Brain Decoding Using fMRI Images for Multiple Subjects through Deep Learning.

Substantial information related to human cerebral conditions can be decoded through various noninvasive evaluating techniques like fMRI. Exploration of the neuronal activity of the human brain can divulge the thoughts of a person like what the subject is perceiving, thinking, or visualizing. Furthermore, deep learning techniques can be used to decode the multifaceted patterns of the brain in response to external stimuli. Existing techniques are capable of exploring and classifying the thoughts of the human subject acquired by the fMRI imaging data. fMRI images are the volumetric imaging scans which are highly dimensional as well as require a lot of time for training when fed as an input in the deep learning network. However, the hassle for more efficient learning of highly dimensional high-level features in less training time and accurate interpretation of the brain voxels with less misclassification error is needed. In this research, we propose an improved CNN technique where features will be functionally aligned. The optimal features will be selected after dimensionality reduction. The highly dimensional feature vector will be transformed into low dimensional space for dimensionality reduction through autoadjusted weights and combination of best activation functions. Furthermore, we solve the problem of increased training time by using Swish activation function, making it denser and increasing efficiency of the model in less training time. Finally, the experimental results are evaluated and compared with other classifiers which demonstrated the supremacy of the proposed model in terms of accuracy.

Functional Magnetic Resonance Imaging Study of Electroacupuncture Stimulating Uterine Acupoints.

OBJECTIVE: Based on resting-state functional magnetic resonance imaging (rs-fMRI), to observe the changes of brain function of bilateral uterine points stimulated by electroacupuncture, so as to provide imaging basis for acupuncture in the treatment of gynecological and reproductive diseases. METHODS: 20 healthy female subjects were selected to stimulate bilateral uterine points (EX-CA1) by electroacupuncture. FMRI data before and after acupuncture were collected. The ReHo values before and after acupuncture were compared by using the analysis method of regional homogeneity (ReHo) of the whole brain, so as to explore the regulatory effect of acupuncture intervention on brain functional activities of healthy subjects. RESULTS: Compared with before acupuncture, the ReHo values of the left precuneus lobe, left central posterior gyrus, calcarine, left lingual gyrus, and cerebellum decreased significantly after acupuncture. CONCLUSION: Electroacupuncture at bilateral uterine points can induce functional activities in brain areas such as the precuneus, cerebellum, posterior central gyrus, talform sulcus, and lingual gyrus. The neural activities in these brain areas may be related to reproductive hormone level, emotional changes, somatic sensation, and visual information. It can clarify the neural mechanism of acupuncture at uterine points in the treatment of reproductive and gynecological diseases to a certain extent.

Application of Magnetic Resonance Imaging of Patients with Concussion in Clinical Emergency.

Concussion syndrome is a common disease in neurosurgery, and its incidence ranks first among all traumatic brain injuries. Cognitive dysfunction is one of the most common functional impairments in concussion syndrome. Neuroimaging and content assessments on concussion patients and healthy control subjects are used in this study, which uses MRI technology to evaluate brain pictures of concussion patients. Moreover, this paper separately evaluates the scores of the concussion syndrome group and the healthy control group in multiple functional aspects and performs independent sample t-test after statistics of the two scores. In addition, this paper uses resting-state fMRI to study the changes in the functional connectivity of the medial prefrontal lobe in patients with PCS, which has certain significance in revealing cognitive dysfunction after concussion and has a certain effect on improving the clinical emergency diagnosis and treatment of concussion.

Complexity Assessment of Chronic Pain in Elderly Knee Osteoarthritis Based on Neuroimaging Recognition Techniques.

The chronic pain of knee osteoarthritis in the elderly is investigated in detail in this paper, as well as the complexity of chronic pain utilising neuroimaging recognition techniques. Chronic pain in knee osteoarthritis (KOA) has a major effect on patients' quality of life and functional activities; therefore, understanding the causes of KOA pain and the analgesic advantages of different therapies is important. In recent years, neuroimaging techniques have become increasingly important in basic and clinical pain research. Thanks to the application and development of neuroimaging techniques in the study of chronic pain in KOA, researchers have found that chronic pain in KOA contains both injury-receptive and neuropathic pain components. The neuropathic pain mechanism that causes KOA pain is complicated, and it may be produced by peripheral or central sensitization, but it has not gotten enough attention in clinical practice, and there is no agreement on how to treat combination neuropathic pain KOA. As a result, using neuroimaging techniques such as magnetic resonance imaging (MRI), electroencephalography (EEG), magnetoencephalography (MEG), and near-infrared spectroscopy (NIRS), this review examines the changes in brain pathophysiology-related regions caused by KOA pain, compares the latest results in pain assessment and prediction, and clarifies the central brain analgesic mechanistic. The capsule network model is introduced in this paper from the perspective of deep learning network structure to construct an information-complete and reversible image low-level feature bridge using isotropic representation, predict the corresponding capsule features from MRI voxel responses, and then, complete the accurate reconstruction of simple images using inverse transformation. The proposed model improves the structural similarity index by about 10%, improves the reconstruction performance of low-level feature content in simple images by about 10%, and achieves feature interpretation and analysis of low-level visual cortical fMRI voxels by visualising capsule features, according to the experimental results.

Diagnostic Classification of Patients with Dilated Cardiomyopathy Using Ventricular Strain Analysis Algorithm.

Dilated cardiomyopathy (DCM) is a cardiomyopathy with left ventricle or double ventricle enlargement and systolic dysfunction. It is an important cause of sudden cardiac death and heart failure and is the leading indication for cardiac transplantation. Major heart diseases like heart muscle damage and valvular problems are diagnosed using cardiac MRI. However, it takes time for cardiologists to measure DCM-related parameters to decide whether patients have this disease. We have presented a method for automatic ventricular segmentation, parameter extraction, and diagnosing DCM. In this paper, left ventricle and right ventricle are segmented by parasternal short-axis cardiac MR image sequence; then, related parameters are extracted in the end-diastole and end-systole of the heart. Machine learning classifiers use extracted parameters as input to predict normal people and patients with DCM, among which Random forest classifier gives the highest accuracy. The results show that the proposed system can be effectively utilized to detect and diagnose DCM automatically. The experimental results suggest the capabilities and advantages of the proposed method to diagnose DCM. A small amount of sample input can generate results comparable to more complex methods.

Diagnosis of Schizophrenia Based on Deep Learning Using fMRI.

Schizophrenia is a brain disease that frequently occurs in young people. Early diagnosis and treatment can reduce family burdens and reduce social costs. There is no objective evaluation index for schizophrenia. In order to improve the classification effect of traditional classification methods on magnetic resonance data, a method of classification of functional magnetic resonance imaging data is proposed in conjunction with the convolutional neural network algorithm. We take functional magnetic resonance imaging (fMRI) data for schizophrenia as an example, to extract effective time series from preprocessed fMRI data, and perform correlation analysis on regions of interest, using transfer learning and VGG16 net, and the functional connection between schizophrenia and healthy controls is classified. Experimental results show that the classification accuracy of fMRI based on VGG16 is up to 84.3%. On the one hand, it can improve the early diagnosis of schizophrenia, and on the other hand, it can solve the classification problem of small samples and high-dimensional data and effectively improve the generalization ability of deep learning models.

Dynamic Electrode-to-Image (DETI) mapping reveals the human brain's spatiotemporal code of visual information.

A number of neuroimaging techniques have been employed to understand how visual information is transformed along the visual pathway. Although each technique has spatial and temporal limitations, they can each provide important insights into the visual code. While the BOLD signal of fMRI can be quite informative, the visual code is not static and this can be obscured by fMRI's poor temporal resolution. In this study, we leveraged the high temporal resolution of EEG to develop an encoding technique based on the distribution of responses generated by a population of real-world scenes. This approach maps neural signals to each pixel within a given image and reveals location-specific transformations of the visual code, providing a spatiotemporal signature for the image at each electrode. Our analyses of the mapping results revealed that scenes undergo a series of nonuniform transformations that prioritize different spatial frequencies at different regions of scenes over time. This mapping technique offers a potential avenue for future studies to explore how dynamic feedforward and recurrent processes inform and refine high-level representations of our visual world.

Topology-preserving smoothing of retinotopic maps.

Retinotopic mapping, i.e., the mapping between visual inputs on the retina and neuronal activations in cortical visual areas, is one of the central topics in visual neuroscience. For human observers, the mapping is obtained by analyzing functional magnetic resonance imaging (fMRI) signals of cortical responses to slowly moving visual stimuli on the retina. Although it is well known from neurophysiology that the mapping is topological (i.e., the topology of neighborhood connectivity is preserved) within each visual area, retinotopic maps derived from the state-of-the-art methods are often not topological because of the low signal-to-noise ratio and spatial resolution of fMRI. The violation of topological condition is most severe in cortical regions corresponding to the neighborhood of the fovea (e.g., < 1 degree eccentricity in the Human Connectome Project (HCP) dataset), significantly impeding accurate analysis of retinotopic maps. This study aims to directly model the topological condition and generate topology-preserving and smooth retinotopic maps. Specifically, we adopted the Beltrami coefficient, a metric of quasiconformal mapping, to define the topological condition, developed a mathematical model to quantify topological smoothing as a constrained optimization problem, and elaborated an efficient numerical method to solve the problem. The method was then applied to V1, V2, and V3 simultaneously in the HCP dataset. Experiments with both simulated and real retinotopy data demonstrated that the proposed method could generate topological and smooth retinotopic maps.

Behavioral correlates of cortical semantic representations modeled by word vectors.

The quantitative modeling of semantic representations in the brain plays a key role in understanding the neural basis of semantic processing. Previous studies have demonstrated that word vectors, which were originally developed for use in the field of natural language processing, provide a powerful tool for such quantitative modeling. However, whether semantic representations in the brain revealed by the word vector-based models actually capture our perception of semantic information remains unclear, as there has been no study explicitly examining the behavioral correlates of the modeled brain semantic representations. To address this issue, we compared the semantic structure of nouns and adjectives in the brain estimated from word vector-based brain models with that evaluated from human behavior. The brain models were constructed using voxelwise modeling to predict the functional magnetic resonance imaging (fMRI) response to natural movies from semantic contents in each movie scene through a word vector space. The semantic dissimilarity of brain word representations was then evaluated using the brain models. Meanwhile, data on human behavior reflecting the perception of semantic dissimilarity between words were collected in psychological experiments. We found a significant correlation between brain model- and behavior-derived semantic dissimilarities of words. This finding suggests that semantic representations in the brain modeled via word vectors appropriately capture our perception of word meanings.

Diagnosis of Alzheimer's Disease Severity with fMRI Images Using Robust Multitask Feature Extraction Method and Convolutional Neural Network (CNN).

The automatic diagnosis of Alzheimer's disease plays an important role in human health, especially in its early stage. Because it is a neurodegenerative condition, Alzheimer's disease seems to have a long incubation period. Therefore, it is essential to analyze Alzheimer's symptoms at different stages. In this paper, the classification is done with several methods of machine learning consisting of K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), linear discrimination analysis (LDA), and random forest (RF). Moreover, novel convolutional neural network (CNN) architecture is presented to diagnose Alzheimer's severity. The relationship between Alzheimer's patients' functional magnetic resonance imaging (fMRI) images and their scores on the MMSE is investigated to achieve the aim. The feature extraction is performed based on the robust multitask feature learning algorithm. The severity is also calculated based on the Mini-Mental State Examination score, including low, mild, moderate, and severe categories. Results show that the accuracy of the KNN, SVM, DT, LDA, RF, and presented CNN method is 77.5%, 85.8%, 91.7%, 79.5%, 85.1%, and 96.7%, respectively. Moreover, for the presented CNN architecture, the sensitivity of low, mild, moderate, and severe status of Alzheimer patients is 98.1%, 95.2%,89.0%, and 87.5%, respectively. Based on the findings, the presented CNN architecture classifier outperforms other methods and can diagnose the severity and stages of Alzheimer's disease with maximum accuracy.

Extracting representations of cognition across neuroimaging studies improves brain decoding.

Cognitive brain imaging is accumulating datasets about the neural substrate of many different mental processes. Yet, most studies are based on few subjects and have low statistical power. Analyzing data across studies could bring more statistical power; yet the current brain-imaging analytic framework cannot be used at scale as it requires casting all cognitive tasks in a unified theoretical framework. We introduce a new methodology to analyze brain responses across tasks without a joint model of the psychological processes. The method boosts statistical power in small studies with specific cognitive focus by analyzing them jointly with large studies that probe less focal mental processes. Our approach improves decoding performance for 80% of 35 widely-different functional-imaging studies. It finds commonalities across tasks in a data-driven way, via common brain representations that predict mental processes. These are brain networks tuned to psychological manipulations. They outline interpretable and plausible brain structures. The extracted networks have been made available; they can be readily reused in new neuro-imaging studies. We provide a multi-study decoding tool to adapt to new data.

A neuroimaging biomarker for sustained experimental and clinical pain.

Sustained pain is a major characteristic of clinical pain disorders, but it is difficult to assess in isolation from co-occurring cognitive and emotional features in patients. In this study, we developed a functional magnetic resonance imaging signature based on whole-brain functional connectivity that tracks experimentally induced tonic pain intensity and tested its sensitivity, specificity and generalizability to clinical pain across six studies (total n = 334). The signature displayed high sensitivity and specificity to tonic pain across three independent studies of orofacial tonic pain and aversive taste. It also predicted clinical pain severity and classified patients versus controls in two independent studies of clinical low back pain. Tonic and clinical pain showed similar network-level representations, particularly in somatomotor, frontoparietal and dorsal attention networks. These patterns were distinct from representations of experimental phasic pain. This study identified a brain biomarker for sustained pain with high potential for clinical translation.

Alzheimer's Disease Classification Based on Image Transformation and Features Fusion.

It has become an inevitable trend for medical personnel to analyze and diagnose Alzheimer's disease (AD) in different stages by combining functional magnetic resonance imaging (fMRI) and artificial intelligence technologies such as deep learning in the future. In this paper, a classification method was proposed for AD based on two different transformation images of fMRI and improved the 3DPCANet model and canonical correlation analysis (CCA). The main ideas include that, firstly, fMRI images were preprocessed, and subsequently, mean regional homogeneity (mReHo) and mean amplitude of low-frequency amplitude (mALFF) transformation were performed for the preprocessed images. Then, mReHo and mALFF images were extracted features using the improved 3DPCANet, and these two kinds of the extracted features were fused by CCA. Finally, the support vector machine (SVM) was used to classify AD patients with different stages. Experimental results showed that the proposed approach was robust and effective. Classification accuracy for significant memory concern (SMC) vs. mild cognitive impairment (MCI), normal control (NC) vs. AD, and NC vs. SMC, respectively, reached 95.00%, 92.00%, and 91.30%, which adequately proved the feasibility and effectiveness of the proposed method.

Key relationships between non-invasive functional neuroimaging and the underlying neuronal activity.

Functional neuroimaging using MRI relies on measurements of blood oxygen level-dependent (BOLD) signals from which inferences are made about the underlying neuronal activity. This is possible because neuronal activity elicits increases in blood flow via neurovascular coupling, which gives rise to the BOLD signal. Hence, an accurate interpretation of what BOLD signals mean in terms of neural activity depends on a full understanding of the mechanisms that underlie the measured signal, including neurovascular and neurometabolic coupling, the contribution of different cell types to local signalling, and regional differences in these mechanisms. Furthermore, the contributions of systemic functions to cerebral blood flow may vary with ageing, disease and arousal states, with regard to both neuronal and vascular function. In addition, recent developments in non-invasive imaging technology, such as high-field fMRI, and comparative inter-species analysis, allow connections between non-invasive data and mechanistic knowledge gained from invasive cellular-level studies. Considered together, these factors have immense potential to improve BOLD signal interpretation and bring us closer to the ultimate purpose of decoding the mechanisms of human cognition. This theme issue covers a range of recent advances in these topics, providing a multidisciplinary scientific and technical framework for future work in the neurovascular and cognitive sciences. This article is part of the theme issue 'Key relationships between non-invasive functional neuroimaging and the underlying neuronal activity'.

Time-dependent spatial specificity of high-resolution fMRI: insights into mesoscopic neurovascular coupling.

High-resolution functional magnetic resonance imaging (fMRI) is becoming increasingly popular because of the growing availability of ultra-high magnetic fields which are capable of improving sensitivity and spatial resolution. However, it is debatable whether increased spatial resolutions for haemodynamic-based techniques, like fMRI, can accurately detect the true location of neuronal activity. We have addressed this issue in functional columns and layers of animals with haemoglobin-based optical imaging and different fMRI contrasts, such as blood oxygenation level-dependent, cerebral blood flow and cerebral blood volume fMRI. In this review, we describe empirical evidence primarily from our own studies on how well these fMRI signals are spatially specific to the neuronally active site and discuss insights into neurovascular coupling at the mesoscale. This article is part of the theme issue 'Key relationships between non-invasive functional neuroimaging and the underlying neuronal activity'.

Broad Learning Enhanced 1H-MRS for Early Diagnosis of Neuropsychiatric Systemic Lupus Erythematosus.

In this paper, we explore the potential of using the multivoxel proton magnetic resonance spectroscopy (1H-MRS) to diagnose neuropsychiatric systemic lupus erythematosus (NPSLE) with the assistance of a support vector machine broad learning system (BL-SVM). We retrospectively analysed 23 confirmed patients and 16 healthy controls, who underwent a 3.0 T magnetic resonance imaging (MRI) sequence with multivoxel 1H-MRS in our hospitals. One hundred and seventeen metabolic features were extracted from the multivoxel 1H-MRS image. Thirty-three metabolic features selected by the Mann-Whitney U test were considered to have a statistically significant difference (p < 0.05). However, the best accuracy achieved by conventional statistical methods using these 33 metabolic features was only 77%. We turned to develop a support vector machine broad learning system (BL-SVM) to quantitatively analyse the metabolic features from 1H-MRS. Although not all the individual features manifested statistics significantly, the BL-SVM could still learn to distinguish the NPSLE from the healthy controls. The area under the receiver operating characteristic curve (AUC), the sensitivity, and the specificity of our BL-SVM in predicting NPSLE were 95%, 95.8%, and 93%, respectively, by 3-fold cross-validation. We consequently conclude that the proposed system effectively and efficiently working on limited and noisy samples may brighten a noinvasive in vivo instrument for early diagnosis of NPSLE.

Multimodal principal component analysis to identify major features of white matter structure and links to reading.

The role of white matter in reading has been established by diffusion tensor imaging (DTI), but DTI cannot identify specific microstructural features driving these relationships. Neurite orientation dispersion and density imaging (NODDI), inhomogeneous magnetization transfer (ihMT) and multicomponent driven equilibrium single-pulse observation of T1/T2 (mcDESPOT) can be used to link more specific aspects of white matter microstructure and reading due to their sensitivity to axonal packing and fiber coherence (NODDI) and myelin (ihMT and mcDESPOT). We applied principal component analysis (PCA) to combine DTI, NODDI, ihMT and mcDESPOT measures (10 in total), identify major features of white matter structure, and link these features to both reading and age. Analysis was performed for nine reading-related tracts in 46 neurotypical 6-16 year olds. We identified three principal components (PCs) which explained 79.5% of variance in our dataset. PC1 probed tissue complexity, PC2 described myelin and axonal packing, while PC3 was related to axonal diameter. Mixed effects regression models did not identify any significant relationships between principal components and reading skill. Bayes factor analysis revealed that the absence of relationships was not due to low power. Increasing PC1 in the left arcuate fasciculus with age suggest increases in tissue complexity, while increases of PC2 in the bilateral arcuate, inferior longitudinal, inferior fronto-occipital fasciculi, and splenium suggest increases in myelin and axonal packing with age. Multimodal white matter imaging and PCA provide microstructurally informative, powerful principal components which can be used by future studies of development and cognition. Our findings suggest major features of white matter undergo development during childhood and adolescence, but changes are not linked to reading during this period in our typically-developing sample.

A Comparative Analysis of Visual Encoding Models Based on Classification and Segmentation Task-Driven CNNs.

Nowadays, visual encoding models use convolution neural networks (CNNs) with outstanding performance in computer vision to simulate the process of human information processing. However, the prediction performances of encoding models will have differences based on different networks driven by different tasks. Here, the impact of network tasks on encoding models is studied. Using functional magnetic resonance imaging (fMRI) data, the features of natural visual stimulation are extracted using a segmentation network (FCN32s) and a classification network (VGG16) with different visual tasks but similar network structure. Then, using three sets of features, i.e., segmentation, classification, and fused features, the regularized orthogonal matching pursuit (ROMP) method is used to establish the linear mapping from features to voxel responses. The analysis results indicate that encoding models based on networks performing different tasks can effectively but differently predict stimulus-induced responses measured by fMRI. The prediction accuracy of the encoding model based on VGG is found to be significantly better than that of the model based on FCN in most voxels but similar to that of fused features. The comparative analysis demonstrates that the CNN performing the classification task is more similar to human visual processing than that performing the segmentation task.

Sample size evolution in neuroimaging research: An evaluation of highly-cited studies (1990-2012) and of latest practices (2017-2018) in high-impact journals.

We evaluated 1038 of the most cited structural and functional (fMRI) magnetic resonance brain imaging papers (1161 studies) published during 1990-2012 and 270 papers (300 studies) published in top neuroimaging journals in 2017 and 2018. 96% of highly cited experimental fMRI studies had a single group of participants and these studies had median sample size of 12, highly cited clinical fMRI studies (with patient participants) had median sample size of 14.5, and clinical structural MRI studies had median sample size of 50. The sample size of highly cited experimental fMRI studies increased at a rate of 0.74 participant/year and this rate of increase was commensurate with the median sample sizes of neuroimaging studies published in top neuroimaging journals in 2017 (23 participants) and 2018 (24 participants). Only 4 of 131 papers in 2017 and 5 of 142 papers in 2018 had pre-study power calculations, most for single t-tests and correlations. Only 14% of highly cited papers reported the number of excluded participants whereas 49% of papers with their own data in 2017 and 2018 reported excluded participants. Publishers and funders should require pre-study power calculations necessitating the specification of effect sizes. The field should agree on universally required reporting standards. Reporting formats should be standardized so that crucial study parameters could be identified unequivocally.

Interpretable Learning Approaches in Resting-State Functional Connectivity Analysis: The Case of Autism Spectrum Disorder.

Deep neural networks have recently been applied to the study of brain disorders such as autism spectrum disorder (ASD) with great success. However, the internal logics of these networks are difficult to interpret, especially with regard to how specific network architecture decisions are made. In this paper, we study an interpretable neural network model as a method to identify ASD participants from functional magnetic resonance imaging (fMRI) data and interpret results of the model in a precise and consistent manner. First, we propose an interpretable fully connected neural network (FCNN) to classify two groups, ASD versus healthy controls (HC), based on input data from resting-state functional connectivity (rsFC) between regions of interests (ROIs). The proposed FCNN model is a piecewise linear neural network (PLNN) which uses piecewise linear function LeakyReLU as its activation function. We experimentally compared the FCNN model against widely used classification models including support vector machine (SVM), random forest, and two new classes of deep neural network models in a large dataset containing 871 subjects from ABIDE I database. The results show the proposed FCNN model achieves the highest classification accuracy. Second, we further propose an interpreting method which could explain the trained model precisely with a precise linear formula for each input sample and decision features which contributed most to the classification of ASD versus HC participants in the model. We also discuss the implications of our proposed approach for fMRI data classification and interpretation.