Survival risk prediction is crucial for personalized treatment of gliomas. Medical image foundational models can explore complex medical features, which are critical for prognosis in gliomas. We propose SAM-Risk, which uses a customized SAM-Med3D with multi-view representation fusion and clinical knowledge-based age-grade stratified loss for glioma survival risk prediction. First, to utilize potential interactions between multiple views at an early stage, we design a 3D representation generation module that transforms 1D handcrafted radiomics and clinical features into 3D representations, which are fused with multimodal MRIs through a multi-view representation fusion module. The fused representation is fed into the customized SAM-Med3D, fine-tuned using LoRA and a disparity function to extract survival risk-related features. We design a feature refinement module to explore the inter-channel relationships among the outputs of the fine-tuned SAM-Med3D. Additionally, we propose an age-grade stratified loss based on glioma prognosis standards to make the predicted risk more consistent with clinical prior knowledge. Validated on two publicly available UCSF-PDGM and BraTS2020 datasets, SAM-Risk achieves a C-index of 75.08% and 73.67%, respectively, outperforming several survival risk prediction methods.

Seizure prediction through scalp electroencephalogram (EEG) holds considerable practical potential. The primary challenge faced by existing algorithms lies in the individual heterogeneity, which hinders the generalizability of models to new patients. Additionally, inconsistencies in channel settings across various epilepsy centers further limit the applicability of models to diverse datasets. To address these challenges, we incorporate large language models (LLMs) into EEG analysis and propose a novel seizure prediction method based on LLMs (SPLLM), significantly enhancing both model generalizability and applicability. Specifically, this approach reprograms LLMs by transforming EEG signals into textual representations compatible with LLMs via a single-channel pre-training strategy. The method integrates cross-domain knowledge from both text and EEG data through a cross-attention mechanism, utilizing autoregressive pretrained LLMs to capture the temporal dependencies inherent in EEG signals. Moreover, the cross-domain generalization ability of LLMs alleviates patient heterogeneity, while the single-channel pre-training strategy enables the model to adapt to diverse channel settings. On two public datasets and one private dataset, SPLLM increases the average AUC by 8.2%, and the average balanced accuracy by 8.4% compared to existing methods. Experimental results demonstrate that the proposed method not only enhances cross-patient prediction accuracy but also adapts to data from different datasets, offering a scalable solution for the clinical application of seizure prediction.

With the rapid development of globalization and technology, the industrial structure has undergone profound changes and market competition is becoming increasingly fierce. In order to enhance their competitive advantage, enterprises are integrating resources through supply chain systems (SCS) and establishing strategic partnerships to achieve rapid market response and optimized resource allocation. Artificial Intelligence (AI) -based Internet of Things (IoT) has brought unprecedented changes to supply chain systems. AIoT not only improves the transparency and efficiency of the supply chain, but also significantly reduces carbon emissions, making a positive contribution to green and sustainable development. However, with the widespread application of AIoT in SCS, its security issues have become increasingly prominent, posing a serious threat to the stable operation of the supply chain. Therefore, this article proposes a secure and efficient authentication protocol for supply chain systems in AIoT. This protocol implements user authentication, ensures forward security of session key and guarantees secure data transmission. Through security analysis, this article proves that the protocol can resist various known attacks. In addition, through performance analysis, the protocol has low overhead and can meet the efficiency requirements of SCS.

Wireless sensor networks (WSNs) comprised of resource-limited devices face challenges related to network congestion and security threats. In this regard, this study introduces a groundbreaking approach called P-tensor product Fourier optical speckle-based compressive sensing (PTP-FOSCS) for image encryption. Primarily, to augment the scheme’s sensitivity to plaintext information, the parameters for the scrambling encryption were derived using the original image’s SHA-256 hash. Subsequently, the measurement matrix of the compressive sensing (CS) was constructed by capitalizing on the intrinsic randomness offered by Fourier optical speckle. The incorporation of P-tensor product (PTP) theory played a pivotal role by circumventing the conventional hurdle of dimension matching in matrix multiplication, thereby greatly improving the scheme’s flexibility and reducing its storage burden. Furthermore, the optical image encryption offers expeditious and parallel data processing capabilities, making it suitable for integration with CS for encrypting two images simultaneously to improved security and enhanced efficiency within the encryption system. Ultimately, the ciphertext image was discreetly embedded within a carrier image utilizing information hiding technology, which effectively masked the presence of encrypted information, thereby preventing visual suspicion from potential attackers. Empirical validation and comprehensive data corroborate the feasibility and security of the proposed methodology, which has a total key space of approximately 2572. It effectively withstands BFA, statistical attacks, CPA, among others. Furthermore, the novel measurement matrix significantly reduces data storage requirements and achieves higher-quality image reconstruction compared to classical alternatives applied in CS.

Generating biomedical hypotheses is a difficult task as it requires uncovering the implicit associations between massive scientific terms from a large body of published literature. A recent line of Hypothesis Generation (HG) approaches - temporal graph-based approaches - have shown great success in modeling temporal evolution of term-pair relationships. However, these approaches model the temporal evolution of each term or term-pair with Recurrent Neural Network (RNN) independently, which neglects the rich covariation among all terms or term-pairs while ignoring direct dependencies between any two timesteps in a temporal sequence. To address this problem, we propose a Spatiotemporal Transformer-based Hypothesis Generation (STHG) method to interleave spatial covariation and temporal progression in a unified framework for constructing direct connections between any two term-pairs while modeling the temporal relevance between any two timesteps. Experiments on three biomedical relationship datasets show that STHG outperforms the state-of-the-art methods.

This letter proposes a two-points non-iterative IpDFT algorithm for parameter estimation of the damped real-valued sinusoidal signal, which is named as the I2pNDFT. Both long- and short- range leakages are compensated to estimate the parameters accurately. Simulation results prove the effectiveness of our methodmagenta, compared with other IpDFT methods.