Pneumonia is an acute respiratory infection, posing a serious threat to health and lives. Lung ultrasound (LUS), as a non-invasive and rapid imaging technique, can monitor real-time changes in lung, providing valuable assistance in clinical diagnosis. However, most LUS studies are limited to frame-level analysis and ignore respiratory cycle changes, leading to diagnostic errors. To address these problems, we propose a cross-dimensional spatial-temporal feature integration model for LUS video analysis. Specifically, the sliding window and feature difference analysis are first utilized to preprocess the original LUS videos for eliminating invalid and highly similar frames and implementing abstract video. Subsequently, a cross-dimensional feature fusion backbone integrates an improved temporal-C3D network and a self-designed recursive inception-meet-transformer (IMT) network to extract features from different dimensions for fusion. Thereby, comprehensive features can be obtained for characterizing LUS videos. Finally, the Longformer is employed to analyze the temporal dependencies of cross-dimensional features, supplemented by a classification head for evaluating LUS videos. 3018 LUS video clips were collected from 119 patients in three hospitals for the evaluation of the proposed LUS video scoring model. By dividing at the patient level, the training and testing set consist of 2652 clips from 104 patients and 366 clips from 15 patients, respectively. Experimental results of 5-fold cross validation demonstrate that the proposed model achieves outstanding scoring performance, with an accuracy, precision, recall, specificity, F1-score, and AUC of $91.78~\pm ~0.52$ %, $92.19~\pm ~0.76$ %, $91.81~\pm ~0.62$ %, $97.17~\pm ~0.20$ %, $91.94~\pm ~0.44$ %, and $97.83~\pm ~0.19$ %, respectively. The independent testing set also shows the superior generalization capability with a scoring accuracy of $87.65~\pm ~1.12$ %. Moreover, ablation studies confirm that each designed module contributes significantly to the model's performance, and comparative experiments further confirm the superiority of the proposed model compared to previous models. These robust findings highlight the proposed LUS video scoring model's strong potential for clinical deployment.

The propagation of acoustic waves through bone remains a longstanding challenge in transcranial ultrasound imaging. As a highly scattering medium, the skull causes significant distortions in the ultrasonic wavefield, introducing complex aberrations that hinder precise image reconstruction. Conventional delay-and-sum (DAS) algorithms, which process pixels independently, fail to account for inter-pixel relationships, limiting their ability to correct such distortions. To address this issue, we propose a Pixel-Responsive Optimization (PRO) Beamforming Method that leverages backscattered signals from compound plane waves. By constructing a pixel-response matrix and simulating a virtual acoustic lens, PRO isolates and aligns distorted fields with reference phases to restore near-ideal propagation. Experiments on bovine femur plates and a human skull demonstrate improved image resolution, recovery of submerged signals, and artifact suppression. PRO achieves up to a 90% improvement in full-width at half-maximum (FWHM) compared to DAS, requiring no prior assumptions and showing strong generalizability in complex scenarios through bone. This advancement holds promise for future in vivo transcranial brain imaging applications.

Early prognostic prediction is crucial for determining appropriate clinical interventions. Previous single-omics models had limitations, such as high contingency and overlooking complex physical conditions. In this paper, we introduced multi-omics graph knowledge representation to predict in-hospital outcomes for pneumonia patients. This method utilizes CT imaging and three non-imaging omics information, and explores a knowledge graph for modeling multi-omics relations to enhance the overall information representation. For imaging omics, a multichannel pyramidal recursive MLP and Longformer-based 3D deep learning module was developed to extract depth features in lung window, while radiomics features were simultaneously extracted in both lung and mediastinal windows. Non-imaging omics involved the adoption of laboratory, microbial, and clinical indices to complement the patient's physical condition. Following feature screening, the similarity fusion network and graph convolutional network (GCN) were employed to determine omics similarity and provide prognostic prediction. The results of comparative experiments and generalization validation demonstrat that the proposed multi-omics GCN-based prediction model has good robustness and outperformed previous single-type omics, classical machine learning, and previous deep learning methods. Thus, the proposed multi-omics graph knowledge representation model enhances early prognostic prediction performance in pneumonia, facilitating a comprehensive assessment of disease severity and timely intervention for high-risk patients.

Multilayered composite media are widely used in various industries, and the presence of small defects like voids or pores could lead to reduced mechanical properties. Ultrasound imaging with full-matrix capture (FMC) is a well-established modality to detect the small defect. However, the sequential emission of probe element combined with full-matrix reception results in heavy computational complexity and low frame rates, limiting real-time implementation. Furthermore, conventional FMC methods are only suitable for single-layer media and will be inaccurate for multilayered structures. To overcome these limitations, an efficient approach called spectrum-domain plane wave imaging (SD-PWI) was proposed to imaging multilayered media. By modifying the exploding reflector model to be applicable to PWI in multilayered imaging scenarios, the received wavefield was accurately extrapolated to the top of the objective layer, and the entire layer of interest was successfully reconstructed, employing fast Fourier transform based beamforming. Experimental findings demonstrated the effectiveness of SD-PWI. Compared with two classical FMC approaches, such as ray-tracing synthetic aperture and extended phase shift migration, multiangle compounded SD-PWI achieved improved image quality and higher efficiency. The side-drilled holes with diameters of 1–2.5 mm can be effectively detected, showcasing its ability to diagnose minor defects. Moreover, SD-PWI achieved a frame rate of 15 Hz for 3-layer medium imaging using a 192-element phased array. It is demonstrated that the proposed SD-PWI method is an accurate and efficient modality to studying multilayered media in industrial applications.

Autonomous tracking of suspicious unmanned aerial vehicles (UAVs) by legitimate monitoring UAVs (or monitors) can be crucial to public safety and security. It is non-trivial to optimize the trajectory of a monitor while conceiving its monitoring intention, due to typically non-convex propulsion and thrust power functions. This article presents a novel framework to jointly optimize the propulsion and thrust powers, as well as the 3D trajectory of a solar-powered monitor which conducts covert, video-based, UAV-on-UAV tracking and surveillance. A multi-objective problem is formulated to minimize the energy consumption of the monitor and maximize a weighted sum of distance keeping and altitude changing, which measures the disguising of the monitor. Based on the practical power models of the UAV propulsion, thrust and hovering, and the model of the harvested solar power, the problem is non-convex and intangible for existing solvers. We convexify the propulsion power by variable substitution, and linearize the solar power. With successive convex approximation, the resultant problem is then transformed with tightened constraints and efficiently solved by the proximal difference-of-convex algorithm with extrapolation in polynomial time. The proposed scheme can be also applied online. Extensive simulations corroborate the merits of the scheme, as compared to baseline schemes with partial or no disguising.