Objective. 4D-CBCT provides phase-resolved images valuable for radiomics analysis for outcome prediction throughout treatment courses. However, 4D-CBCT suffers from streak artifacts caused by under-sampling, which severely degrades the accuracy of radiomic features. Previously we developed group-patient-trained deep learning methods to enhance the 4D-CBCT quality for radiomics analysis, which was not optimized for individual patients. In this study, a patient-specific model was developed to further improve the accuracy of 4D-CBCT based radiomics analysis for individual patients. Approach. This patient-specific model was trained with intra-patient data. Specifically, patient planning 4D-CT was augmented through image translation, rotation, and deformation to generate 305 CT volumes from 10 volumes to simulate possible patient positions during the onboard image acquisition. 72 projections were simulated from 4D-CT for each phase and were used to reconstruct 4D-CBCT using FDK back-projection algorithm. The patient-specific model was trained using these 305 paired sets of patient-specific 4D-CT and 4D-CBCT data to enhance the 4D-CBCT image to match with 4D-CT images as ground truth. For model testing, 4D-CBCT were simulated from a separate set of 4D-CT scan images acquired from the same patient and were then enhanced by this patient-specific model. Radiomics features were then extracted from the testing 4D-CT, 4D-CBCT, and enhanced 4D-CBCT image sets for comparison. The patient-specific model was tested using 4 lung-SBRT patients’ data and compared with the performance of the group-based model. The impact of model dimensionality, region of interest (ROI) selection, and loss function on the model accuracy was also investigated. Main results. Compared with a group-based model, the patient-specific training model further improved the accuracy of radiomic features, especially for features with large errors in the group-based model. For example, the 3D whole-body and ROI loss-based patient-specific model reduces the errors of the first-order median feature by 83.67%, the wavelet LLL feature maximum by 91.98%, and the wavelet HLL skewness feature by 15.0% on average for the four patients tested. In addition, the patient-specific models with different dimensionality (2D versus 3D) or loss functions (L1 versus L1 + VGG + GAN) achieved comparable results for improving the radiomics accuracy. Using whole-body or whole-body+ROI L1 loss for the model achieved better results than using the ROI L1 loss alone as the loss function. Significance. This study demonstrated that the patient-specific model is more effective than the group-based model on improving the accuracy of the 4D-CBCT radiomic features analysis, which could potentially improve the precision for outcome prediction in radiotherapy.

Purpose. To investigate the impact of 4D-CBCT image quality on radiomic analysis and the efficacy of using deep learning based image enhancement to improve the accuracy of radiomic features of 4D-CBCT. Material and Methods. In this study, 4D-CT data from 16 lung cancer patients were obtained. Digitally reconstructed radiographs (DRRs) were simulated from the 4D-CT, and then used to reconstruct 4D CBCT using the conventional FDK (Feldkamp et al 1984 J. Opt. Soc. Am . A 1 612–9) algorithm. Different projection numbers (i.e. 72, 120, 144, 180) and projection angle distributions (i.e. evenly distributed and unevenly distributed using angles from real 4D-CBCT scans) were simulated to generate the corresponding 4D-CBCT. A deep learning model (TecoGAN) was trained on 10 patients and validated on 3 patients to enhance the 4D-CBCT image quality to match with the corresponding ground-truth 4D-CT. The remaining 3 patients with different tumor sizes were used for testing. The radiomic features in 6 different categories, including histogram, GLCM, GLRLM, GLSZM, NGTDM, and wavelet, were extracted from the gross tumor volumes of each phase of original 4D-CBCT, enhanced 4D-CBCT, and 4D-CT. The radiomic features in 4D-CT were used as the ground-truth to evaluate the errors of the radiomic features in the original 4D-CBCT and enhanced 4D-CBCT. Errors in the original 4D-CBCT demonstrated the impact of image quality on radiomic features. Comparison between errors in the original 4D-CBCT and enhanced 4D-CBCT demonstrated the efficacy of using deep learning to improve the radiomic feature accuracy. Results. 4D-CBCT image quality can substantially affect the accuracy of the radiomic features, and the degree of impact is feature-dependent. The deep learning model was able to enhance the anatomical details and edge information in the 4D-CBCT as well as removing other image artifacts. This enhancement of image quality resulted in reduced errors for most radiomic features. The average reduction of radiomics errors for 3 patients are 20.0%, 31.4%, 36.7%, 50.0%, 33.6% and 11.3% for histogram, GLCM, GLRLM, GLSZM, NGTDM and Wavelet features. And the error reduction was more significant for patients with larger tumors. The findings were consistent across different respiratory phases, projection numbers, and angle distributions. Conclusions. The study demonstrated that 4D-CBCT image quality has a significant impact on the radiomic analysis. The deep learning-based augmentation technique proved to be an effective approach to enhance 4D-CBCT image quality to improve the accuracy of radiomic analysis.

We devise a cutting-edge near-field terahertz (THz) covert communication strategy with noise uncertainty where the beam is focused at a specific location, defined by both distance and direction. Leveraging unique near-field properties, the strategy combats eavesdroppers by increasing the capacity gap between legitimate and eavesdropping channels. We first develop a novel performance analytical framework for the near-field THz covert communication system, based on which we derive closed-form expressions for key performance metrics and thresholds, including the average covert probability, covert outage probability, covert rate, optimal detection threshold, and received power threshold of the eavesdropper. To further improve the secrecy performance, we design a new true-time-delay (TTD)-based piecewise approximation hybrid beamforming scheme for maximizing the covert rate, while effectively mitigating the negative impact caused by the beam split effect. Our numerical results demonstrate that the near-field THz covert communication strategy effectively combats eavesdroppers at all distances in the sector covering the main beam, demonstrating its practical significance for future wireless networks.

This article addresses trajectory optimization, resource allocation, and access management in a multi-uncrewed aerial vehicle (UAV) assisted collaborative mobile edge computing (MEC) network for the low-altitude economy. In the network, UAVs collaborate to compute offloaded tasks and improve fairness among time-varying UAV battery levels. The objective of this article is to maximize the network utility defined by the size of successful offloaded tasks, the fairness among the user equipments (UPs), and the processing time and the energy consumption of the UAVs. In particular, we consider the time-varying UAV battery model, which affects the energy cost weights of the UAVs. Therefore, we propose a heuristic optimization framework which integrates the utility partitioning two-stage matching (UPTSM) algorithm and the variables constrained whale optimization algorithm (VC-WOA). The UPTSM algorithm decomposes the original optimization problem into two subproblems and models them as the bipartite graph matching problems. The VC-WOA achieves the search for legal solutions by limiting the variables which violate the task processing time constraints. Simulation results demonstrate the effectiveness of the proposed heuristic optimization framework in speeding up the convergence and improving the fairness among the UAV battery levels.

This paper proposes a channel decomposition method and a novel beamforming architecture for line-of-sight (LoS) multi-input multi-output (MIMO) systems with dual continuous apertures (CAPs). Specifically, we develop a three-dimensional (3D) dual-CAP geometric model through orthogonal basis projection, establishing a unified electromagnetic analysis framework for arbitrarily oriented non-coplanar CAPs and enabling consistent 3D wave propagation modeling. Building on this model, we derive the closed-form expression for the effective degrees of freedom (EDoF) of the dual-CAP LoS MIMO system by analyzing spherical wave phase differences via sampling theory. This explicitly connects EDoF to wavelength, propagation distance, and angular rotation. Our proposed channel decomposition method decouples dual-CAP LoS MIMO channels into multiple independent SISO subchannels, which enables a novel beamforming architecture. We implement this architecture through a wavefront degrees of freedom orthogonal subchannel decomposition (WDOSD) algorithm to maximize the achievable rate of the dual-CAP LoS MIMO system. Numerical results demonstrate that: i) both component-wise EDoF and total EDoF can be accurately obtained using our proposed closed-form expressions; ii) under varying transmitter CAP sizes with fixed power, our WDOSD algorithm achieves up to three times performance improvement over the minimum mean-squared error (MMSE) algorithm; and iii) under varying communication distance with fixed angle, the WDOSD algorithm achieves up to two times performance improvement over the MMSE algorithm.

Diverse and complex wireless interference is one of the most critical threats to modern wireless communication systems. The continuous shift of wireless interference toward higher frequency and wider bandwidth imposes sampling-rate limitations on wireless interference identification (WII). Existing compressed sensing-based WII methods designed for undersampling scenarios suffer from high-complexity signal reconstruction and low identification accuracy caused by fixed sampling strategies. To address these challenges, we propose a multi-domain fusion model which employs domain-specific hybrid sampling to extract interference features for multi-attribute WII without signal reconstruction. Given the respective classification advantages of random and uniform undersampling in time-domain sequences and time–frequency images, this paper proposes a dual-branch architecture to exploit their joint benefits. Specifically, we propose a learnable sparse sampler combined with a Transformer to extract time-domain features in the random undersampling branch. We further prove that the Restricted Isometry Property (RIP)-compliant undersampling largely preserves the feature class discriminability, which motivates the introduction of the RIP loss. In parallel, we propose a multi-scale feature extraction module and a cross-fusion module for dimensionality reduction in the uniform undersampling branch. Subsequently, an attribute correlation-driven graph convolution network is introduced to classify the fused features from both branches, further improving WII performance. Finally, we propose an adaptive multi-domain binary cross-entropy loss and prove that the optimal weight of the RIP loss effectively mitigates gradient conflicts. Experimental results show that the proposed model improves precision by 25.1% over the state-of-the-art, while maintaining effective multi-attribute WII performance at undersampling ratios up to 8.