Discriminative Brain Research Articles

Dynamic functional connections analysis with spectral learning for brain disorder detection

Dynamic functional connections (dFCs), can reveal neural activities, which provides an insightful way of mining the temporal patterns within the human brain and further detecting brain disorders. However, most existing studies focus on the dFCs estimation to identify brain disorders by shallow temporal features and methods, which cannot capture the inherent temporal patterns of dFCs effectively. To address this problem, this study proposes a novel method, named dynamic functional connections analysis with spectral learning (dCSL), to explore inherently temporal patterns of dFCs and further detect the brain disorders. Concretely, dCSL includes two components, dFCs estimation module and dFCs analysis module. In the former, dFCs are estimated via the sliding window technique. In the latter, the spectral kernel mapping is first constructed by combining the Fourier transform with the non-stationary kernel. Subsequently, the spectral kernel mapping is stacked into a deep kernel network to explore higher-order temporal patterns of dFCs through spectral learning. The proposed dCSL, sharing the benefits of deep architecture and non-stationary kernel, can not only calculate the long-range relationship but also explore the higher-order temporal patterns of dFCs. To evaluate the proposed method, a set of brain disorder classification tasks are conducted on several public datasets. As a result, the proposed dCSL achieves 5% accuracy improvement compared with the widely used approaches for analyzing sequence data, 1.3% accuracy improvement compared with the state-of-the-art methods for dFCs. In addition, the discriminative brain regions are explored in the ASD detection task. The findings in this study are consistent with the clinical performance in ASD.

The influence of mental calculations on brain regions and heart rates

Performing mathematical calculations is a cognitive activity that can affect biological signals. This study aims to examine the changes in electroencephalogram (EEG) and electrocardiogram (ECG) signals of 36 healthy subjects during the performance of arithmetic tasks. To process EEG signals in different frequency bands, the energy and entropy of entropy (EoE) were extracted from the power spectrum and phase spectrum, respectively. Statistical analysis was conducted to determine meaningful features. These features were sent into support vector machine (SVM) and multi-layer perception (MLP) classifiers to assess their capability in separating math and rest classes. Results indicated the highest classification accuracy of 98.4% for classifying good counters in math and rest state using the MLP method. Based on the majority of features selected for each EEG channel, discriminative brain areas were identified. Analyzing EEG signals proved that math calculation may have multiple influences on various parts of the brain. By comparing good counters’ brain activities to those in a resting state, prominent changes were observed in the F4, C4, T4, T5, P3, and O2 areas. However, O1 and O2 channels showed significant changes in the brain of bad counters compared to the resting state. Considering ECG signals also demonstrated that during math calculation the number of heart rates per minute surpasses the rest state. These alterations can occur due to cognitive abilities or emotional processes which were observed to be prominent in subjects who performed more accurate calculations.

Leveraging Brain Modularity Prior for Interpretable Representation Learning of fMRI.

Resting-state functional magnetic resonance imaging (rs-fMRI) can reflect spontaneous neural activities in the brain and is widely used for brain disorder analysis. Previous studies focus on extracting fMRI representations using machine/deep learning methods, but these features typically lack biological interpretability. The human brain exhibits a remarkable modular structure in spontaneous brain functional networks, with each module comprised of functionally interconnected brain regions-of-interest (ROIs). However, existing learning-based methods cannot adequately utilize such brain modularity prior. In this paper, we propose a brain modularity-constrained dynamic representation learning framework for interpretable fMRI analysis, consisting of dynamic graph construction, dynamic graph learning via a novel modularity-constrained graph neural network (MGNN), and prediction and biomarker detection. The designed MGNN is constrained by three core neurocognitive modules (i.e., salience network, central executive network, and default mode network), encouraging ROIs within the same module to share similar representations. To further enhance discriminative ability of learned features, we encourage the MGNN to preserve network topology of input graphs via a graph topology reconstruction constraint. Experimental results on 534 subjects with rs-fMRI scans from two datasets validate the effectiveness of the proposed method. The identified discriminative brain ROIs and functional connectivities can be regarded as potential fMRI biomarkers to aid in clinical diagnosis.

Elucidating genetic and molecular basis of altered higher-order brain structure-function coupling in major depressive disorder

Previous studies have shown that major depressive disorder (MDD) patients exhibit structural and functional impairments, but few studies have investigated changes in higher-order coupling between structure and function. Here, we systematically investigated the effect of MDD on higher-order coupling between structural connectivity (SC) and functional connectivity (FC). Each brain region was mapped into embedding vector by the node2vec algorithm. We used support vector machine (SVM) with the brain region embedding vector to distinguish MDD patients from health controls (HCs) and identify the most discriminative brain regions. Our study revealed that MDD patients had decreased higher-order coupling in connections between the most discriminative brain regions and local connections in rich-club organization and increased higher-order coupling in connections between the ventral attentional network and limbic network compared with HCs. Interestingly, transcriptome-neuroimaging association analysis demonstrated the correlations between regional rSC-FC coupling variations between MDD patients and HCs and α/β-hydrolase domain-containing 6 (ABHD6), β 1,3-N-acetylglucosaminyltransferase-9(β3GNT9), transmembrane protein 45B (TMEM45B), the correlation between regional dSC-FC coupling variations and retinoic acid early transcript 1E antisense RNA 1(RAET1E-AS1), and the correlations between regional iSC-FC coupling variations and ABHD6, β3GNT9, katanin-like 2 protein (KATNAL2). In addition, correlation analysis with neurotransmitter receptor/transporter maps found that the rSC-FC and iSC-FC coupling variations were both correlated with neuroendocrine transporter (NET) expression, and the dSC-FC coupling variations were correlated with metabotropic glutamate receptor 5 (mGluR5). Further mediation analysis explored the relationship between genes, neurotransmitter receptor/transporter and MDD related higher-order coupling variations. These findings indicate that specific genetic and molecular factors underpin the observed disparities in higher-order SC-FC coupling between MDD patients and HCs. Our study confirmed that higher-order coupling between SC and FC plays an important role in diagnosing MDD. The identification of new biological evidence for MDD etiology holds promise for the development of innovative antidepressant therapies.

Exploring the potential of representation and transfer learning for anatomical neuroimaging: Application to psychiatry

The perspective of personalized medicine for brain disorders requires efficient learning models for anatomical neuroimaging-based prediction of clinical conditions. There is now a consensus on the benefit of deep learning (DL) in addressing many medical imaging tasks, such as image segmentation. However, for single-subject prediction problems, recent studies yielded contradictory results when comparing DL with Standard Machine Learning (SML) on top of classical feature extraction. Most existing comparative studies were limited in predicting phenotypes of little clinical interest, such as sex and age, and using a single dataset. Moreover, they conducted a limited analysis of the employed image pre-processing and feature selection strategies. This paper extensively compares DL and SML prediction capacity on five multi-site problems, including three increasingly complex clinical applications in psychiatry namely schizophrenia, bipolar disorder, and Autism Spectrum Disorder (ASD) diagnosis. To compensate for the relative scarcity of neuroimaging data on these clinical datasets, we also evaluate three pre-training strategies for transfer learning from brain imaging of the general healthy population: self-supervised learning, generative modeling and supervised learning with age. Overall, we find similar performance between randomly initialized DL and SML for the three clinical tasks and a similar scaling trend for sex prediction. This was replicated on an external dataset. We also show highly correlated discriminative brain regions between DL and linear ML models in all problems. Nonetheless, we demonstrate that self-supervised pre-training on large-scale healthy population imaging datasets (N≈10k), along with Deep Ensemble, allows DL to learn robust and transferable representations to smaller-scale clinical datasets (N≤1k). It largely outperforms SML on 2 out of 3 clinical tasks both in internal and external test sets. These findings suggest that the improvement of DL over SML in anatomical neuroimaging mainly comes from its capacity to learn meaningful and useful abstract representations of the brain anatomy, and it sheds light on the potential of transfer learning for personalized medicine in psychiatry

Aberrant concordance among dynamics of spontaneous brain activity in patients with migraine without aura: A multivariate pattern analysis study

BackgroundAlterations in the static and dynamic characteristics of spontaneous brain activity have been extensively studied to investigate functional brain changes in migraine without aura (MwoA). However, alterations in concordance among the dynamics of spontaneous brain activity in MwoA remain largely unknown. This study aimed to determine the possibilities of diagnosis based on the concordance indices. MethodsResting-state functional MRI scans were performed on 32 patients with MwoA and 33 matched healthy controls (HCs) in the first cohort, as well as 36 patients with MwoA and 32 HCs in the validation cohort. The dynamic indices including fractional amplitude of low-frequency fluctuation, regional homogeneity, voxel-mirrored homotopic connectivity, degree centrality and global signal connectivity were analyzed. We calculated the concordance of grey matter volume-wise (across voxels) and voxel-wise (across time windows) to quantify the degree of integration among different functional levels represented by these dynamic indices. Subsequently, the voxel-wise concordance alterations were analyzed as features for multi-voxel pattern analysis (MVPA) utilizing the support vector machine. ResultsCompared with that of HCs, patients with MwoA had lower whole-grey matter volume-wise concordance, and the mean value of volume-wise concordance was negatively correlated with the frequency of migraine attacks. The MVPA results revealed that the most discriminative brain regions were the right thalamus, right cerebellar Crus II, left insula, left precentral gyrus, right cuneus, and left inferior occipital gyrus. ConclusionsConcordance alterations in the dynamics of spontaneous brain activity in brain regions could be an important feature in the identification of patients with MwoA.

Identifying ADHD-Related Abnormal Functional Connectivity with a Graph Convolutional Neural Network.

Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental disorder that is characterized by inattention, hyperactivity, and impulsivity. The neural mechanisms underlying ADHD remain inadequately understood, and current approaches do not well link neural networks and attention networks within brain networks. Our objective is to investigate the neural mechanisms related to attention and explore neuroimaging biological tags that can be generalized within the attention networks. In this paper, we utilized resting-state functional magnetic resonance imaging data to examine the differential functional connectivity network between ADHD and typically developing individuals. We employed a graph convolutional neural network model to identify individuals with ADHD. After classification, we visualized brain regions with significant contributions to the classification results. Our results suggest that the frontal, temporal, parietal, and cerebellar regions are likely the primary areas of dysfunction in individuals with ADHD. We also explored the relationship between regions of interest and attention networks, as well as the connection between crucial nodes and the distribution of positively and negatively correlated connections. This analysis allowed us to pinpoint the most discriminative brain regions, including the right orbitofrontal gyrus, the left rectus gyrus and bilateral insula, the right inferior temporal gyrus and bilateral transverse temporal gyrus in the temporal region, and the lingual gyrus of the occipital lobe, multiple regions of the basal ganglia and the upper cerebellum. These regions are primarily involved in the attention executive control network and the attention orientation network. Dysfunction in the functional connectivity of these regions may contribute to the underlying causes of ADHD.

Adaptive 3DCNN-based Interpretable Ensemble Model for Early Diagnosis of Alzheimer's Disease.

Adaptive interpretable ensemble model based on three-dimensional Convolutional Neural Network (3DCNN) and Genetic Algorithm (GA), i.e., 3DCNN+EL+GA, was proposed to differentiate the subjects with Alzheimer's Disease (AD) or Mild Cognitive Impairment (MCI) and further identify the discriminative brain regions significantly contributing to the classifications in a data-driven way. Plus, the discriminative brain sub-regions at a voxel level were further located in these achieved brain regions, with a gradient-based attribution method designed for CNN. Besides disclosing the discriminative brain sub-regions, the testing results on the datasets from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Open Access Series of Imaging Studies (OASIS) indicated that 3DCNN+EL+GA outperformed other state-of-the-art deep learning algorithms and that the achieved discriminative brain regions (e.g., the rostral hippocampus, caudal hippocampus, and medial amygdala) were linked to emotion, memory, language, and other essential brain functions impaired early in the AD process. Future research is needed to examine the generalizability of the proposed method and ideas to discern discriminative brain regions for other brain disorders, such as severe depression, schizophrenia, autism, and cerebrovascular diseases, using neuroimaging.

Analysing the behaviour change of brain regions of methamphetamine abusers using electroencephalogram signals: Hope to design a decision support system.

Long-term use of methamphetamine (meth) causes cognitive and neuropsychological impairments. Analysing the impact of this substance on the human brain can aid prevention and treatment efforts. In this study, the electroencephalogram (EEG) signals of meth abusers in the abstinence period and healthy subjects were recorded during eyes-closed and eyes-opened states to distinguish the brain regions that meth can significantly influence. In addition, a decision support system (DSS) was introduced as a complementary method to recognize substance users accompanied by biochemical tests. According to these goals, the recorded EEG signals were pre-processed and decomposed into frequency bands using the discrete wavelet transform (DWT) method. For each frequency band, energy, KS entropy, Higuchi and Katz fractal dimensions of signals were calculated. Then, statistical analysis was applied to select features whose channels contain a p-value less than 0.05. These features between two groups were compared, and the location of channels containing more features was specified as discriminative brain areas. Due to evaluating the performance of features and distinguishing the two groups in each frequency band, features were fed into a k-nearest neighbour (KNN), support vector machine (SVM), multilayer perceptron neural networks (MLP) and linear discriminant analysis (LDA) classifiers. The results indicated that prolonged consumption of meth has a considerable impact on the brain areas responsible for working memory, motor function, attention, visual interpretation, and speech processing. Furthermore, the best classification accuracy, almost 95.8%, was attained in the gamma band during the eyes-closed state.

End-stage renal disease accompanied by mild cognitive impairment: A study and analysis of trimodal brain network fusion.

The function and structure of brain networks (BN) may undergo changes in patients with end-stage renal disease (ESRD), particularly in those accompanied by mild cognitive impairment (ESRDaMCI). Many existing methods for fusing BN focus on extracting interaction features between pairs of network nodes from each mode and combining them. This approach overlooks the correlation between different modal features during feature extraction and the potentially valuable information that may exist between more than two brain regions. To address this issue, we propose a model using a multi-head self-attention mechanism to fuse brain functional networks, white matter structural networks, and gray matter structural networks, which results in the construction of brain fusion networks (FBN). Initially, three networks are constructed: the brain function network, the white matter structure network, and the individual-based gray matter structure network. The multi-head self-attention mechanism is then applied to fuse the three types of networks, generating attention weights that are transformed into an optimized model. The optimized model introduces hypergraph popular regular term and L1 norm regular term, leading to the formation of FBN. Finally, FBN is employed in the diagnosis and prediction of ESRDaMCI to evaluate its classification performance and investigate the correlation between discriminative brain regions and cognitive dysfunction. Experimental results demonstrate that the optimal classification accuracy achieved is 92.80%, which is at least 3.63% higher than the accuracy attained using other methods. This outcome confirms the effectiveness of our proposed method. Additionally, the identification of brain regions significantly associated with scores on the Montreal cognitive assessment scale may shed light on the underlying pathogenesis of ESRDaMCI.

Boosting lower-limb motor imagery performance through an ensemble method for gait rehabilitation

Lower-limb exoskeletons have been used extensively in many rehabilitation applications to assist disabled people with their therapies. Brain–machine interfaces (BMIs) further provide effective and natural control schemes. However, the limited performance of brain signal decoding from lower-limb kinematics restricts the broad growth of both BMI and rehabilitation industry. To address these challenges, we propose an ensemble method for lower-limb motor imagery (MI) classification. The proposed model employs multiple techniques to boost performance, including deep and shallow parts. Traditional wavelet transformation followed by filter-bank common spatial pattern (CSP) employs neurophysiologically reasonable patterns, while multi-head self-attention (MSA) followed by temporal convolutional network (TCN) extracts deeper encoded generalized patterns. Experimental results in a customized lower-limb exoskeleton on 8 subjects in 3 consecutive sessions showed that the proposed method achieved 60.27% and 64.20% for three (MI of left leg, MI of right leg, and rest) and two classes (lower-limb MI vs. rest), respectively. Besides, the proposed model achieves improvements of up to 4% and 2% accuracy for the subject-specific and subject-independent modes compared to the current state-of-the-art (SOTA) techniques, respectively. Finally, feature analysis was conducted to show discriminative brain patterns in each MI task and sessions with different feedback modalities. The proposed models integrated in the brain-actuated lower-limb exoskeleton established a potential BMI for gait training and neuroprosthesis.

Multi feature fusion network for schizophrenia classification and abnormal brain network recognition

Schizophrenia classification and abnormal brain network recognition have an important research significance. Researchers have proposed many classification methods based on machine learning and deep learning. However, fewer studies utilized the advantages of complementary information from multi feature to learn the best representation of schizophrenia. In this study, we proposed a multi-feature fusion network (MFFN) using functional network connectivity (FNC) and time courses (TC) to distinguish schizophrenia patients from healthy controls. DNN backbone was adopted to learn the feature map of functional network connectivity, C-RNNAM backbone was designed to learn the feature map of time courses, and Deep SHAP was applied to obtain the most discriminative brain networks. We proved the effectiveness of this proposed model using the combining two public datasets and evaluated this model quantitatively using the evaluation indexes. The results showed that the functional network connectivity generated by independent component analysis has advantage in schizophrenia classification by comparing static and dynamic functional connections. This method obtained the best classification accuracy (ACC=87.30%, SPE=89.28%, SEN=85.71%, F1 =88.23%, and AUC=0.9081), and it demonstrated the superiority of this proposed model by comparing state-of-the-art methods. Ablation experiment also demonstrated that multi feature fusion and attention module can improve classification accuracy. The most discriminative brain networks showed that default mode network and visual network of schizophrenia patients have aberrant connections in brain networks. In conclusion, this method can identify schizophrenia effectively and visualize the abnormal brain network, and it has important clinical application value.

HCTMFS: A multi-modal feature selection framework with higher-order correlated topological manifold for ESRDaMCI

Background and ObjectiveThe diagnosis of end-stage renal disease associated with mild cognitive impairment (ESRDaMCI) mainly relies on objective cognitive assessment, clinical observation, and neuro-psychological evaluation, while only adopting clinical tools often limits the diagnosis accuracy. MethodsWe proposed a multi-modal feature selection framework with higher-order correlated topological manifold (HCTMFS) to classify ESRDaMCI patients and identify the discriminative brain regions. It constructed brain structural and functional networks with diffuse kurtosis imaging (DKI) and functional magnetic resonance imaging (fMRI) data, and extracted node efficiency and clustering coefficient from the brain networks to construct multi-modal feature matrices. The topological relationship matrices were constructed to measure the lower-order topological correlation between features. Then the consensus matrices were learned to approximate the topological relationship matrices at different confidence levels and eliminate the noise influence of individual matrices. ResultsThe higher-order topological correlation between features was explored by the Laplacian matrix of the hypergraph, which was calculated through the consensus matrix. The new framework achieved an accuracy rate of 93.56 % for classifying ESRDaMCI patients, and outperformed the existing state-of-the-art methods in terms of sensitivity, specificity, and area under the curve. ConclusionsThis study contributes to effectively reflect the functional neural degradation of ESRDaMCI and provide a reference for the diagnosis of ESRDaMCI by selecting discriminative brain regions.

Altered effective connectivity from cerebellum to motor cortex in chronic low back pain: A multivariate pattern analysis and spectral dynamic causal modeling study

To explore the central processing mechanism of pain perception in chronic low back pain (cLBP) using multi-voxel pattern analysis (MVPA) based on the static and dynamic fractional amplitude of low-frequency fluctuations (fALFF) analysis, and spectral dynamic causal modeling (spDCM). Thirty-two patients with cLBP and 29 matched healthy controls (HCs) for the first cohort and 24 patients with cLBP and 22 HCs for the validation cohort underwent resting-state fMRI scan. The alterations in static and dynamic fALFF were as classification features to distinguish patients with cLBP from HCs. The brain regions gotten from the MVPA results were used for further spDCM analysis. We found that the most discriminative brain regions that contributed to the classification were the right supplementary motor area (SMA.R), left paracentral lobule (PCL.L), and bilateral cerebellar Crus II. The spDCM results displayed decreased excitatory influence from the bilateral cerebellar Crus II to PCL.L in patients with cLBP compared with HCs. Moreover, the conversion of effective connectivity from the bilateral cerebellar Crus II to SMA.R from excitatory influence to inhibitive influence, and the effective connectivity strength exhibited partially mediated effects on Chinese Short Form Oswestry Disability Index Questionnaire (C-SFODI) scores. Our findings suggest that the cerebellum and its weakened or inhibited connections to the motor cortex may be one of the underlying feedback pathways for pain perception in cLBP, and partially mediate the degree of dysfunction.

Brain morphometric features predict depression symptom phenotypes in late-life depression using a deep learning model.

Our objective was to use deep learning models to identify underlying brain regions associated with depression symptom phenotypes in late-life depression (LLD). Diagnosed with LLD (N = 116) and enrolled in a prospective treatment study. Cross-sectional. Structural magnetic resonance imaging (sMRI) was used to predict five depression symptom phenotypes from the Hamilton and MADRS depression scales previously derived from factor analysis: (1) Anhedonia, (2) Suicidality, (3) Appetite, (4) Sleep Disturbance, and (5) Anxiety. Our deep learning model was deployed to predict each factor score via learning deep feature representations from 3D sMRI patches in 34 a priori regions-of-interests (ROIs). ROI-level prediction accuracy was used to identify the most discriminative brain regions associated with prediction of factor scores representing each of the five symptom phenotypes. Factor-level results found significant predictive models for Anxiety and Suicidality factors. ROI-level results suggest the most LLD-associated discriminative regions in predicting all five symptom factors were located in the anterior cingulate and orbital frontal cortex. We validated the effectiveness of using deep learning approaches on sMRI for predicting depression symptom phenotypes in LLD. We were able to identify deep embedded local morphological differences in symptom phenotypes in the brains of those with LLD, which is promising for symptom-targeted treatment of LLD. Future research with machine learning models integrating multimodal imaging and clinical data can provide additional discriminative information.

Image-Evoked Emotion Recognition for Hearing-Impaired Subjects with EEG Signals

In recent years, there has been a growing interest in the study of emotion recognition through electroencephalogram (EEG) signals. One particular group of interest are individuals with hearing impairments, who may have a bias towards certain types of information when communicating with those in their environment. To address this, our study collected EEG signals from both hearing-impaired and non-hearing-impaired subjects while they viewed pictures of emotional faces for emotion recognition. Four kinds of feature matrices, symmetry difference, and symmetry quotient based on original signal and differential entropy (DE) were constructed, respectively, to extract the spatial domain information. The multi-axis self-attention classification model was proposed, which consists of local attention and global attention, combining the attention model with convolution through a novel architectural element for feature classification. Three-classification (positive, neutral, negative) and five-classification (happy, neutral, sad, angry, fearful) tasks of emotion recognition were carried out. The experimental results show that the proposed method is superior to the original feature method, and the multi-feature fusion achieved a good effect in both hearing-impaired and non-hearing-impaired subjects. The average classification accuracy for hearing-impaired subjects and non-hearing-impaired subjects was 70.2% (three-classification) and 50.15% (five-classification), and 72.05% (three-classification) and 51.53% (five-classification), respectively. In addition, by exploring the brain topography of different emotions, we found that the discriminative brain regions of the hearing-impaired subjects were also distributed in the parietal lobe, unlike those of the non-hearing-impaired subjects.

Addressing multi-site functional MRI heterogeneity through dual-expert collaborative learning for brain disease identification.

Several studies employ multi-site rs-fMRI data for major depressive disorder (MDD) identification, with a specific site as the to-be-analyzed target domain and other site(s) as the source domain. But they usually suffer from significant inter-site heterogeneity caused by the use of different scanners and/or scanning protocols and fail to build generalizable models that can well adapt to multiple target domains. In this article, we propose a dual-expert fMRI harmonization (DFH) framework for automated MDD diagnosis. Our DFH is designed to simultaneously exploit data from a single labeled source domain/site and two unlabeled target domains for mitigating data distribution differences across domains. Specifically, the DFH consists of a domain-generic student model and two domain-specific teacher/expert models that are jointly trained to perform knowledge distillation through a deep collaborative learning module. A student model with strong generalizability is finally derived, which can be well adapted to unseen target domains and analysis of other brain diseases. To the best of our knowledge, this is among the first attempts to investigate multi-target fMRI harmonization for MDD diagnosis. Comprehensive experiments on 836 subjects with rs-fMRI data from 3 different sites show the superiority of our method. The discriminative brain functional connectivities identified by our method could be regarded as potential biomarkers for fMRI-related MDD diagnosis.

A voxel-based morphometry investigation of brain structure variations in late-life depression with insomnia.

Late-life depression (LLD) is linked to various medical conditions and influenced by aging-related processes. Sleep disturbances and insomnia symptoms may be early indicators or risk factors for depression. Neuroimaging studies have attempted to understand the neural mechanisms underlying LLD, focusing on different brain networks. This study aims to further delineate discriminative brain structural profiles for LLD with insomnia using MRI. We analyzed 24 cases in the LLD with insomnia group, 26 cases in the LLD group, and 26 in the healthy control (HC) group. Patients were evaluated using the Hamilton Depression Rating Scale (HAMD-17), Hamilton Anxiety Rating Scale (HAMA), Mini-Mental State Examination (MMSE), and Pittsburgh Sleep Quality Index (PSQI). Structural MRI data were gathered and analyzed using voxel-based morphometry (VBM) to identify differences in gray matter volume (GMV) among the groups. Correlation analyses were conducted to explore the relationships between GMV and clinical characteristics. Significant difference in sex distribution was observed across the groups (p = 0.029). However, no significant differences were detected in age and MMSE scores among the groups. LLD with insomnia group exhibited significantly higher HAMA (p = 0.041) and PSQI scores (p < 0.05) compared to the LLD group. ANOVA identified significant difference in GMV of anterior lobe of cerebellum (peak MNI coordinate: x = 52, y = -40, z = -30) among HC, LLD, and LLD with insomnia. Post-hoc two-sample t-tests revealed that the significant difference in GMV was only found between the LLD group and the HC group (p < 0.05). The mean GMV in the cerebellum was positively correlated with HAMA scale in LLD patients (r = 0.47, p < 0.05). There is significant difference in GMV in the LLD group, the association between late-life depression and insomnia may be linked to anxiety. This study provides insights into the discriminative brain structural profiles of LLD and LLD with insomnia, advancing the understanding of the underlying neural mechanisms and potential targets for intervention.

Multimodal cross enhanced fusion network for diagnosis of Alzheimer’s disease and subjective memory complaints

Deep learning methods using multimodal imagings have been proposed for the diagnosis of Alzheimer’s disease (AD) and its early stages (SMC, subjective memory complaints), which may help to slow the progression of the disease through early intervention. However, current fusion methods for multimodal imagings are generally coarse and may lead to suboptimal results through the use of shared extractors or simple downscaling stitching. Another issue with diagnosing brain diseases is that they often affect multiple areas of the brain, making it important to consider potential connections throughout the brain. However, traditional convolutional neural networks (CNNs) may struggle with this issue due to their limited local receptive fields. To address this, many researchers have turned to transformer networks, which can provide global information about the brain but can be computationally intensive and perform poorly on small datasets. In this work, we propose a novel lightweight network called MENet that adaptively recalibrates the multiscale long-range receptive field to localize discriminative brain regions in a computationally efficient manner. Based on this, the network extracts the intensity and location responses between structural magnetic resonance imagings (sMRI) and 18-Fluoro-Deoxy-Glucose Positron Emission computed Tomography (FDG-PET) as an enhancement fusion for AD and SMC diagnosis. Our method is evaluated on the publicly available ADNI datasets and achieves 97.67% accuracy in AD diagnosis tasks and 81.63% accuracy in SMC diagnosis tasks using sMRI and FDG-PET. These results achieve state-of-the-art (SOTA) performance in both tasks. To the best of our knowledge, this is one of the first deep learning research methods for SMC diagnosis with FDG-PET.

Hypergraph representation of multimodal brain networks for patients with end-stage renal disease associated with mild cognitive impairment

The structure and function of brain networks (BN) may be altered in patients with end-stage renal disease (ESRD). However, there are relatively few attentions on ESRD associated with mild cognitive impairment (ESRDaMCI). Most studies focus on the pairwise relationships between brain regions, without taking into account the complementary information of functional connectivity (FC) and structural connectivity (SC). To address the problem, a hypergraph representation method is proposed to construct a multimodal BN for ESRDaMCI. First, the activity of nodes is determined by connection features extracted from functional magnetic resonance imaging (fMRI) (i.e., FC), and the presence of edges is determined by physical connections of nerve fibers extracted from diffusion kurtosis imaging (DKI) (i.e., SC). Then, the connection features are generated through bilinear pooling and transformed into an optimization model. Next, a hypergraph is constructed according to the generated node representation and connection features, and the node degree and edge degree of the hypergraph are calculated to obtain the hypergraph manifold regularization (HMR) term. The HMR and L1 norm regularization terms are introduced into the optimization model to achieve the final hypergraph representation of multimodal BN (HRMBN). Experimental results show that the classification performance of HRMBN is significantly better than that of several state-of-the-art multimodal BN construction methods. Its best classification accuracy is 91.0891%, at least 4.3452% higher than that of other methods, verifying the effectiveness of our method. The HRMBN not only achieves better results in ESRDaMCI classification, but also identifies the discriminative brain regions of ESRDaMCI, which provides a reference for the auxiliary diagnosis of ESRD.