Developing robust Alzheimer's Disease (AD) classification models necessitates extensive training data, but aggregating multi-center medical data poses privacy risks. Although Federated Learning (FL) and Swarm Learning (SL) allow training generic models without data sharing, their performance is limited by variations in AD pathology features and sample class imbalances across centers. To address this issue, we propose a novel Harmonized Swarm Learning framework with Guided Optimization (HSGO) to enhance multi-center collaboration while preserving data privacy. Our framework employs a class-balanced loss function to train a robust generic model and guides the optimization of personalized models towards the generic model, eliminating extra AD pathology feature extraction steps. Furthermore, we design a dynamic feature similarity storage mechanism to facilitate personalized training. Experiments performed under two different multi-center data partitioning scenarios demonstrate that HSGO achieves competitive performance when compared with five baseline methods. Additionally, Layer-wise Relevance Propagation (LRP) analysis indicates that HSGO may help identify potential key brain regions in AD by integrating local and global features compared to traditional SL.

In the era of big data, the demand for spatial dataset search has become increasingly urgent. Leveraging the powerful storage and computing capabilities of cloud platforms, the cloud has become a common choice for deploying dataset search services. However, under risks of untrusted cloud environment and malicious attacks, protecting the privacy of sensitive location information during spatial dataset search becomes particularly critical. This paper focuses on the problem of privacy-preserving spatial datasets joinable search in cloud, which has not been addressed in existing research. We first propose a grid-based joinable coverage distinction model to measure the joinability of spatial datasets, and further present a baseline scheme (PDJDS). To further enhance efficiency and reduce storage cost, we propose an optimized scheme (PDJDS+), which constructs a coarse-grained grid-based inverted index to filter candidate datasets and integrates a joinable coverage distinction check table to expedite the evaluation of spatial dataset coverage distinction. Experiments conducted on three real-world spatial data repositories demonstrate that our scheme achieves superior performance in terms of search accuracy, efficiency, and storage cost.

BACKGROUND: As a typical type of neurodegenerative disorders, Parkinson's disease(PD) is characterized by significant clinical and progression heterogeneity. Based on gene expression data, reliable detection of PACE subtypes in Parkinson's disease(PD-PACE) has played a crucial role in addressing the heterogeneity of this disease. Established machine learning approaches generally adopt single-view learning schemes and employ temporal features underlying RNA sequencing data. Topological features, which are associated with gene graphs and cell graphs, were disregarded in previous works. Actually, Parkinson-specific gene graphs(PGG) could act as topological features to capture structural changes of molecular networks. RESULTS: Under the framework of dual-view graph learning, this study proposes a DualGCN-GE method to identify multiple PD-PACE subtypes from whole-blood expression data, with regards of progression velocity. This DualGCN-GE method has proposed dual-view graph convolution network(GCN) to integrate temporal and topological features underlying whole-blood expression data, thus detecting PD-PACE subtypes. Experimental analysis of three benchmark datasets has validated the effectiveness and advantage of the DualGCN-GE method in the disease subtype detection task. CONCLUSION: For gene expression data of human blood samples, topological features have encoded unique information that are absent in temporal features. Using a collaborative fusion strategy, spatio-temporal representations extracted from whole blood expression data have improved accuracy and reliability in detecting PD-PACE subtypes.

Ultrasound measurement of optic nerve sheath diameter (ONSD) is considered a noninvasive method for estimating elevated intracranial pressure (ICP) in patients. Clinical trials have demonstrated a strong correlation between changes in ONSD and changes in ICP. Therefore, accurate segmentation of the ONSD is crucial for noninvasive ICP assessment. In this paper, we propose a two-stage self-supervised semantic segmentation method to enhance optic nerve segmentation. In the pre-training phase, we use a fully convolutional-based masked autoencoder (FCMAE) to reconstruct full images from partially masked inputs. The encoder of FCMAE aggregates contextual information to infer the masked image regions, and this pretrained encoder is then migrated to the segmentation task for parameter initialization. In the fine-tuning phase, we perform the optic nerve segmentation task. After obtaining the initial segmentation results through the UPerNet network, we use a direction field (DF) module to compute a vector of DFs pointing to the nearest edge of the optic nerve for each pixel. This DF information is then used to refine the initial segmentation results via the feature correction module. The model was trained on a dataset of optic nerve sheath images collected from hospital patients and achieved a Dice score of 98.03%. Our proposed method exhibits superior performance across all metrics compared to other segmentation models.

For the diagnosis and assessment of neurological disorders, single-nucleus RNA sequencing (snRNA-seq) data from human brain samples have revealed valuable insights about regulatory mechanisms that are associated with disease progression. During data mining of RNA-seq data that are associated with Alzheimer's disease (AD) and dementia, conventional deep learning methods generally focus on changes in gene transcript levels, while ignoring graph features of dementia-specific gene networks to a certain degree. It is noted that graph features underlying RNA-seq data have the potential to enhance model performance by analyzing structural changes of AD-specific gene regulatory networks namely AD-GRN. To sufficiently exploit graph features, spatiotemporal graph learning technique has been employed to recognize meaningful patterns that govern AD progression. Using brain snRNA-seq data as the information source, this study has developed an ST-GCN architecture, which has embedded a co-attention network and a nonlinear manifold alignment(NMA) fusion block, to systematically explore abnormal regulatory mechanisms about neurological disorders. The co-attention network aims to obtain compact graph representations by compressing evolving AD-GRNs. The proposed STAD-CoAtt method integrates temporal and graph features, thus constructing joint latent representations of snRNA-seq data. Experiments about two benchmark RNA-seq datasets from ROSMAP and GSE platforms have demonstrated the effectiveness and superiority of the STAD-CoAtt method in assessing neuropathology stages and cognitive dysfunction. By incorporating cross-view interactions, the proposed STAD-CoAtt method has obtained superior performance over established SOTA approaches in AD classification tasks.

Salient object detection in optical remote sensing images (ORSI-SOD) aims to segment salient regions from high-resolution remote sensing images. However, most existing ORSI-SOD methods primarily rely on feature learning of regions to address the issue of blurred edges, while neglecting the potential advantages of similarity calculation in inferring edge clues. To overcome this issue, we propose a novel network with similarity perception termed edge-guided refinement network (ERNet), which distinguishes the edge region of salient objects from coarse to fine through two-stage similarity calculation. Firstly, we introduce the adaptive uncertainty calibration module (AUCM), which utilizes the proposed similarity-based edge perception mechanism (SEPM) to adaptively calibrate edge uncertain information. Secondly, to effectively capture global semantic information, we propose the hierarchical semantic reconstruction module (HSRM), which comprehensively correlates different levels of semantic clues from both internal and external perspectives. Finally, to supplement the local detail of salient objects, we design the dynamic detail interaction module (DDIM), which dynamically extracts detail information of objects at different scales. Extensive experiments on three challenging benchmark datasets have demonstrated the remarkable superiority of our ERNet compared to 30 state-of-the-art models. The source codes will be publicly available at https://github.com/xinwang11/ERNet.

During infectious disease outbreaks, tracking contacted objects is important for suppressing the spread of the virus and using trajectories of moving objects to discover contacted objects is one of effective approaches. Existing algorithms focus on individual contact event discovery but lack the ability to obtain the k-degree contact events. In this paper, we propose efficient k-degree contact pattern mining algorithms that are capable of mining k-degree contact events. The definition of k-degree contact event is first formulated. Based on the definition, a sliding window-based baseline k-degree contact pattern mining algorithm (KCPMA) is presented. To improve the mining efficiency, the sample-point checking strategy and R-tree index are adopted and the optimized mining algorithm (KCPMA+) is proposed. Comprehensive experiments on real datasets demonstrate that the proposed algorithms are effective and efficient in mining k-degree contact events.

Domain generalization (DG) aims to enhance the ability of model learning from source domains to generalize to other unseen domains. Existing gradient-based methods focus on learning better domain-invariant features using gradients from multiple source domains, but do not consider the impact of gradient granularity on model training. In this paper, we rethink how to mitigate the gradient conflicting problem from an optimization perspective. The limitations of existing gradient-based methods are theoretically analyzed in terms of modification ratio and modification frequency, showing that gradient granularity is a key factor in ensuring correct modification of the gradient. To address this issue, a gradient modification method, called CorGrad, is proposed by layering and slicing refinement operations to increase the modification frequency and the modification ratio. It can better reduce domain-specific information so that the model can learn better domain-invariant features. Finally, extensive experiments are conducted to verify the effectiveness of the proposed CorGrad, and the results show that the proposed CorGrad can obtain competitive performance in five DG benchmarks, and an average performance of 60.4% can be obtained on the DomainBed when using ResNet18 as the backbone. The code is publicly available at https://github.com/libzwo/CorGrad.

In recent years, Transformers have been widely applied in human pose estimation by converting image features into token forms as inputs. However, redundant information in images burdens the network and can even negatively impact training as noise. Thus, we propose a coarse-to-fine Transformer called CFPose for efficient human pose estimation. We first extract visual features through a backbone network, then remove redundancy and coarsely crop the human figure via a coarse-grained decision network. Coarse-Grained token (CG token) and keypoint token are fed into a two-stage Transformer, where after the CG encoder, keypoint token sufficiently incorporate coarse features. Only keypoint token and Fine-Grained token (FG token) from a fine-grained decision network that further segments features are input to the FG encoder for training. Finally, keypoint token are mapped to 2D heatmaps for keypoint prediction. Impressively, CFPose reduces computational complexity by 43% while improving accuracy to 76.2% on COCO. It also achieves competitive results on MPII.

Graph learning models have received increasing attention in the computational analysis of single-cell RNA sequencing (scRNA-seq) data. Compared with conventional deep neural networks, graph neural networks and language models have exhibited superior performance by extracting graph-structured data from raw gene count matrices. Established deep neural network-based clustering approaches generally focus on temporal expression patterns while ignoring inherent interactions at gene-level as well as cell-level, which could be regarded as spatial dynamics in single-cell data. Both gene-gene and cell-cell interactions are able to boost the performance of cell type detection, under the framework of multi-view modeling. In this study, spatiotemporal embedding and cell graphs are extracted to capture spatial dynamics at the molecular level. In order to enhance the accuracy of cell type detection, this study proposes the scHybridBERT architecture to conduct multi-view modeling of scRNA-seq data using extracted spatiotemporal patterns. In this scHybridBERT method, graph learning models are employed to deal with cell graphs and the Performer model employs spatiotemporal embeddings. Experimental outcomes about benchmark scRNA-seq datasets indicate that the proposed scHybridBERT method is able to enhance the accuracy of single-cell clustering tasks by integrating spatiotemporal embeddings and cell graphs.

Reconstructing the brightness temperature map from the visibilities in synthetic aperture interferometric radiometers (SAIRs) has been proved to be an ill-posed inverse problem. The regularization methods are crucial to effectively overcome the ill-condition of the inverse problem. This letter presents a maximum a posteriori (MAP) approach for retrieving the accurate brightness temperature map in SAIRs. Furthermore, edge-preserving regularization using a Huber–Markov random field (Huber-MRF) model is used to provide a stable solution and eliminate the oscillation artifacts. Numerical experiment results and quantitative analyses verify the effectiveness of the proposed method.

OBJECTIVE: In recent years, the early diagnosis and treatment of coronary microvascular dysfunction (CMD) have become crucial for preventing coronary heart disease. This paper aims to develop a computer-assisted autonomous diagnosis method for CMD by using ECG features and expert features. APPROACH: Clinical electrocardiogram (ECG), myocardial contrast echocardiography (MCE), and coronary angiography (CAG) are used in our method. Firstly, morphological features, temporal features, and T-wave features of ECG are extracted by multi-channel residual network with BiLSTM (MCResnet-BiLSTM) model and the multi-source T-wave features (MTF) extraction model, respectively. And these features are fused to form ECG features. In addition, the CFR[Formula: see text] is calculated based on the parameters related to the MCE at rest and stress state, and the Angio-IMR is calculated based on CAG. The combination of CFR[Formula: see text] and Angio-IMR is termed as expert features. Furthermore, the hybrid features, fused from the ECG features and the expert features, are input into the multilayer perceptron to implement the identification of CMD. And the weighted sum of the softmax loss and center loss is used as the total loss function for training the classification model, which optimizes the classification ability of the model. RESULT: The proposed method achieved 93.36% accuracy, 94.46% specificity, 92.10% sensitivity, 95.89% precision, and 93.95% F1 score on the clinical dataset of the Second Affiliated Hospital of Zhejiang University. CONCLUSION: The proposed method accurately extracts global ECG features, combines them with expert features to obtain hybrid features, and uses weighted loss to significantly improve diagnostic accuracy. It provides a novel and practical method for the clinical diagnosis of CMD.

Abstract This study proposes a self‐supervised method to reconstruct 3D limbic structures from 2D landmarks extracted from a single view. The loss of self‐consistency can be reduced by performing a random orthogonal projection of the reconstructed 3D structure. Thus, the training process can be self‐supervised by using geometric self‐consistency in the reconstruction–projection–reconstruction process. The self‐supervised network mainly consists of graph convolution and Transformer encoders. This network is called the SS‐Graphformer. By adding a discriminator, the SS‐Graphformer is used as a generator to form a Wasserstein Generative Adversarial Network architecture with a Gradient Penalty to improve the accuracy of the reconstruction. It is experimentally demonstrated that the addition of the 2D structure discriminator can significantly improve the accuracy of the reconstruction.

Abstract Human keypoints detection is different from general detection tasks and requires networks that can learn visual information and anatomical constraints. Since CNN is excellent in extracting texture features of images and transformer can learn the correlation among keypoints well, many CTPNets (CNN+transformer type human pose estimation networks) have emerged. However, these networks are unconcerned with the processing of the features extracted from the CNN and naturally expand only from the channel dimension, ignoring the spatial features in the visual information that are essential for complex detection tasks like pose estimation. So the channel spatial integrated transformer for human pose estimation, termed CSIT, is proposed. The visual information are summarized as texture and spatial information, and a parallel network is used to expand the feature maps in the channel and spatial dimensions to learn texture features and spatial features respectively. In addition, anatomically constrained information is learned by keypoint embeddings. At the end of the network, the 1D vector representation method with more advanced performance and more compatible with transformer's characteristics is used to predict keypoints. Experiments show that CSIT outperforms the mainstream CTPNets on the COCO test‐dev dataset, and also show satisfactory results on the MPII dataset.

Synthetic aperture imaging radiometers (SAIRs) are a powerful tool for high-resolution imaging. The reconstruction process from the visibility function to the brightness temperature map in SAIRs has been demonstrated to be an ill-posed inverse problem. Although the existing regularization methods can effectively overcome the ill-condition, there are still large residual errors and oscillation ripples, especially at the edges of the reconstructed map. In this letter, a reweighted total variation (RTV) method is presented to reconstruct the brightness temperature map in SAIRs and preserve the edge information of the map without windowing. A split Bregman iteration algorithm is used to optimize the RTV regularization model and increase the calculation speed. Numerical simulation experiments are carried out to verify the effectiveness and show the performance of the proposed method.

Age estimation can obtain biological age which is helpful for diagnosis of healthy status and disease. The current age estimation methods do not consider the deep relationships of instances, which limits the potential improvement of the age estimation performance. A hierarchical age estimation mechanism with adaboost-based deep instance weighted fusion is proposed to solve this problem. First, a circulation iterative means clustering (CIMC) algorithm is designed for constructing the hierarchical instance space (multiple-layer instance spaces) and obtain multiple trained base regression models. Second, an adaboost-based deep instance weighted fusion (ADIWF) mechanism is designed to fuse the results of the trained regression models. Several representative age-related datasets are used for verification of the proposed method. The experimental results show that the mean absolute error (MAE) can be decreased apparently, by 6.86% and 1.42% on the Heart and Diabetes Dataset, respectively. Besides, some factors that may influence the performance of the proposed mechanism are studied. In general, the proposed age estimation mechanism is effective. In addition, the mechanism is a kind of framework mechanism, so it can be used to construct different concrete age estimation algorithms, and is helpful for related studies.

Compressed sensing magnetic resonance imaging (CS‐MRI) is an effective way of reducing the sampling data in the k ‐space and shortening the scanning time. Motivated by the high performance of directional tensor product complex tight framelets (TPCTFs) for the image denoising problem, the authors proposed a novel framework that integrated TPCTF for sparse representation and projected fast iterative soft‐thresholding algorithm (pFISTA) for CS‐MRI reconstruction. Furthermore, to take advantage of the cross‐scale relations in the wavelet tree of frame coefficients, the bivariate shrinkage (BS) function with local variance estimation is proposed to shrink thresholding. Such TPCTFs can provide sparse directional representations very well for MR image. When compared with other the state‐of‐the‐art CS‐MRI algorithms in numerical experiments, the proposed TPCTF‐BS method achieves a higher reconstruction quality with respect to image edge preservation and the artefact suppression.