Structural magnetic resonance imaging (sMRI) is commonly used for the identification of Alzheimer's disease because of its keen insight into atrophy-induced changes in brain structure. Current mainstream convolutional neural network-based deep learning methods ignore the long-term dependencies between voxels; thus, it is challenging to learn the global features of sMRI data. In this study, an advanced deep learning architecture called Brain Informer (BraInf) was developed based on an efficient self-attention mechanism. The proposed model integrates representation learning, feature distilling, and classifier modeling into a unified framework. First, the proposed model uses a multihead ProbSparse self-attention block for representation learning. This self-attention mechanism selects the first ⌊lnN⌋ elements that can represent the overall features from the perspective of probability sparsity, which significantly reduces computational cost. Subsequently, a structural distilling block is proposed that applies the concept of patch merging to the distilling operation. The block reduces the size of the three-dimensional tensor and further lowers the memory cost while preserving the original data as much as possible. Thus, there was a significant improvement in the space complexity. Finally, the feature vector was projected into the classification target space for disease prediction. The effectiveness of the proposed model was validated using the Alzheimer's Disease Neuroimaging Initiative dataset. The model achieved 97.97% and 91.89% accuracy on Alzheimer's disease and mild cognitive impairment classification tasks, respectively. The experimental results also demonstrate that the proposed framework outperforms several state-of-the-art methods.

Available evidence suggests that dynamic functional connectivity can capture time-varying abnormalities in brain activity in resting-state cerebral functional magnetic resonance imaging (rs-fMRI) data and has a natural advantage in uncovering mechanisms of abnormal brain activity in schizophrenia (SZ) patients. Hence, an advanced dynamic brain network analysis model called the temporal brain category graph convolutional network (Temporal-BCGCN) was employed. Firstly, a unique dynamic brain network analysis module, DSF-BrainNet, was designed to construct dynamic synchronization features. Subsequently, a revolutionary graph convolution method, TemporalConv, was proposed based on the synchronous temporal properties of features. Finally, the first modular test tool for abnormal hemispherical lateralization in deep learning based on rs-fMRI data, named CategoryPool, was proposed. This study was validated on COBRE and UCLA datasets and achieved 83.62% and 89.71% average accuracies, respectively, outperforming the baseline model and other state-of-the-art methods. The ablation results also demonstrate the advantages of TemporalConv over the traditional edge feature graph convolution approach and the improvement of CategoryPool over the classical graph pooling approach. Interestingly, this study showed that the lower-order perceptual system and higher-order network regions in the left hemisphere are more severely dysfunctional than in the right hemisphere in SZ, reaffirmings the importance of the left medial superior frontal gyrus in SZ. Our code was available at: https://github.com/swfen/Temporal-BCGCN.

Components of metabolic syndrome might be predictors of the therapeutic outcome of psychiatric symptom in schizophrenia, whereas clinical results are inconsistent and an intrinsic therapeutic link between weaker psychiatric symptoms and emergent metabolic syndrome remains unclear. This study aims to reveal the relationship and illustrate potential mechanism by exploring the alteration of cerebellar functional connectivity (FC) in schizophrenia patients with comorbidity metabolic syndrome. Thirty-six schizophrenia patients with comorbidity of metabolic syndrome (SCZ-MetS), 45 schizophrenia patients without metabolic syndrome (SCZ-nMetS) and 39 healthy controls (HC) were recruited in this study. We constructed FC map of cerebello-cortical circuit and used moderation effect analysis to reveal complicated relationship among FC, psychiatric symptom and metabolic disturbance. Components of metabolic syndrome were significantly correlated with positive symptom score and negative symptom score. Importantly, the dysconnectivity between cognitive module of cerebellum and left middle frontal gyrus in SCZ-nMetS was recuperative increased in SCZ-MetS, and was significantly correlated with general symptom score. Finally, we observed significant moderation effect of body mass index on this correlation. The present findings further supported the potential relationship between emergence of metabolic syndrome and weaker psychiatric symptom, and provided neuroimaging evidence. The mechanism of intrinsic therapeutic link involved functional change of cerebello-cortical circuit.

Schizophrenia (SZ) is considered as a self-disorder with disordered local synchronous activation. Previous studies have reported widespread dyssynchrony of local activation in patients with SZ, which may be one of the crucial physiological mechanisms of SZ. To further verify this assumption, this work used a surface-based two-dimensional regional homogeneity (2dReHo) approach to compare the local neural synchronous spontaneous oscillation between patients with SZ and healthy controls (HC), instead of the volume-based regional homogeneity approach described in previous study. Ninety-seven SZ patients and 126 HC were recruited to this study, and we found the SZ showed abnormal 2dReHo across the cortical surface. Specifically, at the global level, the SZ patients showed significantly reduced global 2dReHo; at the vertex level, the foci with increased 2dReHo in SZ were located in the default mode network (DMN), frontoparietal network (FPN), and limbic network (LN); however, foci with decreased 2dReHo were located in the somatomotor network (SMN), auditory network (AN), and visual network (VN). Additionally, this work found positive correlations between the 2dReHo of bilateral rectus and illness duration, as well as a significant positive correlation between the 2dReHo of right orbital inferior frontal gyrus (OIFG) with the negative scores of the positive and negative syndrome scale in the SZ patients. Therefore, the 2dReHo could provide some effective features contributed to explore the pathophysiology mechanism of SZ.

Achieving a balance between spectral resolution and spatial resolution in multi-spectral remote sensing images is challenging due to physical constraints. Consequently, pan-sharpening technology was developed to address this challenge. While significant progress was recently achieved in deep-learning-based pan-sharpening techniques, most existing deep learning approaches face two primary limitations: (1) convolutional neural networks (CNNs) struggle with long-range dependency issues, and (2) significant detail loss during deep network training. Moreover, despite these methods’ pan-sharpening capabilities, their generalization to full-sized raw images remains problematic due to scaling disparities, rendering them less practical. To tackle these issues, we introduce in this study a multi-spectral remote sensing image fusion network, termed TAMINet, which leverages a two-stream coordinate attention mechanism and multi-detail injection. Initially, a two-stream feature extractor augmented with the coordinate attention (CA) block is employed to derive modal-specific features from low-resolution multi-spectral (LRMS) images and panchromatic (PAN) images. This is followed by feature-domain fusion and pan-sharpening image reconstruction. Crucially, a multi-detail injection approach is incorporated during fusion and reconstruction, ensuring the reintroduction of details lost earlier in the process, which minimizes high-frequency detail loss. Finally, a novel hybrid loss function is proposed that incorporates spatial loss, spectral loss, and an additional loss component to enhance performance. The proposed methodology’s effectiveness was validated through experiments on WorldView-2 satellite images, IKONOS, and QuickBird, benchmarked against current state-of-the-art techniques. Experimental findings reveal that TAMINet significantly elevates the pan-sharpening performance for large-scale images, underscoring its potential to enhance multi-spectral remote sensing image quality.