Analysis of an Automated Machine Learning Approach in Brain Predictive Modelling: A data-driven approach to Predict Brain Age from Cortical Anatomical Measures
Jessica Dafflon, Walter H. L Pinaya, Federico Turkheimer, James H. Cole, Robert Leech, Mathew A. Harris, Simon R. Cox, Heather C. Whalley, Andrew M. McIntosh, Peter J. Hellyer
The use of machine learning (ML) algorithms has significantly increased in neuroscience. However, from the vast extent of possible ML algorithms, which one is the optimal model to predict the target variable? What are the hyperparameters for such a model? Given the plethora of possible answers to these questions, in the last years, automated machine learning (autoML) has been gaining attention. Here, we apply an autoML library called TPOT which uses a tree-based representation of machine learning pipelines and conducts a genetic-programming based approach to find the model and its hyperparameters that more closely predicts the subject's true age. To explore autoML and evaluate its efficacy within neuroimaging datasets, we chose a problem that has been the focus of previous extensive study: brain age prediction. Without any prior knowledge, TPOT was able to scan through the model space and create pipelines that outperformed the state-of-the-art accuracy for Freesurfer-based models using only thickness and volume information for anatomical structure. In particular, we compared the performance of TPOT (mean accuracy error (MAE): $4.612 \pm .124$ years) and a Relevance Vector Regression (MAE $5.474 \pm .140$ years). TPOT also suggested interesting combinations of models that do not match the current most used models for brain prediction but generalise well to unseen data. AutoML showed promising results as a data-driven approach to find optimal models for neuroimaging applications.
A new generation of molecular tools for analyzing neural activity has been contributing to elucidate classical open questions in neuroscience. With enhanced GEVIs and advanced optical imaging techniques, voltage-imaging technologies have been increasingly used to observe the dynamics of large circuits. In this chapter, we describe how to combine cortical wide-field voltage imaging with hippocampal electrophysiology in awake behaving mice. Furthermore, we highlight how this method can be useful for different possible investigations.
The parcellation of the primate cerebral cortex into numbered regions, based on cytoarchitecture, began with the pioneering research of neuroanatomist Kobrinian Brodmann. While the borders between regions have changed somewhat, and in some cases continue to be disputed, the idea of dividing the cortex into distinct numbered areas has become central to the goal of understanding brain function. And indeed, areal maps do provide a good starting point for functional parcellation. It is obvious, for example, that visual area V1 has a different function than primary motor cortex. However, as with an…
Northwestern Polytechnical University（西北工业大学）；University of Texas at Arlington（德克萨斯大学阿灵顿分校）；University of Georgia（佐治亚大学）
Since gyri and sulci, two basic anatomical building blocks of cortical folding patterns, were suggested to bear different functional roles, a precise mapping from brain function to gyro-sulcal patterns can provide profound insights into both biological and artificial neural networks. However, there lacks a generic theory and effective computational model so far, due to the highly nonlinear relation between them, huge inter-individual variabilities and a sophisticated description of brain function regions/networks distribution as mosaics, such that spatial patterning of them has not been consid…
Effective representation of brain anatomical architecture is fundamental in understanding brain regularity and variability. Despite numerous efforts, it is still difficult to infer reliable anatomical correspondence at finer scale, given the tremendous individual variability in cortical folding patterns. It is even more challenging to disentangle common and individual patterns when comparing brains at different neuro-developmental stages. In this work, we developed a novel learning-based few-shot embedding framework to encode the cortical folding patterns into a latent space represented by a g…
University of California Santa Barbara（加州大学圣巴巴拉分校）；Ernst-Abbe-University（恩斯特·阿贝大学）
Cortical prostheses are devices implanted in the visual cortex that attempt to restore lost vision by electrically stimulating neurons. Currently, the vision provided by these devices is limited, and accurately predicting the visual percepts resulting from stimulation is an open challenge. We propose to address this challenge by utilizing 'brain-like' convolutional neural networks (CNNs), which have emerged as promising models of the visual system. To investigate the feasibility of adapting brain-like CNNs for modeling visual prostheses, we developed a proof-of-concept model to predict the per…
Ludwig-Maximilians-University（慕尼黑大学）；Technical University of Munich（慕尼黑工业大学）
The reconstruction of cerebral cortex surfaces from brain MRI scans is instrumental for the analysis of brain morphology and the detection of cortical thinning in neurodegenerative diseases like Alzheimer's disease (AD). Moreover, for a fine-grained analysis of atrophy patterns, the parcellation of the cortical surfaces into individual brain regions is required. For the former task, powerful deep learning approaches, which provide highly accurate brain surfaces of tissue boundaries from input MRI scans in seconds, have recently been proposed. However, these methods do not come with the ability…
Many studies have found evidence that the brain operates at a critical point, a processus known as self-organized criticality. A recent paper found remarkable scalings suggestive of criticality in systems as different as neural cultures, anesthetized or awake brains. We point out here that the diversity of these states would question any claimed role of criticality in information processing. Furthermore, we show that two non-critical systems pass all the tests for criticality, a control that was not provided in the original article. We conclude that such false positives demonstrate that the pr…
Graph Neural Network Reveals the Cortical Morphology of Local Brain Aging in Normal Cognition and Alzheimer's Disease
University of Southern California（南加州大学）；University of California, Berkeley（加州大学伯克利分校）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；King's College London（伦敦国王学院）
Network algorithmics and the emergence of synchronization in cortical models
当大脑信号被记录在脑电图或一些类似的大规模大脑活动记录中时，通常会观察到振荡模式，这些模式被认为反映了底层神经元集合的总电活动。虽然现在看来，这种模式在时间上与神经元的尖峰和空间上与其他大脑区域都参与了反馈回路，但可能解释这种回路存在的机制基本上仍然未知。在这里，我们提出了一个理论研究，这些问题的皮质模型，我们介绍了较早[内森A，巴博萨VC（2010年）网络算法和皮质突触重量分布的出现。Phys Rev E 81：021916]。我们开始与两个同步措施，旨在捕捉同步的可能性模型提供的整体尖峰活动的神经元和尖峰活动，导致突触后神经元的立即发射的定义。我们目前的计算结果，我们的皮质模型，在Erdens-Rényi意义上的模型是随机的，并在结构上确定性模型。我们已经发现，我们的皮层模型的算法组件最终提供了，通过两个同步措施，在所有情况下，这两种类型的同步出现一个强大的定量基础。反过来，这可以解释神经元组合电活动中的时间反馈回路和空间反馈回路的增加，因为空间上分离的大脑区域参与节奏行为。
How human brain function emerges from structure has intrigued researchers for decades and numerous models have been put forward, yet none of them yields a close structure-function relation. Here we present a resonance model based on neuronal spike timing dependent plasticity (STDP) principle to describe the spontaneous cortical activity by incorporating the dynamic interactions between neuronal populations into a wave equation, which is able to accurately predict the resting brain functional connectivity (FC), including the resting-state networks. Besides, the proposed model provides strong th…
Shared representations in brains and models reveal a two-route cortical organization during scene perception
Department of Cognition, Development and Education Psychology, Faculty of Psychology, University of Barcelona（认知、发展与教育心理学系，心理学学院，巴塞罗那大学）；Institute of Neurosciences, University of Barcelona（神经科学研究所，巴塞罗那大学）；Bellvitge Institute for Biomedical Research（Bellvitge生物医学研究 institute）
Community-Level Modeling of Gyral Folding Patterns for Robust and Anatomically Informed Individualized Brain Mapping
Department of Computer Science and Engineering, University of Texas at Arlington（计算机科学与工程系，德克萨斯大学阿灵顿分校）；School of Computing, University of Georgia（计算学院，佐治亚大学）；Department of Computer Science, Indiana University Indianapolis（计算机科学系，印第安纳大学印第安纳波利斯分校）
Vanderbilt University（范德堡大学）；Vanderbilt University Medical Center（范德堡大学医学中心）；Vanderbilt University Institute of Imaging Science（范德堡大学影像科学研究所）；Vanderbilt Brain Institute（范德堡脑科学研究所）
Mild traumatic brain injury (mTBI) is a complex syndrome that affects up to 600 per 100,000 individuals, with a particular concentration among military personnel. About half of all mTBI patients experience a diverse array of chronic symptoms which persist long after the acute injury. Hence, there is an urgent need for better understanding of the white matter and gray matter pathologies associated with mTBI to map which specific brain systems are impacted and identify courses of intervention. Previous works have linked mTBI to disruptions in white matter pathways and cortical surface abnormalit…
While many human imaging methodologies probe the structural and functional connectivity of the brain, techniques to investigate cortical networks in a causal and directional manner are critical but limited. The use of iEEG enables several approaches to directly characterize brain regions that are functionally connected and in some cases also establish directionality of these connections. In this chapter we focus on the basis, method and application of the cortico-cortical evoked potential (CCEP), whereby electrical pulses applied to one set of intracranial electrodes yields an electrically-ind…
University of Queensland（昆士兰大学）；Queensland Brain Institute（昆士兰脑研究所）
The emergence of explainability methods has enabled a better comprehension of how deep neural networks operate through concepts that are easily understood and implemented by the end user. While most explainability methods have been designed for traditional deep learning, some have been further developed for geometric deep learning, in which data are predominantly represented as graphs. These representations are regularly derived from medical imaging data, particularly in the field of neuroimaging, in which graphs are used to represent brain structural and functional wiring patterns (brain conn…
Multi-modal neuroimaging projects are advancing our understanding of human brain architecture, function, connectivity using high-quality non-invasive data from many subjects. However, ground truth validation of connectivity using invasive tracers is not feasible in humans. Our NonHuman Primate Neuroimaging & Neuroanatomy Project (NHP_NNP) is an international effort (6 laboratories in 5 countries) to: (i) acquire and analyze high-quality multi-modal brain imaging data of macaque and marmoset monkeys using protocols and methods adapted from the HCP; (ii) acquire quantitative invasive tract-traci…
The brain may be thought of as a many-body architecture with a spatio-temporal dynamics described by neuronal structures. The oscillatory nature of brain activity allows these structures (nodes) to be described as a set of coupled oscillators forming a network where the node dynamics, and that of the network topology can be studied. Quantifying its dynamics at various scales is an issue that claims to be explored for several brain activities, e.g., activity at rest. The resting-state associates the underlying brain dynamics of healthy subjects that are not actively compromised with sensory or …
Analyzing the brain in terms of organizational structures at intermediate scales provides an approach to negotiate the complexity arising from interactions between its large number of components. Focusing on a wiring diagram that spans the cortex, basal ganglia and thalamus of the Macaque brain, we provide a mesoscopic-level description of the topological architecture of one of the most well-studied mammalian connectomes. The robust modules we identify each comprise densely inter-connected cortical and sub-cortical areas that play complementary roles in executing specific cognitive functions. …
Objective: A major challenge in designing closed-loop brain-computer interfaces is finding optimal stimulation patterns as a function of ongoing neural activity for different subjects and objectives. Approach: To achieve goal-directed closed-loop neurostimulation, we propose "neural co-processors" which use artificial neural networks and deep learning to learn optimal closed-loop stimulation policies, shaping neural activity and bridging injured neural circuits for targeted repair and rehabilitation. The co-processor adapts the stimulation policy as the biological circuit itself adapts to the …
The large-scale structural ingredients of the brain and neural connectomes have been identified in recent years. These are, similar to the features found in many other real networks: the arrangement of brain regions into modules and the presence of highly connected regions (hubs) forming rich-clubs. Here, we examine how modules and hubs shape the collective dynamics on networks and we find that both ingredients lead to the emergence of complex dynamics. Comparing the connectomes of C. elegans, cats, macaques and humans to surrogate networks in which either modules or hubs are destroyed, we fin…
