Search

Federated learning has shown its unique advantages in many different tasks, including brain image analysis. It provides a new way to train deep learning models while protecting the privacy of medical image data from multiple sites. However, previous studies suggest that domain shift across different sites may influence the performance of federated models. As a solution, we propose a gradient matching federated domain adaptation (GM-FedDA) method for brain image classification, aiming to reduce domain discrepancy with the assistance of a public image dataset and train robust local federated models for target sites. It mainly includes two stages: 1) pretraining stage; we propose a one-common-source adversarial domain adaptation (OCS-ADA) strategy, i.e., adopting ADA with gradient matching loss to pretrain encoders for reducing domain shift at each target site (private data) with the assistance of a common source domain (public data) and 2) fine-tuning stage; we develop a gradient matching federated (GM-Fed) fine-tuning method for updating local federated models pretrained with the OCS-ADA strategy, i.e., pushing the optimization direction of a local federated model toward its specific local minimum by minimizing gradient matching loss between sites. Using fully connected networks as local models, we validate our method with the diagnostic classification tasks of schizophrenia and major depressive disorder based on multisite resting-state functional MRI (fMRI), respectively. Results show that the proposed GM-FedDA method outperforms other commonly used methods, suggesting the potential of our method in brain imaging analysis and other fields, which need to utilize multisite data while preserving data privacy.

Optimization-based visual-inertial simultaneous localization and mapping system (VI-SLAM) focuses on the establishment of the loss function using both inertial and visual constraints. Preintegration theory is commonly used to express inertial constraints, but it lacks the merging equation between keyframes, challenging VI-SLAM from culling and merging redundant keyframes. To address this, we establish an on-manifold preintegration merging theory, including the merging of preintegrated terms, noise covariance, and Jacobians for bias updating, which significantly improves the preintegration theory and provides theoretical support for the keyframe management function of VI-SLAM. Visual constraints are typically expressed using multiple view geometry with 3-D points optimized as scene structure parameters. However, the excessive dimensionality of the optimization parameters generated by 3-D points can lead to computational bottlenecks. Through the recent pose-only imaging geometry representation, we construct a lightweight optimization algorithm for SLAM that avoids the dimensional explosion in bundle adjustment. Based on the above, we propose a 3-D points-free SLAM optimizer. The proposed algorithms are validated on simulation, public datasets, and real-world experiments, and compared against advanced open-source systems, such as ORB-SLAM3 and VINS.

Early screening is essential for effective intervention and treatment of individuals with mental disorders. Functional magnetic resonance imaging (fMRI) is a noninvasive tool for depicting neural activity and has demonstrated strong potential as a technique for identifying mental disorders. Due to the difficulty in data collection and diagnosis, imaging data from patients are rare at a single site, whereas abundant healthy control data are available from public datasets. However, joint use of these data from multiple sites for classification model training is hindered by cross-domain distribution discrepancy and diverse label spaces. Herein, we propose few-shot domain-adaptive anomaly detection (FAAD) to achieve cross-site anomaly detection of brain images based on only a few labeled samples. We introduce domain adaptation to mitigate cross-domain distribution discrepancy and jointly align the general and conditional feature distributions of imaging data across multiple sites. We utilize fMRI data of healthy subjects in the Human Connectome Project (HCP) as the source domain and fMRI images from six independent sites, including patients with mental disorders and demographically matched healthy controls, as target domains. Experiments showed the superiority of the proposed method compared with binary classification, traditional anomaly detection methods, and several recognized domain adaptation methods.

Deep learning methods based on convolution neural networks (CNNs) have achieved good classification performance in decoding electroencephalography (EEG). In this article, a novel framework combining-gating mechanism and dilated CNN (GDCNN) is proposed for decoding EEG signals evoked by four different driving intentions. GDCNN provides different receptive fields and controls the information flow between convolution layers, which help to detect different sizes of information in EEG signals. The proposed method reaches accuracies of 93.17% and 73.33% for the subject-dependent and subject-independent experiments, outperforming several benchmark methods. The data augmentation that randomly concatenates multitrial EEG sequences is adopted to promote generalization of decoding model. This strategy effectively prevents overfitting and improves the decoding accuracies of EEGNet, DeepConvNet, and GDCNN by 4.3%, 4.75%, and 3.92%, respectively. These results indicate GDCNN is beneficial for decoding EEG and it has application potential in the brain–computer interface (BCI) systems based on video stimuli.

Brain biometrics, due to its unique confidentiality and concealment, has received the increasing attention of scientific researchers in recent years. It has shown that steady-state visual evoked potential (SSVEP) signals with a high signal-to-noise ratio and stable spectrum can be used as identification features. However, current studies rely on the extraction of features characterizing the activity of single brain regions, ignoring the functional coupling between different brain regions. In this study, we proposed a novel approach that considers the functional connectivity of SSVEP signals collected by different electrodes as practical biometric features. We investigated individual coherence (COH) connectivity and phase synchronization according to different visual stimulations in terms of frequency component analysis of different principal bands. Fifteen subjects were identified by the support vector machine, random forest, and $k$ -nearest neighbor algorithm. The results show that distinctive features in SSVEP functional networks among individuals can achieve high precision identification (up to 98%). The obtained identification performance shows that SSVEP spectral COH and phase synchronization have the potential for biometric applications.

Previous studies have explored the use of deep neural networks for electroencephalography (EEG)-based motor imagery (MI) recognition, but most of the models focus on the recognition performance achieved for a single subject and are challenging to transfer due to individual differences and low signal-to-noise-ratio of EEG signals. To date, few studies have paid attention to the balance between generalizability and personalization across subjects. To this end, we propose a co-teaching graph learning method for cross-subject EEG-based MI recognition. First, A novel graph learning approach is designed to improve feature extraction from a typical graph structure containing raw EEG signals. Second, two graph learning models are constructed to filter noisy data by using a co-teaching training strategy, preventing overfitting on noisy samples obtained from different subjects. The proposed model shows a 5.4% and 3.2% increase in accuracy of single- and multisubject four-class MI recognition tasks compared to the previous best method, respectively. Experimental results also demonstrate that it is easy to derive a model that can represent generic knowledge of multiple MI subjects and can be fine-tuned efficiently for new subjects.

Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from most existing works dedicated to adaptive refinement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range (depth) finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth. This sequential modeling, conducted based on transformer features, essentially learns the epipolar line search in traditional multi-view stereo. We devise a multi-task learning for better optimization convergence and depth accuracy. We found the monotonicity property of the SDFs along each ray greatly benefits the depth estimation. Our method ranks top on both the DTU and the Tanks & Temples datasets over all previous learning-based methods, achieving an overall reconstruction score of 0.33 mm on DTU and an F-score of 59.48% on Tanks & Temples. It is able to produce high-quality depth estimation and point cloud reconstruction in challenging scenarios such as objects/scenes with non-textured surface, severe occlusion, and highly varying depth range. Further, we propose RayMVSNet++ to enhance contextual feature aggregation for each ray through designing an attentional gating unit to select semantically relevant neighboring rays within the local frustum around that ray. This improves the performance on datasets with more challenging examples (e.g., low-quality images caused by poor lighting conditions or motion blur). RayMVSNet++ achieves state-of-the-art performance on the ScanNet dataset. In particular, it attains an AbsRel of 0.058m and produces accurate results on the two subsets of textureless regions and large depth variation.

Previous studies have made great efforts to expand the instruction set in steady-state visual evoked potential (SSVEP)-based brain-computer interfaces. However, most systems are limited to single persons and expand the instruction set by increasing the flicker stimulation frequency range or via multiple frequencies sequential coding or joint frequency/phase coding. In this article, we propose a multibrain coding SSVEP paradigm that encodes the SSVEP instructions generated by N independent subjects with M flicker stimuli, thus increasing the instruction set to MN instructions. A total of 40 subjects participated in online experiments in this article. The results show that there is no significant difference in accuracy (p > 0.05, paired t test) between the multibrain and single-brain coding systems, while the information transfer rate (ITR) increases significantly (p < 0.0001, paired t test), with the ITR increasing from 37.66 ± 3.60 bits/min for the single-brain coding system to 111.65 ± 10.84 bits/min for multibrain coding system when N = 3 and M = 5. In summary, the proposed multibrain coding paradigm exponentially increases the number of instructions without increasing the output instruction time, which is of great significance to the application and promotion of BCIs.

Insufficient annotated data and minor lung lesions pose big challenges for computed tomography (CT)-aided automatic COVID-19 diagnosis at an early outbreak stage. To address this issue, we propose a Semi-Supervised Tri-Branch Network (SS-TBN). First, we develop a joint TBN model for dual-task application scenarios of image segmentation and classification such as CT-based COVID-19 diagnosis, in which pixel-level lesion segmentation and slice-level infection classification branches are simultaneously trained via lesion attention, and individual-level diagnosis branch aggregates slice-level outputs for COVID-19 screening. Second, we propose a novel hybrid semi-supervised learning method to make full use of unlabeled data, combining a new double-threshold pseudo labeling method specifically designed to the joint model and a new inter-slice consistency regularization method specifically tailored to CT images. Besides two publicly available external datasets, we collect internal and our own external datasets including 210,395 images (1,420 cases versus 498 controls) from ten hospitals. Experimental results show that the proposed method achieves state-of-the-art performance in COVID-19 classification with limited annotated data even if lesions are subtle, and that segmentation results promote interpretability for diagnosis, suggesting the potential of the SS-TBN in early screening in insufficient labeled data situations at the early stage of a pandemic outbreak like COVID-19.

In many dynamic environment applications, with the evolution of data collection ways, the data attributes are incremental and the samples are stored with accumulated feature spaces gradually. For instance, in the neuroimaging-based diagnosis of neuropsychiatric disorders, with emerging of diverse testing ways, we get more brain image features over time. The accumulation of different types of features will unavoidably bring difficulties in manipulating the high-dimensional data. It is challenging to design an algorithm to select valuable features in this feature incremental scenario. To address this important but rarely studied problem, we propose a novel Adaptive Feature Selection method (AFS). It enables the reusability of the feature selection model trained on previous features and adapts it to fit the feature selection requirements on all features automatically. Besides, an ideal $\ell _{0}$ℓ0-norm sparse constraint for feature selection is imposed with a proposed effective solving strategy. We present the theoretical analyses about the generalization bound and convergence behavior. After tackling this problem in a one-shot case, we extend it to the multi-shot scenario. Plenty of experimental results demonstrate the effectiveness of reusing previous features and the superior of $\ell _{0}$ℓ0-norm constraint in various aspects, together with its effectiveness in discriminating schizophrenic patients from healthy controls.

Cognitive load prediction is one of the most important issues in the nascent field of neuroergonomics, and it has significant value in real-world applications. Most of the previous studies of cognitive load prediction only utilized electroencephalography (EEG)-based spectral signatures or interchannel connectivity, ignoring abundant temporal microstate features, which may represent the transient topologies of EEG signals. Furthermore, previous studies have mostly focused on the binary-level classification of cognitive load for single-type cognitive tasks. To date, there are few studies on the multilevel prediction of cognitive load during mixed cognitive tasks. Here, we first designed a new paradigm termed the “finding fault game,” mixing multiple tasks of memory, counting, and visual search, and then developed a multidimensional analysis framework to improve cognitive load prediction using a fusion of spatial, temporal, and spectral EEG features. Specifically, EEG-based functional connectivity, microstates and power spectral densities (PSD) were calculated for three cognitive load levels. Twelve adult subjects participated in the study. The experimental results show that increased cognitive load was associated with elevated theta and degraded alpha power and significant changes in interchannel connectivity and microstates, and that fusing the three types of EEG features improved the performance of three-level cognitive load prediction, achieving the accuracies of greater than 80% in the cross-validation, real-time, and over-time prediction. The findings suggest that all three types of EEG features can serve as signatures of cognitive load and that their fusion can improve multilevel prediction.

Visual navigation and three-dimensional (3D) scene reconstruction are essential for robotics to interact with the surrounding environment. Large-scale scenarios and computational robustness are great challenges facing the research community to achieve this goal. This paper raises a pose-only imaging geometry representation and algorithms that might help solve these challenges. The pose-only representation, equivalent to the classical multiple-view geometry, is discovered to be linearly related to camera global translations, which allows for efficient and robust camera motion estimation. As a result, the spatial feature coordinates can be analytically reconstructed and do not require nonlinear optimization. Comprehensive experiments demonstrate that the computational efficiency of recovering the scene and associated camera poses is significantly improved by 2-4 orders of magnitude.

Recent years have witnessed a remarkable breakthrough in synthetic aperture radar automatic target recognition (SAR ATR) with the development of deep learning (DL). Nonetheless, once deployed, the DL-based methods’ ability to incrementally learn new knowledge from few-shot samples without forgetting the old is fragile, hindering them from discriminating unseen targets in real-world situations. In this article, we propose a cosine prototype learning (CPL) framework to first unlock few-shot class-incremental learning (FSCIL) in the SAR ATR field inspired by the intrinsic relationships between target azimuth-aware knowledge and semantic features under the cosine criterion. By condensing class-specific characteristics into individual prototypes, stable profiles of targets are depicted without losing generalization. For the model’s plasticity, a pairwise structure separation (PSS) loss is introduced to separate old and new classes and compact intraclass features. Meanwhile, the model’s transferability on new classes is guaranteed by a prototype consistency (PC) loss. For the model’s stability, we propose a prototype–exemplar distillation (PED) loss and a prototype recalibration (PR) strategy to penalize semantic drifts of old-class feature spaces and alleviate the misalignment of the learned prototypes successively. At inference, a nearest-class-mean (NCM) classifier is adopted for evaluation by comparing cosine similarity scores between testing samples and class-specific prototypes. In experiments, the proposed components of our method are explored by ablation studies. Strong baselines are established, and extensive experiments conducted on the moving and stationary target acquisition and recognition (MSTAR) dataset show that our method outperforms state-of-the-art methods under various FSCIL conditions, verifying its effectiveness for the FSCIL of SAR ATR.

3D symmetry detection is a fundamental problem in computer vision and graphics. Most prior works detect symmetry when the object model is fully known, few studies symmetry detection on objects with partial observation, such as single RGB-D images. Recent work addresses the problem of detecting symmetries from incomplete data with a deep neural network by leveraging the dense and accurate symmetry annotations. However, due to the tedious labeling process, full symmetry annotations are not always practically available. In this work, we present a 3D symmetry detection approach to detect symmetry from single-view RGB-D images without using symmetry supervision. The key idea is to train the network in a weakly-supervised learning manner to complete the shape based on the predicted symmetry such that the completed shape be similar to existing plausible shapes. To achieve this, we first propose a discriminative variational autoencoder to learn the shape prior in order to determine whether a 3D shape is plausible or not. Based on the learned shape prior, a symmetry detection network is present to predict symmetries that produce shapes with high shape plausibility when completed based on those symmetries. Moreover, to facilitate end-to-end network training and multiple symmetry detection, we introduce a new symmetry parametrization for the learning-based symmetry estimation of both reflectional and rotational symmetry. The proposed approach, coupled symmetry detection with shape completion, essentially learns the symmetry-aware shape prior, facilitating more accurate and robust symmetry detection. Experiments demonstrate that the proposed method is capable of detecting reflectional and rotational symmetries accurately, and shows good generality in challenging scenarios, such as objects with heavy occlusion and scanning noise. Moreover, it achieves state-of-the-art performance, improving the F1-score over the existing supervised learning method by 2%-11% on the ShapeNet and ScanNet datasets.

The scarcity of labels is common and great challenge in traditional supervised learning. Semi-supervised learning (SSL) leverages unlabeled samples to alleviate the absence of label information. Similar with annotation, label proportion is another type of prior information and plays a significant role in classification tasks. Compared with the acquisition of labels, label proportion can be obtained more easily. For example, only a small number of patients have been diagnosed with or not with cancers in hospital database, while the proportion with cancer can be generally estimated by historical records. How to incorporate such prior information of label proportion is crucial but rarely studied in literature. Traditional SSL methods often ignore this prior information and will lead to performance degradation inevitably. To solve this problem, we propose a novel SSL with Label Proportion (SSLLP). Our approach encourages to preserve label consistency and label proportion by imposing the cardinality bound constraints. Our formulated problem equals to a mixed-integer constrained submodular minimization and it is difficult to be solved directly. Therefore, we transformed the original problem into a convex one by Lov$\acute{\text{a}}$a´sz extension and designed an efficient solving algorithm. Extensive experimental results present the improved performance of our method over several state-of-the-art methods.

The neurophysiological basis of spontaneous low-frequency brain activity has become a major theme in the study of neural function in both humans and animal models. In such studies, the anesthesia model was generally adopted. However, the effects of anesthesia on spontaneous activity remain unclear. In this work, we explored the characteristics of cerebral spontaneous low-frequency activities at different depths of anesthesia in mice. Using Fourier transformation and the multitaper analysis methods, spontaneous low-frequency oscillations (LFOs) in the intrinsic signals of different cerebral regions (artery, vein, and cortex) were extracted and analyzed. Under different concentrations of anesthetic, the frequency of spontaneous LFO signals remained stable, while LFO amplitudes increased with the depth of anesthesia. The results imply that the anesthetic impacts the amplitude of spontaneous LFOs but does not alter the oscillation frequency.

As a basic organizing principle of the human brain, hemispheric specialization is an important perspective to explore the pathology of schizophrenia. However, it remains unclearly whether the hemispheric specialization of functional connectivity plays a role in mediating auditory verbal hallucinations in schizophrenia. In this study, 18 schizophrenic patients with auditory verbal hallucinations, 18 patients without auditory verbal hallucinations, and 18 matched healthy controls underwent resting-state functional MRI scans, and seed-based voxel-wise functional connectivity was calculated to quantify the degree of hemispheric specialization. The results revealed that both the auditory verbal hallucinations and non-auditory verbal hallucinations groups exhibited significantly increased specialization in the left middle temporal gyrus and left precuneus, and significantly reduced specialization in the right precuneus relative to healthy controls, and that the auditory verbal hallucinations severity was significantly correlated with the hemispheric specialization of the right precuneus in the auditory verbal hallucinations group. Moreover, the left frontal lobe exhibited reduced hemispheric specialization in the auditory verbal hallucinations group compared with non-auditory verbal hallucinations group, and the patients with and without auditory verbal hallucinations could be clustered into two groups with an accuracy of 80.6% based on the brain regions exhibiting significant specialization changes. The findings indicate that the hemispheric specialization of the aforementioned regions may play a role in mediating auditory verbal hallucinations in schizophrenia, and the distinct hemispheric specialization patterns of functional connectivity may provide a potential biomarker to differentiate schizophrenic patients with and without auditory verbal hallucinations.

The current study aimed to investigate the altered cerebellar–cerebral functional connectivity (FC) induced by radiotherapy to nasopharyngeal carcinoma (NPC) patients. Twenty-four NPC patients without treatment, and 35 NPC patients receiving radiotherapy underwent functional MRI scanning. Montreal cognitive assessment (MoCA) was performed to evaluate the cognitive status of all participants. FC between 10 predefined cerebellar seeds, which were demonstrated to be involved in different brain functional networks, and all brain voxels was obtained for each participant. Using a second-level two-sample t-test, three significantly different FCs between the two patient groups were found, including the connections between the left lobule VIII and the right medial frontal gyrus, the left lobule VIII and the right crus I, and the right lobule VIIb and the right fusiform gyrus. The altered cerebellar–cerebral FCs were also significantly correlated to the MoCA score, as well as the attention score, one of the seven subscores in MoCA. We suggested that the altered cerebellar–cerebral FCs may underlie the radiation-induced cognitive deficits in NPC patients, especially in the domain of attention. Furthermore, considering the functional networks in which the altered connections involved, the anticorrelation between the default network and dorsal attention network may be impaired, and the mediating function of the frontoparietal network to dorsal attention network may be disrupted. The significantly altered cerebellar–cerebral FC may serve as the potential biomarker in revealing the radiation-induced functional abnormalities and may help in the early intervention to the cognitive impairment.

Previous static resting-state functional connectivity (FC) MRI (rs-fcMRI) studies have suggested certain heredity characteristics of schizophrenia. Recently, dynamic rs-fcMRI analysis, which can better characterize the time-varying nature of intrinsic activity and connectivity and may therefore unveil the special connectivity patterns that are always lost in static FC analysis, has shown a potential neuroendophenotype of schizophrenia. In this study, we have extended previous static rs-fcMRI studies to a dynamic study by exploring whether healthy siblings share aberrant dynamic FC patterns with schizophrenic patients, which may imply a potential risk for siblings to develop schizophrenia. We utilized the dynamic rs-fcMRI method using a sliding window approach to evaluate FC discrepancies within transient states across schizophrenic patients, unaffected siblings, and matched healthy controls. Statistical analysis showed five trait-related connections that are related to cingulo-opercular, occipital, and default mode networks, reflecting the shared connectivity alterations between schizophrenic patients and their unaffected siblings. The findings suggested that schizophrenic patients and their unaffected siblings shared common transient functional disconnectivity, implying a potential risk for the healthy siblings of developing schizophrenia.

There has been increasing interest in multivariate pattern analysis (MVPA) as a means of distinguishing psychiatric patients from healthy controls using brain imaging. However, it remains unclear whether MVPA methods can accurately estimate the medication status of psychiatric patients. This study aims to develop an MVPA approach to accurately predict the antidepressant medication status of individuals with major depression on the basis of whole-brain resting-state functional connectivity MRI (rs-fcMRI). We investigated data from rs-fcMRI of 24 medication-naive depressed patients, 16 out of whom subsequently underwent antidepressant treatment and achieved clinical recovery, and 29 demographically similar controls. By training a linear support vector machine classifier and combining it with principal component analysis, the medication-naive patients were identified from the healthy controls with 100% accuracy. In addition, we found reliable correlations between MVPA prediction scores and clinical symptom severity. Moreover, the most discriminative functional connections were located within or across the cerebellum and default mode, affective, and sensorimotor networks, indicating that these networks may play important roles in major depression. Most importantly, only ∼30% of these discriminative connections were normalized in clinically recovered patients after antidepressant treatment. The current study may not only show the feasibility of estimating medication status by MVPA of whole-brain rs-fcMRI data in major depression but also shed new light on the pathological mechanism of this disorder.

In this note, adaptive neural network (NN) control is investigated for a class of uncertain nonlinear systems with asymmetric saturation actuators and external disturbances. To handle the effect of nonsmooth asymmetric saturation nonlinearity, a Gaussian error function-based continuous differentiable asymmetric saturation model is employed such that the backstepping technique can be used in the control design. The explosion of complexity in traditional backstepping design is avoided using dynamic surface control. Using radial basis function NN, adaptive control is developed to guarantee that all the signals in the closed-loop system are semiglobally uniformly ultimately bounded, and the tracking error converges to a small neighborhood of origin by appropriately choosing design constants. The effectiveness of the proposed control is demonstrated in the simulation study.

Behavioral evidence suggests functional remission or recovery in nonrefractory depressive disorder after successful antidepressant therapy, but the effect of treatment on brain structures remains unclear. It is possible that some specific structural changes are trait-related, in addition to some state-dependent anatomical regions that could be normalized by medications. In the current study, 32 treatment-naïve nonrefractory depressive disorder patients and 34 matched healthy controls underwent structural MRI scans and a subgroup including 16 patients underwent the second scans after clinical recovery with antidepressant treatment. The statistical analysis of gray matter images showed that the state-dependent regions mainly comprised the key regions within the lateral default, dorsal attention, and frontoparietal networks, whereas the trait-related regions included the medial prefrontal cortex, right anterior insula, thalamus, right parahippocampal gyrus, and right middle occipital gyrus. Moreover, the gray matter changes in the left orbitofrontal cortex, right middle frontal gyrus, left inferior parietal lobule, thalamus, left precentral gyrus, left precuneus, and right middle occipital gyrus were significantly positively correlated with the durations of the current depressive episode. The current findings may not only shed new light on the neuronal effect of antidepressant on depression but also provide potential evidence of the relapse risks for the clinically recovered patients after antidepressant treatment.

Increasingly more neuroimaging studies have shown that the complex symptoms of schizophrenia are linked to disrupted neural circuits and dysconnectivity of intrinsic connectivity networks. Previous studies have assumed temporal stationarity of resting-state functional connectivity, whereas temporal dynamics have rarely been explored. Here, we utilized resting-state functional MRI with a sliding window approach to measure the amplitude of low-frequency fluctuations (ALFFs) in functional connectivity in 24 patients with schizophrenia and 25 healthy controls. We found that there were significant differences in the ALFFs of specific connections, the majority of which were located between the intrinsic connectivity networks. Importantly, the experimental results of a multivariate pattern analysis of these ALFF measures showed that 81.3 (P<0.0009) of the participants were correctly classified as either schizophrenic patients or healthy controls by leave-one-out cross-validation. Our results show significant abnormality in the dynamics of internetwork functional connectivity in schizophrenia, which contributes toward the characterization and differentiation of schizophrenic patients, and may be used as a potential biomarker.

Research on spontaneous low-frequency oscillations is important to reveal underlying regulatory mechanisms in the brain. The mechanism for the stimulus modulation of low-frequency oscillations is not known. Here, we used the intrinsic optical imaging technique to examine stimulus-modulated low-frequency oscillation signals in the rat visual cortex. The stimulation was presented monocularly as a flashing light with different frequencies and intensities. The phases of low-frequency oscillations in different regions tended to be synchronized and the rhythms typically accelerated within a 30-s period after stimulation. These phenomena were confined to visual stimuli with specific flashing frequencies (12.5–17.5 Hz) and intensities (5–10 mA). The acceleration and synchronization induced by the flashing frequency were more marked than those induced by the intensity. These results show that spontaneous low-frequency oscillations can be modulated by parameter-dependent flashing lights and indicate the potential utility of the visual stimulus paradigm in exploring the origin and function of low-frequency oscillations.

Statistical analysis on diffusion tensor imaging has been used extensively in mesial temporal lobe epilepsy (mTLE) and most studies report decrease in fractional anisotropy (FA) in multiple white matter regions. However, these findings vary across studies and between regions. Therefore, in this study, we used tract-based spatial statistics along with machine learning approaches to investigate the whole-brain white matter changes between 17 left mTLE patients and 15 right mTLE patients and 34 matched healthy controls. The results showed that the three groups could be distinguished from each other with promising accuracy. Compared with controls, the FA value of the most discriminating voxels was decreased in the ipsilateral limbic system, corpus callosum, and temporal white matter in both patient groups. Compared with right mTLE, left mTLE had decreased FA in the left temporal white matter, whereas right mTLE had decreased FA in the right frontal and temporal white matter, and right posterior corona radiata. These findings not only provide useful information for lateralization of the seizure focus but can also be used as a potential biomarker for the diagnosis and treatment of the mTLE. This may be helpful in assessment of patients with mTLE when no lesion is detected on visual evaluation.

Graph-based image segmentation techniques generally represent the problem in terms of a graph. In this work, we present a novel graph, called the directional nearest neighbor graph. The construction principle of this graph is that each node corresponding to a pixel in the image is connected to a fixed number of nearest neighbors measured by color value and the connected neighbors are distributed in four directions. Compared with the classical grid graph and the nearest neighbor graph, our method can capture low-level texture information using a less-connected edge topology. To test the performance of the proposed method, a comparison with other graph-based methods is carried out on synthetic and real-world images. Results show an improved segmentation for texture objects as well as a lower computational load.Graph-based image segmentation techniques generally represent the problem in terms of a graph. In this work, we present a novel graph, called the directional nearest neighbor graph. The construction principle of this graph is that each node corresponding to a pixel in the image is connected to a fixed number of nearest neighbors measured by color value and the connected neighbors are distributed in four directions. Compared with the classical grid graph and the nearest neighbor graph, our method can capture low-level texture information using a less-connected edge topology. To test the performance of the proposed method, a comparison with other graph-based methods is carried out on synthetic and real-world images. Results show an improved segmentation for texture objects as well as a lower computational load.

There is increasing evidence that antisocial personality disorder (ASPD) stems from brain abnormalities. However, there are only a few studies investigating brain structure in ASPD. The aim of this study was to find regional coherence abnormalities in resting-state functional MRI of ASPD. Thirty-two ASPD individuals and 34 controls underwent a resting-state functional MRI scan. The regional homogeneity (ReHo) approach was used to examine whether ASPD was related to alterations in resting-state neural activity. Support vector machine discriminant analysis was used to evaluate the sensitivityspecificity characteristics of the ReHo index in discriminating between the ASPD individuals and controls. The results showed that, compared with controls, ASPD individuals show lower ReHo in the right cerebellum posterior lobe (Crus1) and the right middle frontal gyrus, as well as higher ReHo in the right middle occipital gyrus (BA 19), left inferior temporal gyrus (BA 37), and right inferior occipital gyrus (cuneus, BA 18). All alternation regions reported a predictive accuracy above 70. To our knowledge, this study was the first to study the change in regional activity coherence in the resting brain of ASPD individuals. These results not only elucidated the pathological mechanism of ASPD from a resting-state functional viewpoint but also showed that these alterations in ReHo may serve as potential markers for the detection of ASPD.

Automatic recognition of the contents of a scene is an important issue in the field of computer vision. Although considerable progress has been made, the complexity of scenes remains an important challenge to computer vision research. Most previous approaches for scene recognition are based on the so-called “bag of visual words” model, which uses clustering methods to quantize numerous local region descriptors into a codebook. The size of the codebook and the selection of initial clustering centers greatly affect the performance. Furthermore, the large size of the codebook leads to high computational costs and large memory consumption. To overcome these weaknesses, we present an unsupervised natural scene recognition approach that is not based on the “bag of visual words” model. This approach constructs multiple images of different resolutions and extracts structural and textural features from these images. The structural features are represented by weighted histograms of the gradient orientation descriptor, which is presented in this paper, and the textural features are represented by filter responses of Gabor filters and a Schmid set. We regard the structural and textural features as two independent feature channels, and combine them to realize automatic categorization of scenes using a support vector machine. We then evaluated our approach using three commonly used datasets with various scene categories. Our experiments demonstrate that the weighted histograms of the gradient orientation descriptor outperform the classical scale invariant feature transform descriptor in natural-scene recognition, and our approach achieves good performance with respect to current state-of-the-art methods.Automatic recognition of the contents of a scene is an important issue in the field of computer vision. Although considerable progress has been made, the complexity of scenes remains an important challenge to computer vision research. Most previous approaches for scene recognition are based on the so-called “bag of visual words” model, which uses clustering methods to quantize numerous local region descriptors into a codebook. The size of the codebook and the selection of initial clustering centers greatly affect the performance. Furthermore, the large size of the codebook leads to high computational costs and large memory consumption. To overcome these weaknesses, we present an unsupervised natural scene recognition approach that is not based on the “bag of visual words” model. This approach constructs multiple images of different resolutions and extracts structural and textural features from these images. The structural features are represented by weighted histograms of the gradient orientation descriptor, which is presented in this paper, and the textural features are represented by filter responses of Gabor filters and a Schmid set. We regard the structural and textural features as two independent feature channels, and combine them to realize automatic categorization of scenes using a support vector machine. We then evaluated our approach using three commonly used datasets with various scene categories. Our experiments demonstrate that the weighted histograms of the gradient orientation descriptor outperform the classical scale invariant feature transform descriptor in natural-scene recognition, and our approach achieves good performance with respect to current state-of-the-art methods.

Recent resting-state functional connectivity MRI studies using group-level statistical analysis have demonstrated the inheritable characters of schizophrenia. The objective of the present study was to use pattern classification as a means to investigate schizophrenia inheritance based on the whole-brain resting-state functional connectivity at the individual subject level. One-against-one pattern classifications were made amongst three groups (i.e. patients diagnosed with schizophrenia, healthy siblings, and healthy controls after preprocessing), resulting in an 80.4 separation between patients with schizophrenia and healthy controls, a 77.6 separation between schizophrenia patients and their healthy siblings, and a 78.7 separation between healthy siblings and healthy controls, respectively. These results suggest that the healthy siblings of schizophrenia patients have an altered resting-state functional connectivity pattern compared with healthy controls. Thus, healthy siblings may have a potential higher risk for developing schizophrenia compared with the general population. Moreover, this pattern differed from that of schizophrenia patients and may contribute to the normal behavior exhibition of healthy siblings in daily life.

We combined measures of resting-state functional magnetic resonance imaging and diffusion tensor imaging (DTI) to investigate alterations of function-structure relationships in patients with early-onset schizophrenia. DTI analysis revealed reduced fractional anisotropy in right frontal white matter. Corresponding gray matter regions showed reduced functional connectivity with other regions in the brain in patients with early-onset schizophrenia, compared with healthy controls. Our results demonstrated abnormal function-structure relationships in early-onset schizophrenia, and supported the view that white matter lesions might disrupt the neural circuits between frontal regions and other brain regions, and affect the functional connectivity in the frontal cortex.

We combined measures of resting-state functional magnetic resonance imaging and diffusion tensor imaging (DTI) to investigate alterations of function-structure relationships in patients with early-onset schizophrenia. DTI analysis revealed reduced fractional anisotropy in right frontal white matter. Corresponding gray matter regions showed reduced functional connectivity with other regions in the brain in patients with early-onset schizophrenia, compared with healthy controls. Our results demonstrated abnormal function-structure relationships in early-onset schizophrenia, and supported the view that white matter lesions might disrupt the neural circuits between frontal regions and other brain regions, and affect the functional connectivity in the frontal cortex.

Ample evidence from functional magnetic resonance imaging studies has demonstrated functional brain asymmetries in the motor cortex and cerebellum within the task of finger-to-thumb (intratask), but the asymmetries across left and right hand-performed tasks of finger-to-thumb (intertask) are little known. Here, we found that intratask evoked asymmetry responses in the motor cortex and cerebellum, and interestingly in the Extra-Nuclear and insula. Intertask comparisons between left and right hand-activated images and between the asymmetries of intratasks of left and right hand, however, revealed distinct lateralization responses in the temporal cortex, extranuclear, parahippocampal gyrus, cingulate gyrus and prominently in basal ganglia. These results suggest that multiple aspects of functional asymmetries in motor organization are reflected in specific brain regions.

Sequences of images of the cortical surface can be processed to reveal information about the cortical microcirculation, regional cerebral blood flow (rCBF), and changes induced by neuronal activity. This study examined the use of different analysis methodologies on intrinsic optical images taken from rat sensory motor cortex and testes. Generalized linear model (GLM) analysis was used and compared with standard signal processing methods including principal component analysis. The GLM method has been used by Fristonet al.(1994,Hum. Brain Map.,1: 214–220) in the analysis of functional magnetic resonance imagery to identify regions of focal activity. We investigated the use of this method to analyze video image data of the modulation of rCBF from rat cortex. The results revealed spatiotemporal variations in rCBF in response to stimulation within local regions of cortex. The advantage of the GLM method is that it augments ordinary signal processing methods with an estimate of statistical reliability. The use of different wavelengths of illumination reveals spatial structures with different temporal relationships. In image time series data collected under green and red illumination a phase difference was found in the low frequency ≈0.1 Hz vasomotion oscillation. This phase difference occurred in data from both cortex and testes. A possible explanation of these differences is that the spectral absorption characteristics of the tissue reflect changes in the volume proportions of the different hemoglobin derivatives in interacting with the modulation of the volume of blood. It is suggested that the combination of these effects produces the phase differences we detect.