The increasing deployment of digital healthcare systems has led to the continuous transmission of highly sensitive patient data, raising urgent concerns about data leakage in high-noise, high-loss, and dynamically changing. Existing privacy-preservation techniques often struggle to provide robustness, low overhead, and real-time responsiveness under high jitter and packet loss, limiting their effectiveness in rapid detection and accurate tracing of leaks. To address these challenges, we propose a Reinforcement Learning-Driven Joint Watermarking Framework (RLDJ-W). First, it utilizes a reinforcement learning strategy to adaptively modulate the watermark embedding interval, ensuring both invisibility and enhancing the watermark’s survivability in harsh channels. Then, it leverages Bi-LSTM to capture and model multi-granularity time-series features of network flows, thereby dynamically evaluating the invisibility of the watermark flows. Finally, a high-performance decoding network based on MLP is designed to achieve efficient and accurate watermark information extraction. Experimental results demonstrate that the watermarking capacity of RLDJ-W achieves 2.25 bit/s, requiring only an average of 5.88 packets per bit of watermark. It also maintains over 85% detection accuracy even under 100ms delay jitter and 40% packet loss, consistently outperforming state-of-the-art baselines.

The study of the nicotine addiction mechanism is of great significance in both nicotine withdrawal and brain science. The detection of addiction-related brain circuitry using functional magnetic resonance imaging (fMRI) is a critical step in studying this mechanism. However, it is challenging to accurately estimate addiction-related brain circuitry due to the low signal-to-noise ratio of fMRI and the issue of small sample size. In this work, a graph diffusion-infused adversarial learning (GDAL) network is proposed to capture addiction-related brain circuitry accurately. The GDAL combines the graph convolution method with the diffusion model so that the model can fully capture addiction-related brain circuitry in non-Euclidean space. The diffusion reconstruction module (DRM) is designed to reconstruct the brain network to maintain the consistency of sample distribution in the latent space so that the brain circuitry can be detected more accurately. The proposed model reduces the search space by improving the conditional guidance of the DRM so that the model can better understand the latent distribution for the issue of small sample size. The experimental results demonstrate the effectiveness of the proposed method.

Vehicle edge computing (VEC) can effectively meet the demand for computing resources in autonomous driving. However, complex resource constraints exist in the practical application of VEC, making offloading tasks a key challenge. Traditional scheduling algorithms are usually optimized only for latency and cost and can handle only a small number of tasks; however, they cannot handle real-world intensive vehicle-road cooperation scenarios involving many tasks. Thus, this article constructs a large-scale multiobjective computing offloading optimization model that comprehensively considers latency, energy consumption, load balancing, and resource utilization. To improve the offloading performance of VEC, we propose a large-scale multiobjective optimization algorithm with hybrid directed sampling and adaptive offspring generation (LMOEA-HDGS). The algorithm can generate adaptive offspring by sampling in two types of search directions in the decision space and can adapt to the complex shape of the Pareto front while balancing diversity and convergence. The experimental results show that the proposed algorithm can effectively optimize the task offloading problem of VEC in an intensive vehicle-road cooperation scenario.

This paper explores the computation enhancement problem in an intelligent reflecting surface (IRS) enabled wireless powered mobile edge computing system serving the intelligent transportation relying on powerful computational support. Initially, in the downlink, the base station (BS) with edge server transmits energy signals to the battery-powered roadside units (RSUs) with computing capabilities, which are grouped into distinct clusters. Subsequently, RSUs leverage the harvested energy for local computing and offloading their tasks to the BS by using a hybrid rate splitting multiple access (RSMA) and time division multiple access (TDMA) strategy. Finally, the computed outcomes from the edge server are transmitted for integration with the computations carried out locally at the RSUs. The objective is to maximize the minimal computation rate of RSU clusters, where the transmit power of the BS and RSUs, the downlink and uplink beamforming of the IRS, the CPU frequency of the RSUs, and the time slot assignment are jointly optimized. To address the bottleneck issues constraining computation rate, this paper proposes an iterative algorithm that combines sequential rank-one constraint relaxation and block coordinate descent methods. Ultimately, the simulation results confirm the effectiveness of the proposed algorithm in enhancing the weakest link constraining the system computation rate when contrasted with the baseline algorithms.

Effective connectivity estimation plays a crucial role in understanding the interactions and information flow between different brain regions. However, the functional time series used for estimating effective connectivity is derived from certain software, which may lead to large computing errors because of different parameter settings and degrade the ability to model complex causal relationships between brain regions. In this paper, a brain diffuser with hierarchical transformer (BDHT) is proposed to estimate effective connectivity for mild cognitive impairment (MCI) analysis. To our best knowledge, the proposed brain diffuser is the first generative model to apply diffusion models to the application of generating and analyzing multimodal brain networks. Specifically, the BDHT leverages structural connectivity to guide the reverse processes in an efficient way. It makes the denoising process more reliable and guarantees effective connectivity estimation accuracy. To improve denoising quality, the hierarchical denoising transformer is designed to learn multi-scale features in topological space. By stacking the multi-head attention and graph convolutional network, the graph convolutional transformer (GraphConformer) module is devised to enhance structure-function complementarity and improve the ability in noise estimation. Experimental evaluations of the denoising diffusion model demonstrate its effectiveness in estimating effective connectivity. The proposed model achieves superior performance in terms of accuracy and robustness compared to existing approaches. Moreover, the proposed model can identify altered directional connections and provide a comprehensive understanding of parthenogenesis for MCI treatment.Note to Practitioners—Diagnosing MCI allows for timely intervention and treatment measures to potentially slow down or even halt further cognitive decline. Exploring causal relations between brain regions enables a better understanding of pathogenic mechanisms and the development of effective biomarkers for MCI diagnosis. The current practice heavily relies on the software to analyze MCI causality, leading to large computing errors and degrading MCI analysis performance because of different parameter settings. This work aims to provide a unified framework for the estimation of brain effective connectivity using generative artificial intelligence. Due to their ability to generate high-quality samples, diffusion models have demonstrated remarkable performance in cross-modal medical image synthesis through iterative denoising processes. Our model provides a new insight into how to transform four-dimensional functional magnetic resonance imaging into effective connectivity without relying on software toolkits. The proposed model achieves good disease prediction performance and identifies altered directional connections that may be potential biomarkers for MCI treatment. Our work enables practitioners to develop deep learning model-based medical tools to assist clinicians with disease diagnosis and pathological analysis in an efficient way. Our work can also extend to the intelligently assisted diagnosis of other neurological diseases.

Underwater imaging grapples with challenges from light-water interactions, leading to color distortions and reduced clarity. In response to these challenges, we propose a novel Color Balance Prior Guided Hybrid Sense Underwater Image Restoration framework (GuidedHybSensUIR). This framework operates on multiple scales, employing the proposed Detail Restorer module to restore low-level detailed features at finer scales and utilizing the proposed Feature Contextualizer module to capture long-range contextual relations of high-level general features at a broader scale. The hybridization of these different scales of sensing results effectively addresses color casts and restores blurry details. In order to effectively point out the evolutionary direction for the model, we propose a novel Color Balance Prior as a strong guide in the feature contextualization step and as a weak guide in the final decoding phase. We construct a comprehensive benchmark using paired training data from three real-world underwater datasets and evaluate on six test sets, including three paired and three unpaired, sourced from four real-world underwater datasets. Subsequently, we tested 14 traditional and retrained 23 deep learning existing underwater image restoration methods on this benchmark, obtaining metric results for each approach. This effort aims to furnish a valuable benchmarking dataset for standard basis for comparison. The extensive experiment results demonstrate that our method outperforms 37 other state-of-the-art methods overall on various benchmark datasets and metrics, despite not achieving the best results in certain individual cases. The code and dataset are available at https://github.com/CXH-Research/GuidedHybSensUIR.

Accurate segmentation of blood vessels is essential for various clinical assessments and postoperative analyses. However, the inherent challenges of vascular imaging-such as sparsity, fine granularity, low contrast, data distribution variability, and the critical need for preserving topological integrity-make generalized vessel segmentation particularly complex. While specialized segmentation methods have been developed for specific anatomical regions, their over-reliance on tailored models hinders broader applicability and generalization. General-purpose segmentation models introduced in medical imaging often fail to address critical vascular characteristics, including the connectivity of segmentation results. In this study, we propose OVS-Net, an optimized vessel segmentation framework designed to generalize across diverse vessel structures and imaging modalities. It introduces a dual-branch architecture design for improving small vessel segmentation and a morphology-aware correction module to preserve vascular topology and connectivity. We compiled a comprehensive multi-modality dataset from 17 datasets to train and benchmark the proposed OVS-Net against 6 SAM-based methods and 17 expert models under various conditions. The results demonstrate that our approach achieves superior segmentation accuracy, generalization, and a 34.6% improvement in connectivity, underscoring its potential for clinical applications. The code and dataset information are available at https://github.com/Hk416mod2/OVS-Net.

The rapid expansion of intelligent vehicles in 6G networks has intensified the demand for real-time task processing. However, traditional cloud-edge collaboration models for large-scale vehicle task offloading are increasingly inadequate to address the growing complexity and demands. To address this challenge, we propose a unified cloud-edge-end collaborative vehicle task offloading multiobjective optimization model for large-scale vehicle task offloading, which simultaneously considers four optimization objectives: latency, energy consumption, load balancing and quality of service (QoS). To solve the large-scale multiobjective optimization problem, we propose a large-scale multiobjective evolutionary algorithm based on problem transformation and bidirectional vectors (LSMOEA-PTBV). Experiments in a simulated 6G vehicular network demonstrate that LSMOEA-PTBV outperforms state-of-the-art methods. Our work enhances the end-user experience, meets the increasingly complex demands of modern applications, and advances the development of integrated sensing and computing systems and intelligent transportation systems in the 6G era.

Intelligent reflecting surface (IRS) and rate-splitting multiple access (RSMA) technologies are at the forefront of enhancing spectrum and energy efficiency in the next generation multi-antenna communication systems. This paper explores a RSMA system with multiple IRSs, and proposes two purpose-driven scheduling schemes, i.e., the exhaustive IRS-aided (EIA) and opportunistic IRS-aided (OIA) schemes. The aim is to optimize the system weighted energy efficiency (EE) under the above two schemes, respectively. Specifically, the Dinkelbach, branch and bound, successive convex approximation, and the semidefinite relaxation methods are exploited within the alternating optimization framework to obtain effective solutions to the considered problems. The numerical findings indicate that the EIA scheme exhibits better performance compared to the OIA scheme in diverse scenarios when considering the weighted EE, and the proposed algorithm demonstrates superior performance in comparison to the baseline algorithms.

Hybrid motor imagery brain-computer interfaces (MI-BCIs), which integrate both electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) signals, outperform those based solely on EEG. However, simultaneously recording EEG and fNIRS signals is highly challenging due to the difficulty of colocating both types of sensors on the same scalp surface. This physical constraint complicates the acquisition of high-quality hybrid signals, thereby limiting the widespread application of hybrid MI-BCIs. To address this issue, this study proposes the spatio-temporal controlled diffusion model (SCDM) as a framework for cross-modal generation from EEG to fNIRS. The model utilizes two core modules, the spatial cross-modal generation (SCG) module and the multi-scale temporal representation (MTR) module, which adaptively learn the respective latent temporal and spatial representations of both signals in a unified representation space. The SCG module further maps EEG representations to fNIRS representations by leveraging their spatial relationships. Experimental results show high similarity between synthetic and real fNIRS signals. The joint classification performance of EEG and synthetic fNIRS signals is comparable to or even better than that of EEG with real fNIRS signals. Furthermore, the synthetic signals exhibit similar spatio-temporal features to real signals while preserving spatial relationships with EEG signals. To our knowledge, it is the first work that an end-to-end framework is proposed to achieve cross-modal generation from EEG to fNIRS. Experimental results suggest that the SCDM may represent a promising paradigm for the acquisition of hybrid EEG-fNIRS signals in MI-BCI systems.

Brain disorder diagnosis via resting-state functional magnetic resonance imaging (rs-fMRI) is usually limited due to the complex imaging features and sample size. For brain disorder diagnosis, the graph convolutional network (GCN) has achieved remarkable success by capturing interactions between individuals and the population. However, there are mainly three limitations: 1) The previous GCN approaches consider the non-imaging information in edge construction but ignore the sensitivity differences of features to non-imaging information. 2) The previous GCN approaches solely focus on establishing interactions between subjects (i.e., individuals and the population), disregarding the essential relationship between features. 3) Multisite data increase the sample size to help classifier training, but the inter-site heterogeneity limits the performance to some extent. This paper proposes a knowledge-aware multisite adaptive graph Transformer to address the above problems. First, we evaluate the sensitivity of features to each piece of non-imaging information, and then construct feature-sensitive and feature-insensitive subgraphs. Second, after fusing the above subgraphs, we integrate a Transformer module to capture the intrinsic relationship between features. Third, we design a domain adaptive GCN using multiple loss function terms to relieve data heterogeneity and to produce the final classification results. Last, the proposed framework is validated on two brain disorder diagnostic tasks. Experimental results show that the proposed framework can achieve state-of-the-art performance.

Multi-modal neuroimaging analysis is crucial for a comprehensive understanding of brain function and pathology, as it allows for the integration of different imaging techniques, thus overcoming the limitations of individual modalities. However, the high costs and limited availability of certain modalities pose significant challenges. To address these issues, this paper proposes the Condition-Aligned Temporal Diffusion (CATD) framework for end-to-end cross-modal synthesis of neuroimaging, enabling the generation of functional magnetic resonance imaging (fMRI)-detected Blood Oxygen Level Dependent (BOLD) signals from more accessible Electroencephalography (EEG) signals. By constructing Conditionally Aligned Block (CAB), heterogeneous neuroimages are aligned into a latent space, achieving a unified representation that provides the foundation for cross-modal transformation in neuroimaging. The combination with the constructed Dynamic Time-Frequency Segmentation (DTFS) module also enables the use of EEG signals to improve the temporal resolution of BOLD signals, thus augmenting the capture of the dynamic details of the brain. Experimental validation demonstrates that the framework improves the accuracy of brain activity state prediction by 9.13% (reaching 69.8%), enhances the diagnostic accuracy of brain disorders by 4.10% (reaching 99.55%), effectively identifies abnormal brain regions, enhancing the temporal resolution of BOLD signals. The proposed framework establishes a new paradigm for cross-modal synthesis of neuroimaging by unifying heterogeneous neuroimaging data into a latent representation space, showing promise in medical applications such as improving Parkinson's disease prediction and identifying abnormal brain regions.

Vignetting commonly occurs as a degradation in images resulting from factors such as lens design, improper lens hood usage, and limitations in camera sensors. This degradation affects image details, color accuracy, and presents challenges in computational photography. Existing vignetting removal algorithms predominantly rely on ideal physics assumptions and hand-crafted parameters, resulting in the ineffective removal of irregular vignetting and suboptimal results. Moreover, the substantial lack of real-world vignetting datasets hinders the objective and comprehensive evaluation of vignetting removal. To address these challenges, we present VigSet, a pioneering dataset for vignetting removal. VigSet includes 983 pairs of both vignetting and vignetting-free high-resolution (over 4k) real-world images under various conditions. In addition, We introduce DeVigNet, a novel frequency-aware Transformer architecture designed for vignetting removal. Through the Laplacian Pyramid decomposition, we propose the Dual Aggregated Fusion Transformer to handle global features and remove vignetting in the low-frequency domain. Additionally, we propose the Adaptive Channel Expansion Module to enhance details in the high-frequency domain. The experiments demonstrate that the proposed model outperforms existing state-of-the-art methods. The code, models, and dataset are available at https://github.com/CXH-Research/DeVigNet.

In the existing spectral GNNs, polynomial-based methods occupy the mainstream in designing a filter through the Laplacian matrix. However, polynomial combinations factored by the Laplacian matrix naturally have limitations in message passing (e.g., over-smoothing). Furthermore, most existing spectral GNNs are based on polynomial bases, which struggle to capture the high-frequency parts of the graph spectral signal. Additionally, we also find that even increasing the polynomial order does not change this situation, which means polynomial-based models have a natural deficiency when facing high-frequency signals. To tackle these problems, we propose WaveNet, which aims to effectively capture the high-frequency part of the graph spectral signal from the perspective of wavelet bases through reconstructing the message propagation matrix. We utilize Multi-Resolution Analysis (MRA) to model this question, and our proposed method can reconstruct arbitrary filters theoretically. We also conduct node classification experiments on real-world graph benchmarks and achieve superior performance on most datasets. Our code is available at https://github.com/Bufordyang/WaveNet

Recently, intelligent reflecting surface (IRS) has emerged as a promising technology, which can be applied in mobile edge computing (MEC) systems to achieve higher data transmission efficiency and reliability, by providing a reflective channel. Concurrently, rate-splitting multiple access (RSMA), as an innovative technology, is increasingly utilized in MEC systems to enhance data offloading efficiency and facilitate a better integration of computation and communication. In this paper, an IRS enabled MEC system with RSMA under user mobility is considered. Based on this system model, we propose an optimization problem that is aimed at maximizing the system's data transmission rate by jointly optimizing the RSMA power allocation and the IRS phase shift parameters. Although traditional optimization methods can be utilized to solve the considered problem, it is quite time consuming since the optimization methods are often iterative algorithms. To design low complexity algorithm, we propose a deep reinforcement learning (DRL) approach that can efficiently make good decisions quickly after training. Numerical results indicate that, compared to the baseline algorithms, the proposed DRL-based IRS-aided offloading algorithm under RSMA protocol achieves superior system performance.

Brain network analysis plays an increasingly important role in studying brain function and the exploring of disease mechanisms. However, existing brain network construction tools have some limitations, including dependency on empirical users, weak consistency in repeated experiments and time-consuming processes. In this work, a diffusion-based brain network pipeline, DGCL is designed for end-to-end construction of brain networks. Initially, the brain region-aware module (BRAM) precisely determines the spatial locations of brain regions by the diffusion process, avoiding subjective parameter selection. Subsequently, DGCL employs graph contrastive learning to optimize brain connections by eliminating individual differences in redundant connections unrelated to diseases, thereby enhancing the consistency of brain networks within the same group. Finally, the node-graph contrastive loss and classification loss jointly constrain the learning process of the model to obtain the reconstructed brain network, which is then used to analyze important brain connections. Validation on two datasets, ADNI and ABIDE, demonstrates that DGCL surpasses traditional methods and other deep learning models in predicting disease development stages. Significantly, the proposed model improves the efficiency and generalization of brain network construction. In summary, the proposed DGCL can be served as a universal brain network construction scheme, which can effectively identify important brain connections through generative paradigms and has the potential to provide disease interpretability support for neuroscience research.

Identifying reproducible and interpretable biomarkers for Alzheimer's disease (AD) detection remains a challenge. AD detection using multi-center datasets can expand the sample size to improve robustness but might lead to a data privacy problem. Moreover, due to the high cost of labeling data, a lot of unlabeled data in each center is not fully utilized. To address this, a hybrid FL (HFL) framework is proposed that not only uses unlabeled data to train deep learning networks, but also achieves data privacy protection. We propose a novel Brain-region Attention Network (BANet), which highlights important regions via attention to represent the region of interest (ROIs).Specifically, we use a brain template to extract ROI signals from the preprocessed structure magnetic resonance imaging (sMRI) data. In addition, we add a self-supervised loss to the current loss to guide the attention map generation to learn the representations from unlabeled data. Finally, we evaluate our method on a multi-center database which is constructed using five AD datasets. The experimental results show that the proposed method performs better than state-of-the-art methods, achieving mean accuracy rates of 85.69 %, 63.34 %, and 69.89 % on the AD vs. NC, MCI vs. NC, and AD vs. MCI respectively. The source code is available for reproducibility at: https://github.com/yuliangCarmelo/HFL .

The study of nicotine addiction mechanism is of great significance in both nicotine withdrawal and brain science. The detection of addiction-related brain connectivity using functional magnetic resonance imaging (fMRI) is a critical step in study of this mechanism. However, it is challenging to accurately estimate addiction-related brain connectivity due to the low-signal-to-noise ratio of fMRI and the issue of small sample size. In this work, a prior-embedding graph generative adversarial network (PG-GAN) is proposed to capture addiction-related brain connectivity accurately. By designing a dual-generator-based scheme, the addiction-related connectivity generator is employed to learn the feature map of addiction connection, while the reconstruction generator is used for sample reconstruction. Moreover, a bidirectional mapping mechanism is designed to maintain the consistency of sample distribution in the latent space so that addiction-related brain connectivity can be estimated more accurately. The proposed model utilizes prior knowledge embeddings to reduce the search space so that the model can better understand the latent distribution for the issue of small sample size. Experimental results demonstrate the effectiveness of the proposed PG-GAN.

Alzheimer's disease (AD) is characterized by alterations of the brain's structural and functional connectivity during its progressive degenerative processes. Existing auxiliary diagnostic methods have accomplished the classification task, but few of them can accurately evaluate the changing characteristics of brain connectivity. In this work, a prior-guided adversarial learning with hypergraph (PALH) model is proposed to predict abnormal brain connections using triple-modality medical images. Concretely, a prior distribution from anatomical knowledge is estimated to guide multimodal representation learning using an adversarial strategy. Also, the pairwise collaborative discriminator structure is further utilized to narrow the difference in representation distribution. Moreover, the hypergraph perceptual network is developed to effectively fuse the learned representations while establishing high-order relations within and between multimodal images. Experimental results demonstrate that the proposed model outperforms other related methods in analyzing and predicting AD progression. More importantly, the identified abnormal connections are partly consistent with previous neuroscience discoveries. The proposed model can evaluate the characteristics of abnormal brain connections at different stages of AD, which is helpful for cognitive disease study and early treatment.

Multimodal neuroimaging provides complementary information critical for accurate early diagnosis of Alzheimer's disease (AD). However, the inherent variability between multimodal neuroimages hinders the effective fusion of multimodal features. Moreover, achieving reliable and interpretable diagnoses in the field of multimodal fusion remains challenging. To address them, we propose a novel multimodal diagnosis network based on multi-fusion and disease-induced learning (MDL-Net) to enhance early AD diagnosis by efficiently fusing multimodal data. Specifically, MDL-Net proposes a multi-fusion joint learning (MJL) module, which effectively fuses multimodal features and enhances the feature representation from global, local, and latent learning perspectives. MJL consists of three modules, global-aware learning (GAL), local-aware learning (LAL), and outer latent-space learning (LSL) modules. GAL via a self-adaptive Transformer (SAT) learns the global relationships among the modalities. LAL constructs local-aware convolution to learn the local associations. LSL module introduces latent information through outer product operation to further enhance feature representation. MDL-Net integrates the disease-induced region-aware learning (DRL) module via gradient weight to enhance interpretability, which iteratively learns weight matrices to identify AD-related brain regions. We conduct the extensive experiments on public datasets and the results confirm the superiority of our proposed method. Our code will be available at: https://github.com/qzf0320/MDL-Net.

3-D shape reconstruction is essential in the navigation of minimally invasive and auto robot-guided surgeries whose operating environments are indirect and narrow, and there have been some works that focused on reconstructing the 3-D shape of the surgical organ through limited 2-D information available. However, the lack and incompleteness of such information caused by intraoperative emergencies (such as bleeding) and risk control conditions have not been considered. In this article, a novel hierarchical shape-perception network (HSPN) is proposed to reconstruct the 3-D point clouds (PCs) of specific brains from one single incomplete image with low latency. A branching predictor and several hierarchical attention pipelines are constructed to generate PCs that accurately describe the incomplete images and then complete these PCs with high quality. Meanwhile, attention gate blocks (AGBs) are designed to efficiently aggregate geometric local features of incomplete PCs transmitted by hierarchical attention pipelines and internal features of reconstructing PCs. With the proposed HSPN, 3-D shape perception and completion can be achieved spontaneously. Comprehensive results measured by Chamfer distance (CD) and PC-to-PC error demonstrate that the performance of the proposed HSPN outperforms other competitive methods in terms of qualitative displays, quantitative experiment, and classification evaluation.

Shadow removal improves the visual quality and legibility of digital copies of documents. However, document shadow removal remains an unresolved subject. Traditional techniques rely on heuristics that vary from situation to situation. Given the quality and quantity of current public datasets, the majority of neural network models are ill-equipped for this task. In this paper, we propose a Transformer-based model for document shadow removal that utilizes shadow context encoding and decoding in both shadow and shadow-free regions. Additionally, shadow detection and pixel-level enhancement are included in the whole coarse-to-fine process. On the basis of comprehensive benchmark evaluations, it is competitive with state-of-the-art methods.

Film, a classic image style, is culturally significant to the whole photographic industry since it marks the birth of photography. However, film photography is time-consuming and expensive, necessitating a more efficient method for collecting film-style photographs. Numerous datasets that have emerged in the field of image enhancement so far are not film-specific. In order to facilitate film-based image stylization research, we construct FilmSet, a large-scale and high-quality film style dataset. Our dataset includes three different film types and more than 5000 in-the-wild high resolution images. Inspired by the features of FilmSet images, we propose a novel framework called FilmNet based on Laplacian Pyramid for stylizing images across frequency bands and achieving film style outcomes. Experiments reveal that the performance of our model is superior than state-of-the-art techniques. The link of our dataset and code is https://github.com/CXH-Research/FilmNet.

Thanks to the autonomy of unmanned aerial vehicle (UAV), UAV-enabled data collection in Internet of Things (IoT) networks has become a key application for the next generation communication network. In this paper, we consider a scenario where an UAV is responsible for collecting data from sensor equipments (SEs) one by one and finally carrying the collected data to the computation center for processing. Different from the commonly used assumption that SEs always generate data at the beginning of each time slot, it is assumed that SEs can generate data at any instant during one time slot, which is more practical. Since SEs are energy limited, they upload data to the UAV by adopting backscatter communication technology to reduce energy consumption. Meanwhile, the updated information usually contains a small number of information bits but requires low latency and high reliability, thus the finite blocklength regime in ultra-reliable and low-latency communication is adopted for SEs’ data transmission to the UAV. To keep the freshness of the updated information, a joint resource allocation problem including data collection time allocation, transmission power and trajectory design of the UAV is formulated as an optimization problem to minimize the average age of information (AoI) of all SEs. The formulated problem mixes discrete and continuous variables, which makes it difficult to solve. Thereby, we decompose the optimization problem into data collection time minimization subproblem and UAV trajectory design subproblem, which are solved by the successive convex approximation method, and the backtracking algorithm and the genetic algorithm , respectively. Numerical results show that the backtracking-based algorithm that can obtain the optimal trajectory of the UAV gains the minimal average AoI, and the genetic-based algorithm achieves sub-optimal average AoI with much lower computational complexity. The results also demonstrate that the average AoI of the backtracking-based algorithm and the genetic-based algorithm is reduced by up to 54% and 46% compared with the greedy-based benchmark algorithm, respectively.

In multi-site studies of Alzheimer's disease (AD), the difference of data in multi-site datasets leads to the degraded performance of models in the target sites. The traditional domain adaptation method requires sharing data from both source and target domains, which will lead to data privacy issue. To solve it, federated learning is adopted as it can allow models to be trained with multi-site data in a privacy-protected manner. In this paper, we propose a multi-site federated domain adaptation framework via Transformer (FedDAvT), which not only protects data privacy, but also eliminates data heterogeneity. The Transformer network is used as the backbone network to extract the correlation between the multi-template region of interest features, which can capture the brain abundant information. The self-attention maps in the source and target domains are aligned by applying mean squared error for subdomain adaptation. Finally, we evaluate our method on the multi-site databases based on three AD datasets. The experimental results show that the proposed FedDAvT is quite effective, achieving accuracy rates of 88.75%, 69.51%, and 69.88% on the AD vs. NC, MCI vs. NC, and AD vs. MCI two-way classification tasks, respectively.

Retinopathy is the primary cause of irreversible yet preventable blindness. Numerous deep-learning algorithms have been developed for automatic retinal fundus image analysis. However, existing methods are usually data-driven, which rarely consider the costs associated with fundus image collection and annotation, along with the class-imbalanced distribution that arises from the relative scarcity of disease-positive individuals in the population. Semi-supervised learning on class-imbalanced data, despite a realistic problem, has been relatively little studied. To fill the existing research gap, we explore generative adversarial networks (GANs) as a potential answer to that problem. Specifically, we present a novel framework, named CISSL-GANs, for class-imbalanced semi-supervised learning (CISSL) by leveraging a dynamic class-rebalancing (DCR) sampler, which exploits the property that the classifier trained on class-imbalanced data produces high-precision pseudo-labels on minority classes to leverage the bias inherent in pseudo-labels. Also, given the well-known difficulty of training GANs on complex data, we investigate three practical techniques to improve the training dynamics without altering the global equilibrium. Experimental results demonstrate that our CISSL-GANs are capable of simultaneously improving fundus image class-conditional generation and classification performance under a typical label insufficient and imbalanced scenario. Our code is available at: https://github.com/Xyporz/CISSL-GANs.

Magnetic resonance (MR) imaging plays an important role in clinical and brain exploration. However, limited by factors such as imaging hardware, scanning time, and cost, it is challenging to acquire high-resolution MR images clinically. In this article, fine perceptive generative adversarial networks (FP-GANs) are proposed to produce super-resolution (SR) MR images from the low-resolution counterparts. By adopting the divide-and-conquer scheme, FP-GANs are designed to deal with the low-frequency (LF) and high-frequency (HF) components of MR images separately and parallelly. Specifically, FP-GANs first decompose an MR image into LF global approximation and HF anatomical texture subbands in the wavelet domain. Then, each subband generative adversarial network (GAN) simultaneously concentrates on super-resolving the corresponding subband image. In generator, multiple residual-in-residual dense blocks are introduced for better feature extraction. In addition, the texture-enhancing module is designed to trade off the weight between global topology and detailed textures. Finally, the reconstruction of the whole image is considered by integrating inverse discrete wavelet transformation in FP-GANs. Comprehensive experiments on the MultiRes_7T and ADNI datasets demonstrate that the proposed model achieves finer structure recovery and outperforms the competing methods quantitatively and qualitatively. Moreover, FP-GANs further show the value by applying the SR results in classification tasks.

The diagnosis of early stages of Alzheimer's disease (AD) is essential for timely treatment to slow further deterioration. Visualizing the morphological features for early stages of AD is of great clinical value. In this work, a novel multidirectional perception generative adversarial network (MP-GAN) is proposed to visualize the morphological features indicating the severity of AD for patients of different stages. Specifically, by introducing a novel multidirectional mapping mechanism into the model, the proposed MP-GAN can capture the salient global features efficiently. Thus, using the class discriminative map from the generator, the proposed model can clearly delineate the subtle lesions via MR image transformations between the source domain and the predefined target domain. Besides, by integrating the adversarial loss, classification loss, cycle consistency loss, and L1 penalty, a single generator in MP-GAN can learn the class discriminative maps for multiple classes. Extensive experimental results on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that MP-GAN achieves superior performance compared with the existing methods. The lesions visualized by MP-GAN are also consistent with what clinicians observe.

Abstract This article was to explore the adoption value of deep learning combined with computed tomography (CT) imaging omics in the prediction of metastatic lymph nodes of nasopharyngeal carcinoma (NPC). An end‐to‐end neural network architecture was designed based on the fully convolutional neural network (FCNN), which was applied to the CT image analysis of 52 patients with lymphatic metastasis and 36 patients without lymphatic metastasis. Patient's lymph node volume (V), the largest cross‐sectional shortest diameter (d‐value), and other macro characteristics were recorded. The microscopic features of its CT imaging omics were extracted. Moreover, receiver operating characteristic (ROC) curve was utilized to analyse the prediction performance (accuracy, area under the curve [AUC], and Youden index) of each feature for lymphatic metastasis. The results showed that the lymph node volume (4.37 ± 0.67) and the shortest diameter of the largest cross section (12.35 ± 2.31) of patients with lymph node metastasis were greatly larger than those without lymph node metastasis (1.84 ± 0.65, 7.98 ± 2.04) (P < 0.05). There were five features that met the conditions of AUC > 0.7 and Yoden index>0.5, including lymph node volume (AUC area 0.945, Youden index 0.597), the shortest diameter of the largest cross section (AUC area 0.746, Youden index 0.539), Surface Area Density (AUC area 0.809, Youden index 0.552), Compactness1 (AUC area 0.751, Youden index 0.537), and Convex Hull Volume (AUC area 0.751, Youden index 0.537). The AUC of V+ Surface Area Density + Compactness1 + Convex Hull Volume was 0.876, and the prediction accuracy was 92.11%. In short, the prediction model composed of the macroscopic features of CT images and some imaging omics features based on deep learning showed high accuracy and AUC for the prediction of NPC metastatic lymph nodes. Moreover, V + Surface Area Density + Compactness1 + Convex Hull Volume can be used as the optimal feature combination model for predicting NPC lymphatic metastasis.

Fusing multi-modality medical images, such as magnetic resonance (MR) imaging and positron emission tomography (PET), can provide various anatomical and functional information about the human body. However, PET data is not always available for several reasons, such as high cost, radiation hazard, and other limitations. This paper proposes a 3D end-to-end synthesis network called Bidirectional Mapping Generative Adversarial Networks (BMGAN). Image contexts and latent vectors are effectively used for brain MR-to-PET synthesis. Specifically, a bidirectional mapping mechanism is designed to embed the semantic information of PET images into the high-dimensional latent space. Moreover, the 3D Dense-UNet generator architecture and the hybrid loss functions are further constructed to improve the visual quality of cross-modality synthetic images. The most appealing part is that the proposed method can synthesize perceptually realistic PET images while preserving the diverse brain structures of different subjects. Experimental results demonstrate that the performance of the proposed method outperforms other competitive methods in terms of quantitative measures, qualitative displays, and evaluation metrics for classification.

It is of great significance to apply deep learning for the early diagnosis of Alzheimer's disease (AD). In this work, a novel tensorizing GAN with high-order pooling is proposed to assess mild cognitive impairment (MCI) and AD. By tensorizing a three-player cooperative game-based framework, the proposed model can benefit from the structural information of the brain. By incorporating the high-order pooling scheme into the classifier, the proposed model can make full use of the second-order statistics of holistic magnetic resonance imaging (MRI). To the best of our knowledge, the proposed Tensor-train, High-order pooling and Semisupervised learning-based GAN (THS-GAN) is the first work to deal with classification on MR images for AD diagnosis. Extensive experimental results on Alzheimer's disease neuroimaging initiative (ADNI) data set are reported to demonstrate that the proposed THS-GAN achieves superior performance compared with existing methods, and to show that both tensor-train and high-order pooling can enhance classification performance. The visualization of generated samples also shows that the proposed model can generate plausible samples for semisupervised learning purpose.

Assessment of skeletal maturity is important for a clinician to make a decision of the most appropriate treatment on various skeletal disorders. This task is very challenging when using machine learning method due to the limited data and large anatomical variations among different subjects. In this article, we propose an ensemble-based deep learning pipeline to automatically assess the distal radius and ulna (DRU) maturity from left-hand radiographs. At the same time, we adapted the concept of densely connected mechanism in the proposed network architecture to reuse features and prevent gradient disappearance. Therefore, the model acquires two convincing advantages: first, our model preserves the maximum information flow and has a much faster convergence rate. Second, our model avoids overfitting even if training with limited data. The experimental dataset contains 1189 left-hand$X$-ray scans of children and teenagers. The proposed method achieves 85.27% and 91.68% for radius and ulna classification, respectively. Extensive experiments prove that our model performs better than using other network structures.

Recently, the intelligent reflecting surface (IRS) is an emerging and promising technology for achieving higher spectrum and energy efficiency in wireless communication systems. In this paper, we consider a wireless powered mobile edge computing (MEC) network that is equipped with an IRS. The IRS is able to provide a reflecting channel to enhance the offloading capability for edge users. Based on this system model, we investigate an optimisation problem to maximize the sum of users' utilities, which jointly consider the energy efficiency, time latency, and price of offloading computations. With task offloading, power limited users can complete the computational tasks even when they face data-intensive workloads. However, in a dynamic system, it is complicated to design the optimal offloading decision strategy. To tackle this problem, we propose a deep reinforcement learning (DRL) based approach. In the designed algorithm, in order to get a better reward, the agent chooses a near optimal solution to adjust the workload partitions, the time allocation, and IRS parameters according to the dynamic channel environment and the random arrival of task workload. Numerical results show that the proposed DRL based IRS-aided offloading algorithm can achieve better system performance compared with that without IRS and the relative benchmark algorithms.

This article studies the data collection problem in an Internet-of-Things (IoT) network with multiple unmanned aerial vehicles (UAVs) where UAVs first power multiple IoT devices by wireless power transfer, and then IoT devices utilize the harvested energy to transmit data to UAVs. Different from most of the existing works that often assume the channel between the UAV and the IoT device is a simplified Line-of-Sight (LoS) channel, a more practical and accurate probabilistic LoS channel model is adopted, in which both the elevation angle and the distance between the UAV and the IoT device determine the channel gain. Our objective is to maximize the UAV's minimum data collection rate among all IoT devices by jointly optimizing time allocation and 3-D trajectory of UAVs within a limited time duration. This results in a nonconvex optimization problem, which is challenge to solve. To tackle this difficulty, we transform the nonconvex problem to a difference of convex (D.C.) optimization problem by subtly using several methods. To solve the D.C. optimization problem, an efficient iterative algorithm is designed via a successive convex approximation method. Numerical simulation results are provided to verify the performance of the proposed algorithm compared to two benchmark algorithms, the algorithm with simplified LoS model and that with 2-D trajectory optimization, under various conditions.

Diabetic retinopathy (DR) is one of the major causes of blindness. It is of great significance to apply deep-learning techniques for DR recognition. However, deep-learning algorithms often depend on large amounts of labeled data, which is expensive and time-consuming to obtain in the medical imaging area. In addition, the DR features are inconspicuous and spread out over high-resolution fundus images. Therefore, it is a big challenge to learn the distribution of such DR features. This article proposes a multichannel-based generative adversarial network (MGAN) with semisupervision to grade DR. The multichannel generative model is developed to generate a series of subfundus images corresponding to the scattering DR features. By minimizing the dependence on labeled data, the proposed semisupervised MGAN can identify the inconspicuous lesion features by using high-resolution fundus images without compression. Experimental results on the public Messidor data set show that the proposed model can grade DR effectively. Note to Practitioners-This article is motivated by the challenging problem due to the inadequacy of labeled data in medical image analysis and the dispersion of efficient features in high-resolution medical images. As for the inadequacy of labeled data in medical image analysis, the reasons mainly include the followings: 1) the high-quality annotation of medical imaging sample depends heavily on scarce medical expertise which is very expensive and 2) comparing with natural issues, it is more difficult to collect medical images because of privacy issues. It is of great significance to apply deep-learning techniques for diabetic retinopathy (DR) recognition. In this article, the multichannel generative adversarial network (GAN) with semisupervision is developed for DR-aided diagnosis. The proposed model can deal with DR classification problem with inadequacy of labeled data in the following ways: 1) the multichannel generative scheme is proposed to generate a series of subfundus images corresponding to the scattering DR features and 2) the proposed multichannel-based GAN (MGAN) model with semisupervision can make full use of both labeled data and unlabeled data. The experimental results demonstrate that the proposed model outperforms the other representative models in terms of accuracy, area under ROC curve (AUC), sensitivity, and specificity.

Separable nonlinear least squares (SNLLS) problems have attracted interest in a wide range of research fields such as machine learning, computer vision, and signal processing. During the past few decades, several algorithms, including the joint optimization algorithm, alternated least squares (ALS) algorithm, embedded point iterations (EPI) algorithm, and variable projection (VP) algorithms, have been employed for solving SNLLS problems in the literature. The VP approach has been proven to be quite valuable for SNLLS problems and the EPI method has been successful in solving many computer vision tasks. However, no clear explanations about the intrinsic relationships of these algorithms have been provided in the literature. In this paper, we give some insights into these algorithms for SNLLS problems. We derive the relationships among different forms of the VP algorithms, EPI algorithm and ALS algorithm. In addition, the convergence and robustness of some algorithms are investigated. Moreover, the analysis of the VP algorithm generates a negative answer to Kaufman's conjecture. Numerical experiments on the image restoration task, fitting the time series data using the radial basis function network based autoregressive (RBF-AR) model, and bundle adjustment are given to compare the performance of different algorithms.

A novel method for the estimation of the temperature distribution in a rapid thermal processing (RTP) system is developed in this paper. The proposed method uses a proper orthogonal decomposition algorithm to extract the dominant modes of the temperature distribution and a reduced-order model is obtained. Then, a reduced-order sliding-mode observer is developed to capture the dynamics of the dominant modes. The estimated dynamics of the dominant modes can be used to reconstruct the temperature distribution. It is proved that the estimation error would be drawn into a small boundary rapidly. Test results confirm the effectiveness of the proposed observer for the RTP system.

Automatic diagnosis of Alzheimers disease (AD) and mild cognition impairment (MCI) from 3D brain magnetic resonance (MR) images plays an important role in early treatment of dementia disease. Deep learning architectures can extract potential features of dementia disease and capture brain anatomical changes from MRI scans. This paper proposes an ensemble of 3D densely connected convolutional networks (3D-DenseNets) for AD and MCI diagnosis. First, dense connections were introduced to maximize the information flow, where each layer connects with all subsequent layers directly. Then weighted-based fusion method was employed to combine 3D-DenseNets with different architectures. Extensive experiments were conducted to analyze the performance of 3D-DenseNet with different hyper-parameters and architectures. Superior performance of the proposed model was demonstrated on ADNI dataset including 833 subjects.

In this study, we propose an automated framework that combines diffusion tensor imaging (DTI) metrics with machine learning algorithms to accurately classify control groups and groups with cervical spondylotic myelopathy (CSM) in the spinal cord. The comparison between selected voxel-based classification and mean value-based classification were performed. A support vector machine (SVM) classifier using a selected voxel-based dataset produced an accuracy of 95.73%, sensitivity of 93.41% and specificity of 98.64%. The efficacy of each index of diffusion for classification was also evaluated. Using the proposed approach, myelopathic areas in CSM are detected to provide an accurate reference to assist spine surgeons in surgical planning in complicated cases.

This paper investigates the resource allocation problem in orthogonal frequency division multiple access multi-user networks, where subcarriers are grouped into chunks due to simplicity of implementation. The aim is to achieve max-min fairness among users by adjusting the transmission power allocation and chunk allocation while taking into account several important constrains. The problem is formulated as a mixed integer nonlinear programming problem, whose optimal solution is extremely hard to find. Then a low complexity suboptimal algorithm is proposed, which solves the chunk allocation and power allocation in two steps separately. A fast optimal power allocation algorithm is designed by exploiting the special structure of the problem. Simulations verify the performance of the proposed algorithm in terms of the users' minimal transmission rate and running time comparing with benchmark algorithms.

In this paper, we investigate the resource allocation for orthogonal frequency division multiple access relay networks, where the relay does not have embedded energy supply and needs to first harvest energy from the received signals from the source before forwarding transmission. The relay uses time switching scheme for wireless information and power transfer. We aim to maximize the weighted sum rate under several constraints by varying the source transmission power, the relay transmission power, and the time switching ratio. We formulate the joint resource allocation problem as an optimization problem, which is non-convex. Although it is difficult to solve the non-convex problem, we derive its closed-form solution by exploiting its special structure. We also prove that the closed- form solution is a partial optimum. Finally, simulations verify the proposed closed-form solution is superior to the equal power solution.