The fusion of magnetic resonance imaging and positron emission tomography can combine biological anatomical information and physiological metabolic information, which is of great significance for the clinical diagnosis and localization of lesions. In this paper, we propose a novel adaptive linear fusion method for multi-dimensional features of brain magnetic resonance and positron emission tomography images based on a convolutional neural network, termed as MdAFuse. First, in the feature extraction stage, three-dimensional feature extraction modules are constructed to extract coarse, fine, and multi-scale information features from the source image. Second, at the fusion stage, the affine mapping function of multi-dimensional features is established to maintain a constant geometric relationship between the features, which can effectively utilize structural information from a feature map to achieve a better reconstruction effect. Furthermore, our MdAFuse comprises a key feature visualization enhancement algorithm designed to observe the dynamic growth of brain lesions, which can facilitate the early diagnosis and treatment of brain tumors. Extensive experimental results demonstrate that our method is superior to existing fusion methods in terms of visual perception and nine kinds of objective image fusion metrics. Specifically, in the results of MR-PET fusion, the SSIM (Structural Similarity) and VIF (Visual Information Fidelity) metrics show improvements of 5.61% and 13.76%, respectively, compared to the current state-of-the-art algorithm. Our code is publicly available at: https://github.com/22385wjy/MdAFuse.

Adversarial attack on point clouds plays a vital role in evaluating and improving the adversarial robustness of 3D deep learning models. Current attack methods are mainly applied by point perturbation in a non-manifold manner. In this paper, we formulate a novel manifold attack, which deforms the underlying 2-manifold surfaces via parameter plane stretching to generate adversarial point clouds. First, we represent the mapping between the parameter plane and underlying surface using generative-based networks. Second, the stretching is learned in the 2D parameter domain such that the generated 3D point cloud fools a pretrained classifier with minimal geometric distortion. Extensive experiments show that adversarial point clouds generated by manifold attack are smooth, undefendable and transferable, and outperform those samples generated by the state-of-the-art non-manifold ones.

Federated weakly supervised video anomaly detection represents a significant advancement in privacy-preserving collaborative learning, enabling distributed clients to train anomaly detectors using only video-level annotations. However, the inherent challenges of optimizing noisy representation with coarse-grained labels often result in substantial local model errors, which are exacerbated during federated aggregation, particularly in heterogeneous scenarios. To address these limitations, we propose a novel dual-detector framework incorporating adaptive dynamic recursive mapping, which significantly enhances local model accuracy and robustness against representation noise. Our framework integrates two complementary components: a channel-averaged anomaly detector and a channel-statistical anomaly detector, which interact through cross-detector adaptive decision parameters to enable iterative optimization and stable anomaly scoring across all instances. Furthermore, we introduce the scene-similarity adaptive local aggregation algorithm, which dynamically aggregates and learns private models based on scene similarity, thereby enhancing generalization capabilities across diverse scenarios. Extensive experiments conducted on the NVIDIA Jetson AGX Xavier platform using the ShanghaiTech and UBnormal datasets demonstrate the superior performance of our approach in both centralized and federated settings. Notably, in federated environments, our method achieves remarkable improvements of 6.2% and 12.3% in AUC compared to state-of-the-art methods, underscoring its effectiveness in resource-constrained scenarios and its potential for real-world applications in distributed video surveillance systems.

Premature ovarian insufficiency (POI) is a reproductive endocrine disorder characterized by infertility and perimenopausal syndrome, with a highly heterogeneous genetic etiology and its mechanism is not fully understood. Therefore, we utilized Oxford Nanopore Technology (ONT) for the first time to characterize the full-length transcript profile, and revealed biomarkers, pathway and molecular mechanisms for POI by bioinformatics analysis and machine learning. Ultimately, we identified 272 differentially expressed genes, 858 core genes, and 25 hub genes by analysis of differential expression, gene set enrichment, and protein–protein interactions. Seven candidate genes were identified based on the intersection features of the random forest and Boruta algorithm. qRT-PCR results indicated that COX5A, UQCRFS1, LCK, RPS2 and EIF5A exhibited consistent expression trends with sequencing data and have potential as biomarkers. Additionally, GSEA analysis revealed that the pathophysiology of POI is closely associated with inhibition of the PI3K-AKT pathway, oxidative phosphorylation and DNA damage repair, as well as activation of inflammatory and apoptotic pathways. Furthermore, we emphasize that downregulation of respiratory chain enzyme complex subunits and inhibition of oxidative phosphorylation pathways play crucial roles in the pathophysiology of POI. In conclusion, our utilization of long-read sequencing has refined the annotation information within the POI transcriptional profile. This valuable data provides novel insights for further exploration into molecular regulatory networks and potential biomarkers associated with POI.