require cellular ensembles that coordinate the tradeoff between the stability and flexibility of neural representations. While the mechanisms underlying the function of cellular ensembles are still unclear, recent experimental and theoretical studies suggest that temporal coordination dynamically binds prefrontal neurons into functional ensembles. A so far largely separate stream of research has investigated the prefrontal efferent and afferent connectivity. These two research streams have recently converged on the hypothesis that prefrontal connectivity patterns influence ensemble formation and the function of neurons within ensembles. Here, we propose a unitary concept that, leveraging a cross-species definition of prefrontal regions, explains how prefrontal ensembles adaptively regulate and efficiently coordinate multiple processes in distinct cognitive behaviors.
Collapse
Affiliation(s)
- Ileana L Hanganu-Opatz
- Institute of Developmental Neurophysiology, Center for Molecular Neurobiology, Hamburg Center of Neuroscience, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.
| | - Thomas Klausberger
- Center for Brain Research, Division of Cognitive Neurobiology, Medical University of Vienna, Vienna, Austria
| | - Torfi Sigurdsson
- Institute of Neurophysiology, Goethe University, Frankfurt, Germany
| | - Andreas Nieder
- Animal Physiology Unit, Institute of Neurobiology, University of Tübingen, 72076 Tübingen, Germany
| | - Simon N Jacob
- Translational Neurotechnology Laboratory, Department of Neurosurgery, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany
| | - Marlene Bartos
- Institute for Physiology I, Medical Faculty, University of Freiburg, Freiburg im Breisgau, Germany
| | - Jonas-Frederic Sauer
- Institute for Physiology I, Medical Faculty, University of Freiburg, Freiburg im Breisgau, Germany
| | - Daniel Durstewitz
- Department of Theoretical Neuroscience, Central Institute of Mental Health & Faculty of Physics and Astronomy, Heidelberg University, Heidelberg, Germany
| | - Christian Leibold
- Faculty of Biology, Bernstein Center Freiburg, BrainLinks-BrainTools, University of Freiburg, Freiburg im Breisgau, Germany
| | - Ilka Diester
- Optophysiology - Optogenetics and Neurophysiology, IMBIT // BrainLinks-BrainTools, University of Freiburg, Freiburg im Breisgau, Germany.
| |
Collapse
|
4
|
Sip V, Hashemi M, Dickscheid T, Amunts K, Petkoski S, Jirsa V. Characterization of regional differences in resting-state fMRI with a data-driven network model of brain dynamics. SCIENCE ADVANCES 2023; 9:eabq7547. [PMID: 36930710 PMCID: PMC10022900 DOI: 10.1126/sciadv.abq7547] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/28/2022] [Accepted: 02/16/2023] [Indexed: 06/18/2023]
Abstract
Model-based data analysis of whole-brain dynamics links the observed data to model parameters in a network of neural masses. Recently, studies focused on the role of regional variance of model parameters. Such analyses however necessarily depend on the properties of preselected neural mass model. We introduce a method to infer from the functional data both the neural mass model representing the regional dynamics and the region- and subject-specific parameters while respecting the known network structure. We apply the method to human resting-state fMRI. We find that the underlying dynamics can be described as noisy fluctuations around a single fixed point. The method reliably discovers three regional parameters with clear and distinct role in the dynamics, one of which is strongly correlated with the first principal component of the gene expression spatial map. The present approach opens a novel way to the analysis of resting-state fMRI with possible applications for understanding the brain dynamics during aging or neurodegeneration.
Collapse
Affiliation(s)
- Viktor Sip
- Aix-Marseille Université, INSERM, Institut de Neurosciences de Systèmes (INS), Marseille, France
| | - Meysam Hashemi
- Aix-Marseille Université, INSERM, Institut de Neurosciences de Systèmes (INS), Marseille, France
| | - Timo Dickscheid
- Institute of Neuroscience and Medicine (INM-1), Research Centre Jülich, Jülich, Germany
| | - Katrin Amunts
- Institute of Neuroscience and Medicine (INM-1), Research Centre Jülich, Jülich, Germany
| | - Spase Petkoski
- Aix-Marseille Université, INSERM, Institut de Neurosciences de Systèmes (INS), Marseille, France
| | - Viktor Jirsa
- Aix-Marseille Université, INSERM, Institut de Neurosciences de Systèmes (INS), Marseille, France
| |
Collapse
|
5
|
Fu Y, Niu M, Gao Y, Dong S, Huang Y, Zhang Z, Zhuo C. Altered nonlinear Granger causality interactions in the large-scale brain networks of patients with schizophrenia. J Neural Eng 2022; 19. [PMID: 36579785 DOI: 10.1088/1741-2552/acabe7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2022] [Accepted: 12/15/2022] [Indexed: 12/23/2022]
Abstract
Objective.It has been demonstrated that schizophrenia (SZ) is characterized by functional dysconnectivity involving extensive brain networks. However, the majority of previous studies utilizing resting-state functional magnetic resonance imaging (fMRI) to infer abnormal functional connectivity (FC) in patients with SZ have focused on the linear correlation that one brain region may influence another, ignoring the inherently nonlinear properties of fMRI signals.Approach. In this paper, we present a neural Granger causality (NGC) technique for examining the changes in SZ's nonlinear causal couplings. We develop static and dynamic NGC-based analyses of large-scale brain networks at several network levels, estimating complicated temporal and causal relationships in SZ patients.Main results. We find that the NGC-based FC matrices can detect large and significant differences between the SZ and healthy control groups at both the regional and subnetwork scales. These differences are persistent and significantly overlapped at various network sparsities regardless of whether the brain networks were built using static or dynamic techniques. In addition, compared to controls, patients with SZ exhibited extensive NGC confusion patterns throughout the entire brain.Significance. These findings imply that the NGC-based FCs may be a useful method for quantifying the abnormalities in the causal influences of patients with SZ, hence shedding fresh light on the pathophysiology of this disorder.
Collapse
Affiliation(s)
- Yu Fu
- College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, People's Republic of China
| | - Meng Niu
- Department of Radiology, The First Hospital of Lanzhou University, Lanzhou, People's Republic of China
| | - Yuanhang Gao
- College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, People's Republic of China
| | - Shunjie Dong
- College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, People's Republic of China
| | - Yanyan Huang
- College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, People's Republic of China
| | - Zhe Zhang
- School of Physics, Hangzhou Normal University, Hangzhou, People's Republic of China.,Institute of Brain Science, Hangzhou Normal University, Hangzhou, People's Republic of China
| | - Cheng Zhuo
- College of Information Science & Electronic Engineering, Zhejiang University, Hangzhou, People's Republic of China.,Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province, Hangzhou, People's Republic of China
| |
Collapse
|
6
|
Keshtkaran MR, Sedler AR, Chowdhury RH, Tandon R, Basrai D, Nguyen SL, Sohn H, Jazayeri M, Miller LE, Pandarinath C. A large-scale neural network training framework for generalized estimation of single-trial population dynamics. Nat Methods 2022; 19:1572-1577. [PMID: 36443486 PMCID: PMC9825111 DOI: 10.1038/s41592-022-01675-0] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2021] [Accepted: 10/14/2022] [Indexed: 11/30/2022]
Abstract
Achieving state-of-the-art performance with deep neural population dynamics models requires extensive hyperparameter tuning for each dataset. AutoLFADS is a model-tuning framework that automatically produces high-performing autoencoding models on data from a variety of brain areas and tasks, without behavioral or task information. We demonstrate its broad applicability on several rhesus macaque datasets: from motor cortex during free-paced reaching, somatosensory cortex during reaching with perturbations, and dorsomedial frontal cortex during a cognitive timing task.
Collapse
Affiliation(s)
- Mohammad Reza Keshtkaran
- Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
| | - Andrew R Sedler
- Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
- Center for Machine Learning, Georgia Institute of Technology, Atlanta, GA, USA
| | - Raeed H Chowdhury
- Department of Biomedical Engineering, Northwestern University, Evanston, IL, USA
- Department of Bioengineering, University of Pittsburgh, Pittsburgh, PA, USA
| | - Raghav Tandon
- Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
- Center for Machine Learning, Georgia Institute of Technology, Atlanta, GA, USA
| | - Diya Basrai
- Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA
- Physiology and Neuroscience, University of California, San Diego, La Jolla, CA, USA
| | - Sarah L Nguyen
- College of Computing, Georgia Institute of Technology, Atlanta, GA, USA
| | - Hansem Sohn
- Department of Brain and Cognitive Sciences, McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Mehrdad Jazayeri
- Department of Brain and Cognitive Sciences, McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Lee E Miller
- Department of Biomedical Engineering, Northwestern University, Evanston, IL, USA
- Department of Neuroscience, Northwestern University, Chicago, IL, USA
- Department of Physical Medicine and Rehabilitation, Northwestern University, Chicago, IL, USA
- Shirley Ryan AbilityLab, Chicago, IL, USA
| | - Chethan Pandarinath
- Wallace H. Coulter Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, GA, USA.
- Center for Machine Learning, Georgia Institute of Technology, Atlanta, GA, USA.
- Department of Neurosurgery, Emory University, Atlanta, GA, USA.
| |
Collapse
|
7
|
John YJ, Sawyer KS, Srinivasan K, Müller EJ, Munn BR, Shine JM. It's about time: Linking dynamical systems with human neuroimaging to understand the brain. Netw Neurosci 2022; 6:960-979. [PMID: 36875012 PMCID: PMC9976648 DOI: 10.1162/netn_a_00230] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2021] [Accepted: 01/04/2022] [Indexed: 11/04/2022] Open
Abstract
Most human neuroscience research to date has focused on statistical approaches that describe stationary patterns of localized neural activity or blood flow. While these patterns are often interpreted in light of dynamic, information-processing concepts, the static, local, and inferential nature of the statistical approach makes it challenging to directly link neuroimaging results to plausible underlying neural mechanisms. Here, we argue that dynamical systems theory provides the crucial mechanistic framework for characterizing both the brain's time-varying quality and its partial stability in the face of perturbations, and hence, that this perspective can have a profound impact on the interpretation of human neuroimaging results and their relationship with behavior. After briefly reviewing some key terminology, we identify three key ways in which neuroimaging analyses can embrace a dynamical systems perspective: by shifting from a local to a more global perspective, by focusing on dynamics instead of static snapshots of neural activity, and by embracing modeling approaches that map neural dynamics using "forward" models. Through this approach, we envisage ample opportunities for neuroimaging researchers to enrich their understanding of the dynamic neural mechanisms that support a wide array of brain functions, both in health and in the setting of psychopathology.
Collapse
Affiliation(s)
- Yohan J. John
- Neural Systems Laboratory, Department of Health Sciences, Boston University, Boston, MA, USA
| | - Kayle S. Sawyer
- Departments of Anatomy and Neurobiology, Boston University, Boston University, Boston, MA, USA
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
- Boston VA Healthcare System, Boston, MA, USA
- Sawyer Scientific, LLC, Boston, MA, USA
| | - Karthik Srinivasan
- McGovern Institute for Brain Research, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Eli J. Müller
- Brain and Mind Center, University of Sydney, Sydney, NSW, Australia
| | - Brandon R. Munn
- Brain and Mind Center, University of Sydney, Sydney, NSW, Australia
| | - James M. Shine
- Brain and Mind Center, University of Sydney, Sydney, NSW, Australia
| |
Collapse
|
8
|
Ramezanian-Panahi M, Abrevaya G, Gagnon-Audet JC, Voleti V, Rish I, Dumas G. Generative Models of Brain Dynamics. Front Artif Intell 2022; 5:807406. [PMID: 35910192 PMCID: PMC9335006 DOI: 10.3389/frai.2022.807406] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/02/2021] [Accepted: 06/10/2022] [Indexed: 01/28/2023] Open
Abstract
This review article gives a high-level overview of the approaches across different scales of organization and levels of abstraction. The studies covered in this paper include fundamental models in computational neuroscience, nonlinear dynamics, data-driven methods, as well as emergent practices. While not all of these models span the intersection of neuroscience, AI, and system dynamics, all of them do or can work in tandem as generative models, which, as we argue, provide superior properties for the analysis of neuroscientific data. We discuss the limitations and unique dynamical traits of brain data and the complementary need for hypothesis- and data-driven modeling. By way of conclusion, we present several hybrid generative models from recent literature in scientific machine learning, which can be efficiently deployed to yield interpretable models of neural dynamics.
Collapse
Affiliation(s)
| | - Germán Abrevaya
- Mila-Quebec AI Institute, Montréal, QC, Canada
- Departamento de Física, Facultad de Ciencias Exactas y Naturales, Instituto de Física de Buenos Aires (IFIBA), CONICET, Universidad de Buenos Aires, Buenos Aires, Argentina
| | | | - Vikram Voleti
- Mila-Quebec AI Institute, Montréal, QC, Canada
- Université de Montréal, Montréal, QC, Canada
| | - Irina Rish
- Mila-Quebec AI Institute, Montréal, QC, Canada
- Université de Montréal, Montréal, QC, Canada
| | - Guillaume Dumas
- Mila-Quebec AI Institute, Montréal, QC, Canada
- Université de Montréal, Montréal, QC, Canada
- Department of Psychiatry, CHU Sainte-Justine Research Center, Mila-Quebec AI Institute, Université de Montréal, Montréal, QC, Canada
| |
Collapse
|
9
|
Cotes RO, Boazak M, Griner E, Jiang Z, Kim B, Bremer W, Seyedi S, Bahrami Rad A, Clifford GD. Multimodal Assessment of Schizophrenia and Depression Utilizing Video, Acoustic, Locomotor, Electroencephalographic, and Heart Rate Technology: Protocol for an Observational Study. JMIR Res Protoc 2022; 11:e36417. [PMID: 35830230 PMCID: PMC9330209 DOI: 10.2196/36417] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2022] [Revised: 05/30/2022] [Accepted: 05/31/2022] [Indexed: 11/20/2022] Open
Abstract
Background Current standards of psychiatric assessment and diagnostic evaluation rely primarily on the clinical subjective interpretation of a patient’s outward manifestations of their internal state. While psychometric tools can help to evaluate these behaviors more systematically, the tools still rely on the clinician’s interpretation of what are frequently nuanced speech and behavior patterns. With advances in computing power, increased availability of clinical data, and improving resolution of recording and sensor hardware (including acoustic, video, accelerometer, infrared, and other modalities), researchers have begun to demonstrate the feasibility of cutting-edge technologies in aiding the assessment of psychiatric disorders. Objective We present a research protocol that utilizes facial expression, eye gaze, voice and speech, locomotor, heart rate, and electroencephalography monitoring to assess schizophrenia symptoms and to distinguish patients with schizophrenia from those with other psychiatric disorders and control subjects. Methods We plan to recruit three outpatient groups: (1) 50 patients with schizophrenia, (2) 50 patients with unipolar major depressive disorder, and (3) 50 individuals with no psychiatric history. Using an internally developed semistructured interview, psychometrically validated clinical outcome measures, and a multimodal sensing system utilizing video, acoustic, actigraphic, heart rate, and electroencephalographic sensors, we aim to evaluate the system’s capacity in classifying subjects (schizophrenia, depression, or control), to evaluate the system’s sensitivity to within-group symptom severity, and to determine if such a system can further classify variations in disorder subtypes. Results Data collection began in July 2020 and is expected to continue through December 2022. Conclusions If successful, this study will help advance current progress in developing state-of-the-art technology to aid clinical psychiatric assessment and treatment. If our findings suggest that these technologies are capable of resolving diagnoses and symptoms to the level of current psychometric testing and clinician judgment, we would be among the first to develop a system that can eventually be used by clinicians to more objectively diagnose and assess schizophrenia and depression with the possibility of less risk of bias. Such a tool has the potential to improve accessibility to care; to aid clinicians in objectively evaluating diagnoses, severity of symptoms, and treatment efficacy through time; and to reduce treatment-related morbidity. International Registered Report Identifier (IRRID) DERR1-10.2196/36417
Collapse
Affiliation(s)
- Robert O Cotes
- Department of Psychiatry and Behavioral Sciences, Emory University School of Medicine, Atlanta, GA, United States
| | - Mina Boazak
- Animo Sano Psychiatry, Durham, NC, United States
| | - Emily Griner
- Department of Psychiatry and Behavioral Sciences, Emory University School of Medicine, Atlanta, GA, United States
| | - Zifan Jiang
- Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, United States.,Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA, United States
| | - Bona Kim
- Visual Medical Education, Emory School of Medicine, Atlanta, GA, United States
| | - Whitney Bremer
- Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, United States
| | - Salman Seyedi
- Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, United States
| | - Ali Bahrami Rad
- Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, United States
| | - Gari D Clifford
- Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, United States.,Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA, United States
| |
Collapse
|
10
|
Thome J, Steinbach R, Grosskreutz J, Durstewitz D, Koppe G. Classification of amyotrophic lateral sclerosis by brain volume, connectivity, and network dynamics. Hum Brain Mapp 2022; 43:681-699. [PMID: 34655259 PMCID: PMC8720197 DOI: 10.1002/hbm.25679] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2021] [Accepted: 09/27/2021] [Indexed: 12/19/2022] Open
Abstract
Emerging studies corroborate the importance of neuroimaging biomarkers and machine learning to improve diagnostic classification of amyotrophic lateral sclerosis (ALS). While most studies focus on structural data, recent studies assessing functional connectivity between brain regions by linear methods highlight the role of brain function. These studies have yet to be combined with brain structure and nonlinear functional features. We investigate the role of linear and nonlinear functional brain features, and the benefit of combining brain structure and function for ALS classification. ALS patients (N = 97) and healthy controls (N = 59) underwent structural and functional resting state magnetic resonance imaging. Based on key hubs of resting state networks, we defined three feature sets comprising brain volume, resting state functional connectivity (rsFC), as well as (nonlinear) resting state dynamics assessed via recurrent neural networks. Unimodal and multimodal random forest classifiers were built to classify ALS. Out-of-sample prediction errors were assessed via five-fold cross-validation. Unimodal classifiers achieved a classification accuracy of 56.35-61.66%. Multimodal classifiers outperformed unimodal classifiers achieving accuracies of 62.85-66.82%. Evaluating the ranking of individual features' importance scores across all classifiers revealed that rsFC features were most dominant in classification. While univariate analyses revealed reduced rsFC in ALS patients, functional features more generally indicated deficits in information integration across resting state brain networks in ALS. The present work undermines that combining brain structure and function provides an additional benefit to diagnostic classification, as indicated by multimodal classifiers, while emphasizing the importance of capturing both linear and nonlinear functional brain properties to identify discriminative biomarkers of ALS.
Collapse
Affiliation(s)
- Janine Thome
- Department of Theoretical Neuroscience, Central Institute of Mental Health Mannheim, Medical Faculty MannheimHeidelberg UniversityGermany
- Clinic for Psychiatry and Psychotherapy, Central Institute of Mental Health Mannheim, Medical Faculty MannheimHeidelberg UniversityGermany
| | - Robert Steinbach
- Hans Berger Department of NeurologyJena University HospitalJenaGermany
| | - Julian Grosskreutz
- Precision Neurology, Department of NeurologyUniversity of LuebeckLuebeckGermany
| | - Daniel Durstewitz
- Department of Theoretical Neuroscience, Central Institute of Mental Health Mannheim, Medical Faculty MannheimHeidelberg UniversityGermany
| | - Georgia Koppe
- Department of Theoretical Neuroscience, Central Institute of Mental Health Mannheim, Medical Faculty MannheimHeidelberg UniversityGermany
- Clinic for Psychiatry and Psychotherapy, Central Institute of Mental Health Mannheim, Medical Faculty MannheimHeidelberg UniversityGermany
| |
Collapse
|
11
|
Kim JH, Zhang Y, Han K, Wen Z, Choi M, Liu Z. Representation learning of resting state fMRI with variational autoencoder. Neuroimage 2021; 241:118423. [PMID: 34303794 PMCID: PMC8485214 DOI: 10.1016/j.neuroimage.2021.118423] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2020] [Revised: 07/18/2021] [Accepted: 07/21/2021] [Indexed: 11/24/2022] Open
Abstract
Resting state functional magnetic resonance imaging (rsfMRI) data exhibits complex but structured patterns. However, the underlying origins are unclear and entangled in rsfMRI data. Here we establish a variational auto-encoder, as a generative model trainable with unsupervised learning, to disentangle the unknown sources of rsfMRI activity. After being trained with large data from the Human Connectome Project, the model has learned to represent and generate patterns of cortical activity and connectivity using latent variables. The latent representation and its trajectory represent the spatiotemporal characteristics of rsfMRI activity. The latent variables reflect the principal gradients of the latent trajectory and drive activity changes in cortical networks. Representational geometry captured as covariance or correlation between latent variables, rather than cortical connectivity, can be used as a more reliable feature to accurately identify subjects from a large group, even if only a short period of data is available in each subject. Our results demonstrate that VAE is a valuable addition to existing tools, particularly suited for unsupervised representation learning of resting state fMRI activity.
Collapse
Affiliation(s)
- Jung-Hoon Kim
- Department of Biomedical Engineering, University of Michigan, United States; Weldon School of Biomedical Engineering, Purdue University, United States
| | - Yizhen Zhang
- Department of Electrical Engineering and Computer Science, University of Michigan, United States
| | - Kuan Han
- Department of Electrical Engineering and Computer Science, University of Michigan, United States
| | - Zheyu Wen
- Department of Electrical Engineering and Computer Science, University of Michigan, United States
| | - Minkyu Choi
- Department of Electrical Engineering and Computer Science, University of Michigan, United States
| | - Zhongming Liu
- Department of Biomedical Engineering, University of Michigan, United States; Department of Electrical Engineering and Computer Science, University of Michigan, United States.
| |
Collapse
|
12
|
Psychiatric Illnesses as Disorders of Network Dynamics. BIOLOGICAL PSYCHIATRY: COGNITIVE NEUROSCIENCE AND NEUROIMAGING 2021; 6:865-876. [DOI: 10.1016/j.bpsc.2020.01.001] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/17/2019] [Accepted: 01/06/2020] [Indexed: 01/05/2023]
|
13
|
Koppe G, Meyer-Lindenberg A, Durstewitz D. Deep learning for small and big data in psychiatry. Neuropsychopharmacology 2021; 46:176-190. [PMID: 32668442 PMCID: PMC7689428 DOI: 10.1038/s41386-020-0767-z] [Citation(s) in RCA: 60] [Impact Index Per Article: 20.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/01/2020] [Revised: 07/04/2020] [Accepted: 07/06/2020] [Indexed: 02/06/2023]
Abstract
Psychiatry today must gain a better understanding of the common and distinct pathophysiological mechanisms underlying psychiatric disorders in order to deliver more effective, person-tailored treatments. To this end, it appears that the analysis of 'small' experimental samples using conventional statistical approaches has largely failed to capture the heterogeneity underlying psychiatric phenotypes. Modern algorithms and approaches from machine learning, particularly deep learning, provide new hope to address these issues given their outstanding prediction performance in other disciplines. The strength of deep learning algorithms is that they can implement very complicated, and in principle arbitrary predictor-response mappings efficiently. This power comes at a cost, the need for large training (and test) samples to infer the (sometimes over millions of) model parameters. This appears to be at odds with the as yet rather 'small' samples available in psychiatric human research to date (n < 10,000), and the ambition of predicting treatment at the single subject level (n = 1). Here, we aim at giving a comprehensive overview on how we can yet use such models for prediction in psychiatry. We review how machine learning approaches compare to more traditional statistical hypothesis-driven approaches, how their complexity relates to the need of large sample sizes, and what we can do to optimally use these powerful techniques in psychiatric neuroscience.
Collapse
Affiliation(s)
- Georgia Koppe
- Department of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Square J5, 68159, Mannheim, Germany.
- Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Square J5, 68159, Mannheim, Germany.
| | - Andreas Meyer-Lindenberg
- Department of Psychiatry and Psychotherapy, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Square J5, 68159, Mannheim, Germany.
| | - Daniel Durstewitz
- Department of Theoretical Neuroscience, Central Institute of Mental Health, Medical Faculty Mannheim, Heidelberg University, Square J5, 68159, Mannheim, Germany.
| |
Collapse
|
14
|
Huys QJM, Browning M, Paulus MP, Frank MJ. Advances in the computational understanding of mental illness. Neuropsychopharmacology 2021; 46:3-19. [PMID: 32620005 PMCID: PMC7688938 DOI: 10.1038/s41386-020-0746-4] [Citation(s) in RCA: 47] [Impact Index Per Article: 15.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/04/2020] [Revised: 06/11/2020] [Accepted: 06/15/2020] [Indexed: 12/11/2022]
Abstract
Computational psychiatry is a rapidly growing field attempting to translate advances in computational neuroscience and machine learning into improved outcomes for patients suffering from mental illness. It encompasses both data-driven and theory-driven efforts. Here, recent advances in theory-driven work are reviewed. We argue that the brain is a computational organ. As such, an understanding of the illnesses arising from it will require a computational framework. The review divides work up into three theoretical approaches that have deep mathematical connections: dynamical systems, Bayesian inference and reinforcement learning. We discuss both general and specific challenges for the field, and suggest ways forward.
Collapse
Affiliation(s)
- Quentin J M Huys
- Division of Psychiatry and Max Planck UCL Centre for Computational Psychiatry and Ageing Research, University College London, London, UK.
- Camden and Islington NHS Trust, London, UK.
| | - Michael Browning
- Computational Psychiatry Lab, Department of Psychiatry, University of Oxford, Oxford, UK
- Oxford Health NHS Trust, Oxford, UK
| | - Martin P Paulus
- Laureate Institute For Brain Research (LIBR), Tulsa, OK, USA
| | - Michael J Frank
- Cognitive, Linguistic & Psychological Sciences, Neuroscience Graduate Program, Brown University, Providence, RI, USA
- Carney Center for Computational Brain Science, Carney Institute for Brain Science Psychiatry and Human Behavior, Brown University, Providence, RI, USA
| |
Collapse
|