Voxel selection framework in multi-voxel pattern analysis of FMRI data for prediction of neural response to visual stimuli

Neural Patterns of Social Pain in the Brain-Wide Representations Across Social Contexts

Empathy can be elicited by physiological pain, as well as in social contexts. Although physiological and different social contexts induce a strong subjective experience of empathy, the general and context-specific neural representations remain elusive. Here, it is combined fMRI with multivariate pattern analysis (MVPA) to establish neurofunctional models for social pain triggered by observing social exclusion and separation naturistic stimuli. The findings revealed that both social contexts engaged the empathy and social function networks. Notably, the intensity of pain empathy elicited by these two social stimuli does not significantly differentiate the neural representations of social exclusion and separation, suggesting context-specific neural representations underlying these experiences. Furthermore, this study established a model that traces the progression from physiological pain to social pain empathy. In conclusion, this study revealed the neural pathological foundations and interconnectedness of empathy induced by social and physiological stimuli and provide robust neuromarkers to precisely evaluate empathy across physiological and social domains.

Structurally-constrained encoding framework using a multi-voxel reduced-rank latent model for human natural vision

Objective. Voxel-wise visual encoding models based on convolutional neural networks (CNNs) have emerged as one of the prominent predictive tools of human brain activity via functional magnetic resonance imaging signals. While CNN-based models imitate the hierarchical structure of the human visual cortex to generate explainable features in response to natural visual stimuli, there is still a need for a brain-inspired model to predict brain responses accurately based on biomedical data.Approach. To bridge this gap, we propose a response prediction module called the Structurally Constrained Multi-Output (SCMO) module to include homologous correlations that arise between a group of voxels in a cortical region and predict more accurate responses.Main results. This module employs all the responses across a visual area to predict individual voxel-wise BOLD responses and therefore accounts for the population activity and collective behavior of voxels. Such a module can determine the relationships within each visual region by creating a structure matrix that represents the underlying voxel-to-voxel interactions. Moreover, since each response module in visual encoding tasks relies on the image features, we conducted experiments using two different feature extraction modules to assess the predictive performance of our proposed module. Specifically, we employed a recurrent CNN that integrates both feedforward and recurrent interactions, as well as the popular AlexNet model that utilizes feedforward connections.Significance.We demonstrate that the proposed framework provides a reliable predictive ability to generate brain responses across multiple areas, outperforming benchmark models in terms of stability and coherency of features.

A Cumulants-Based Human Brain Decoding

Human cognition is influenced by the way the nervous system processes information and is linked to this mechanical explanation of the human body’s cognitive function. Accuracy is the key emphasis in neuroscience which may be enhanced by utilising new hardware, mathematical, statistical, and computational methodologies. Feature extraction and feature selection also play a crucial function in gaining improved accuracy since the proper characteristics can identify brain states efficiently. However, both feature extraction and selection procedures are dependent on mathematical and statistical techniques which implies that mathematical and statistical techniques have a direct or indirect influence on prediction accuracy. The forthcoming challenges of the brain-computer interface necessitate a thorough critical understanding of the complicated structure and uncertain behavior of the brain. It is impossible to upgrade hardware periodically, and thus, an option is necessary to collect maximum information from the brain against varied actions. The mathematical and statistical combination could be the ideal answer for neuroscientists which can be utilised for feature extraction, feature selection, and classification. That is why in this research a statistical technique is offered together with specialised feature extraction and selection methods to increase the accuracy. A score fusion function is changed utilising an enhanced cumulants-driven likelihood ratio test employing multivariate pattern analysis. Functional MRI data were acquired from 12 patients versus a visual test that comprises of pictures from five distinct categories. After cleaning the data, feature extraction and selection were done using mathematical approaches, and lastly, the best match of the projected class was established using the likelihood ratio test. To validate the suggested approach, it is compared with the current methods reported in recent research.

Dynamics reconstruction and classification via Koopman features

Knowledge discovery and information extraction of large and complex datasets has attracted great attention in wide-ranging areas from statistics and biology to medicine. Tools from machine learning, data mining, and neurocomputing have been extensively explored and utilized to accomplish such compelling data analytics tasks. However, for time-series data presenting active dynamic characteristics, many of the state-of-the-art techniques may not perform well in capturing the inherited temporal structures in these data. In this paper, integrating the Koopman operator and linear dynamical systems theory with support vector machines, we develop an ovel dynamic data mining framework to construct low-dimensional linear models that approximate the nonlinear flow of high-dimensional time-series data generated by unknown nonlinear dynamical systems. This framework then immediately enables pattern recognition, e.g., classification, of complex time-series data to distinguish their dynamic behaviors by using the trajectories generated by the reduced linear systems. Moreover, we demonstrate the applicability and efficiency of this framework through the problems of time-series classification in bioinformatics and healthcare, including cognitive classification and seizure detection with fMRI and EEG data, respectively. The developed Koopman dynamic learning framework then lays a solid foundation for effective dynamic data mining and promises a mathematically justified method for extracting the dynamics and significant temporal structures of nonlinear dynamical systems.

Two-step paretial least square regression classifiers in brain-state decoding using functional magnetic resonance imaging

Multivariate analysis methods have been widely applied to decode brain states from functional magnetic resonance imaging (fMRI) data. Among various multivariate analysis methods, partial least squares regression (PLSR) is often used to select relevant features for decoding brain states. However, PLSR is seldom directly used as a classifier to decode brain states from fMRI data. It is unclear how PLSR classifiers perform in brain-state decoding using fMRI. In this study, we propose two types of two-step PLSR classifiers that use PLSR/sparse PLSR (SPLSR) to select features and PLSR for classification to improve the performance of the PLSR classifier. The results of simulated and real fMRI data demonstrated that the PLSR classifier using PLSR/SPLSR to select features outperformed both the PLSR classifier using a general linear model (GLM) and the support vector machine (SVM) using PLSR/SPLSR/GLM in most cases. Moreover, PLSR using SPLSR to select features showed the best performance among all of the methods. Compared to GLM, PLSR is more sensitive in selecting the voxels that are specific to each task. The results suggest that the performance of the PLSR classifier can be largely improved when the PLSR classifier is combined with the feature selection methods of SPLSR and PLSR.

Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network

Decoding of human brain activity has always been a primary goal in neuroscience especially with functional magnetic resonance imaging (fMRI) data. In recent years, Convolutional neural network (CNN) has become a popular method for the extraction of features due to its higher accuracy, however it needs a lot of computation and training data. In this study, an algorithm is developed using Multivariate pattern analysis (MVPA) and modified CNN to decode the behavior of brain for different images with limited data set. Selection of significant features is an important part of fMRI data analysis, since it reduces the computational burden and improves the prediction performance; significant features are selected using t-test. MVPA uses machine learning algorithms to classify different brain states and helps in prediction during the task. General linear model (GLM) is used to find the unknown parameters of every individual voxel and the classification is done using multi-class support vector machine (SVM). MVPA-CNN based proposed algorithm is compared with region of interest (ROI) based method and MVPA based estimated values. The proposed method showed better overall accuracy (68.6%) compared to ROI (61.88%) and estimation values (64.17%).

A decomposition model and voxel selection framework for fMRI analysis to predict neural response of visual stimuli

This paper presents an fMRI signal analysis methodology using geometric mean curve decomposition (GMCD) and mutual information-based voxel selection framework. Previously, the fMRI signal analysis has been conducted using empirical mean curve decomposition (EMCD) model and voxel selection on raw fMRI signal. The erstwhile methodology loses frequency component, while the latter methodology suffers from signal redundancy. Both challenges are addressed by our methodology in which the frequency component is considered by decomposing the raw fMRI signal using geometric mean rather than arithmetic mean and the voxels are selected from EMCD signal using GMCD components, rather than raw fMRI signal. The proposed methodologies are adopted for predicting the neural response. Experimentations are conducted in the openly available fMRI data of six subjects, and comparisons are made with existing decomposition models and voxel selection frameworks. Subsequently, the effect of degree of selected voxels and the selection constraints are analyzed. The comparative results and the analysis demonstrate the superiority and the reliability of the proposed methodology.

Electroencephalogram-based decoding cognitive states using convolutional neural network and likelihood ratio based score fusion

Electroencephalogram (EEG)-based decoding human brain activity is challenging, owing to the low spatial resolution of EEG. However, EEG is an important technique, especially for brain-computer interface applications. In this study, a novel algorithm is proposed to decode brain activity associated with different types of images. In this hybrid algorithm, convolutional neural network is modified for the extraction of features, a t-test is used for the selection of significant features and likelihood ratio-based score fusion is used for the prediction of brain activity. The proposed algorithm takes input data from multichannel EEG time-series, which is also known as multivariate pattern analysis. Comprehensive analysis was conducted using data from 30 participants. The results from the proposed method are compared with current recognized feature extraction and classification/prediction techniques. The wavelet transform-support vector machine method is the most popular currently used feature extraction and prediction method. This method showed an accuracy of 65.7%. However, the proposed method predicts the novel data with improved accuracy of 79.9%. In conclusion, the proposed algorithm outperformed the current feature extraction and prediction method.

Exploring stability-based voxel selection methods in MVPA using cognitive neuroimaging data: a comprehensive study

Feature selection plays a key role in multi-voxel pattern analysis because functional magnetic resonance imaging data are typically noisy, sparse, and high-dimensional. Although the conventional evaluation criterion is the classification accuracy, selecting a stable feature set that is not sensitive to the variance in dataset may provide more scientific insights. In this study, we aim to investigate the stability of feature selection methods and test the stability-based feature selection scheme on two benchmark datasets. Top-k feature selection with a ranking score of mutual information and correlation, recursive feature elimination integrated with support vector machine, and L1 and L2-norm regularizations were adapted to a bootstrapped stability selection framework, and the selected algorithms were compared based on both accuracy and stability scores. The results indicate that regularization-based methods are generally more stable in StarPlus dataset, but in Haxby dataset they failed to perform as well as others.

Brain response pattern identification of fMRI data using a particle swarm optimization-based approach

Many neuroscience studies have been devoted to understand brain neural responses correlating to cognition using functional magnetic resonance imaging (fMRI). In contrast to univariate analysis to identify response patterns, it is shown that multi-voxel pattern analysis (MVPA) of fMRI data becomes a relatively effective approach using machine learning techniques in the recent literature. MVPA can be considered as a multi-objective pattern classification problem with the aim to optimize response patterns, in which informative voxels interacting with each other are selected, achieving high classification accuracy associated with cognitive stimulus conditions. To solve the problem, we propose a feature interaction detection framework, integrating hierarchical heterogeneous particle swarm optimization and support vector machines, for voxel selection in MVPA. In the proposed approach, we first select the most informative voxels and then identify a response pattern based on the connectivity of the selected voxels. The effectiveness of the proposed approach was examined for the Haxby’s dataset of object-level representations. The computational results demonstrated higher classification accuracy by the extracted response patterns, compared to state-of-the-art feature selection algorithms, such as forward selection and backward selection.

Feature selection of fMRI data based on normalized mutual information and fisher discriminant ratio

Pattern classification has been increasingly used in functional magnetic resonance imaging (fMRI) data analysis. However, the classification performance is restricted by the high dimensional property and noises of the fMRI data. In this paper, a new feature selection method (named as "NMI-F") was proposed by sequentially combining the normalized mutual information (NMI) and fisher discriminant ratio. In NMI-F, the normalized mutual information was firstly used to evaluate the relationships between features, and fisher discriminant ratio was then applied to calculate the importance of each feature involved. Two fMRI datasets (task-related and resting state) were used to test the proposed method. It was found that classification base on the NMI-F method could differentiate the brain cognitive and disease states effectively, and the proposed NMI-F method was prior to the other related methods. The current results also have implications to the future studies.

Ensembling brain regions for brain decoding

In this study, we propose a new method which ensembles the brain regions for brain decoding. The ensemble is generated by clustering the fMRI images recorded during an experimental set-up which measures the cognitive states associated to semantic categories. Initially, voxel clusters are formed by using hierarchical agglomerative clustering with correlation as the similarity metric. Then, for each voxel cluster, a support vector machine (SVM) classifier is trained to estimate the class-posteriori probabilities. Lastly, the class-posteriori probabilities are ensembled by concatenating them under the same feature space, which are then used to train a meta-layer SVM for the final classification of the cognitive states. By using the voxel clusters, we aim to utilize the distributed, but complementing nature of the semantic representations in the brain and improve the classification accuracy. Thus, we make an existential claim that the brain regions provide a natural basis for ensemble learning which should be superior to the random clusters formed over a selected set of voxels. Our approach yields to better classification accuracies in Mitchell dataset on most of the subjects, when compared to state-of-the-art which emphasizes voxel selection and ensemble learning with random subspaces.