Edge computing has been proved an efficient approach to provisioning computation offloading service to vehicles on road through Road-Side Units (RSUs). However, the traffic volume on road is highly dynamic, while RSU-based edge servers are static in terms of geographical location and computation capacity. To address this problem, this paper proposes a mobile edge server placement strategy using cruising UAVs along the roads based on the genetic algorithm. We first build a mathematical model to characterize the deployment cost of these UAV-mounted servers and their routes. Next, we design a heuristic UAV-mounted edge server deployment scheme based on K-medoid clustering and genetic algorithms. Experimental results verify that our proposed UAV deployment scheme satisfies the offloading demand of IoV nodes while reducing the total deployment cost by 17.05% to 48.94% compared with existing popular approaches.

Automatic Violence Detection and Classification (AVDC) with deep learning has garnered significant attention in computer vision research. This paper presents a novel approach to combining a custom Deep Convolutional Neural Network (DCNN) with a Gated Recurrent Unit (GRU) in developing a new AVDC model called BrutNet. Specifically, we develop a time-distributed DCNN (TD-DCNN) to generate a compact 2D representation with 512 spatial features per frame from a set of equally-spaced frames of dimension 160×90 in short video segments. Further to leverage the temporal information, a GRU layer is utilised, generating a condensed 1D vector that enables binary classification of violent or non-violent content through multiple dense layers. Overfitting is addressed by incorporating dropout layers with a rate of 0.5, while the hidden and output layers employ rectified linear unit (ReLU) and sigmoid activations, respectively. The model is trained on the NVIDIA Tesla K80 GPU through Google Colab, demonstrating superior performance compared to existing models across various video datasets, including hockey fights, movie fights, AVD, and RWF-2000. Notably, our model stands out by requiring only 3.416 million parameters and achieving impressive test accuracies of 97.62%, 100%, 97.22%, and 86.43% on the respective datasets. Thus, BrutNet exhibits the potential to emerge as a highly efficient and robust AVDC model in support of greater public safety, content moderation and censorship, computer-aided investigations, and law enforcement.

Targets with rotating components generate micro-motion (MM) modulation effect in addition to the main body. Extracting MM parameters is challenging due to interference from the target’s main body, necessitating the separation of modulation signals. This letter proposes a robust complex local mean decomposition (RCLMD) method with self-adaptive sifting stopping, aiming at the problem of component redundancy due to multiple iterations during break and the loss of modulation components during the separation process. The proposed method sets the objective function and self-adaptive stopping criterion, combined with the modulation signal characteristics, enhancing the accuracy and efficiency of MM component extraction. Simulation experiments indicate that at a low signal-to-noise ratio (SNR) of 3 dB, the separation effect of RCLMD is still 14.72\% higher than that of the conventional complex local mean decomposition (CLMD) method, and the separation efficiency is improved by 54.92\%. Furthermore, the measured radar signals verify the effectiveness of the proposed method in real scenarios.

Welcome to this Special Issue of Wiley’s Healthcare Technology Letters (HTL) journal dedicated to the 2023 edition of the Augmented Environments for Computer-Assisted Interventions (AE-CAI), Computer Assisted and Robotic Endoscopy (CARE), and Context-aware Operating Theatres (OR 2.0) joint workshop. We are pleased to present the proceedings of this exciting scientific gathering held in conjunction with the Medical Image Computing and Computer-Assisted Interventions (MICCAI) conference on October 8th, 2023 in Vancouver, British Columbia, Canada. We hope that you will enjoy reading this Special Issue and we look forward to your continuing support and participation in future editions of the AE-CAI, CARE and OR 2.0 workshops. Their continued success demands our ongoing commitment and support, and we hope to welcome you all to the next edition of the workshop at MICCAI 2024 in Marrakesh, Marocco.

This paper presents a prediction-based dynamic range (DR) compensation technique in continuous-time (CT) delta -sigma modulator (DSM) with digital-domain noise coupling (DNC) structure. A digital prediction technique is proposed to address the issue of maximum stable amplitude (MSA) loss caused by DNC. The proposed prediction method has been shown to significantly extend the MSA of CT DSM with DNC. Moreover, through the extension of MSA, the DR and SNDR is significantly improved. A CTDSM with proposed compensation achieves a SNDR of 85.1dB at -1dBFS and a DR of 89dB.

Future communication networks are widely considered to be able to provide both high-speed communication service and reliable sensing service. Integrated sensing and communication (ISAC) has been a novel trend due to its possible hardware gain and spectrum gain by the integration of signal communication and sensing capabilities. Appropriate resource allocation strategy is essential for ensuring the quality of both communication and sensing services in terms of ISAC. Existing ISAC-based resource allocation schemes mainly focus on the coexistence of sensing and communication. However, in multi-user ISAC networks, the services required by users are diverse, including sensing-only, communication-only and dual-function cases. To this end, we proposes a resource allocation strategy based on user quality of service(QoS). Specifically, the sum rate of cellular network is maximized via optimizing spectrum resource selection and transmit power, while meeting the sensing QoS. We achieve the optimal solution to the entire problem by first demonstrating that the communication rate in this paper is a monotonically increasing function of sensing power, allowing us to obtain the optimal power allocation scheme. Subsequently, we employ a matching method to obtain the optimal spectrum sharing scheme.

Integrated sensing and communication (ISAC) is a promising technique for unmanned aerial vehicle (UAV)-empowered 6G networks. In this letter, we propose a novel adaptable ISAC mechanism. Firstly, we investigate both the communication and sensing channel model under Doppler and beam-squint effect for the UAV ISAC with the wideband massive multiple-input multiple-output (MIMO) configuration. Then, we propose an adaptive sensing method by the joint designing the signal echo sensing and beam-squint sensing under practical environment. Specifically, when the echo power is larger than the minimum detectable power, the proposed method could realize the effective sensing by utilizing the system model without feedback. Otherwise, the proposed method could exploit the beam-squint for sensing with the feedback of the sub-carrier index. Finally, various simulation results are provided to demonstrate the effectiveness of the proposed scheme.

Indoor navigation networks serve as the foundation for indoor pedestrian navigation services. However, current graph-based topological network models cannot easily represent complex indoor structures in a manner consistent with user behaviour and cognitive patterns, and thus cannot support fine-grained indoor navigation analysis services. To enhance the rationality of the model, we considered the influences of morphological and functional characteristics of indoor spaces on pedestrian movement and proposed a method for classifying navigation spaces. This method, based on convex space segmentation, defines morphological and functional characteristic functions, classifying indoor navigation spaces as either corridors or open spaces, which suitable for representing as median axis models or visual graphs, respectively. These categories supported the creation of topological network models for route planning analysis. Indoor map experiments confirmed the effectiveness of our method in identifying various types of corridors and open spaces, that addressing the limitations of width-based parameters，even in complex indoor settings.

The use of head-mounted augmented reality (AR) for surgeries has grown rapidly in recent years. AR aids in intraoperative surgical navigation through overlaying 3D holographic reconstructions of medical data. However, performing AR surgeries on complex areas poses challenges in terms of accuracy and speed. This study explores the feasibility of an AR guidance system for resections of positive tumor margins at the head and neck region. We present an intraoperative solution that enables surgeons to access holographic reconstructions of resected cadaver tissues. The solution involves using 3D scanner to capture detailed scans of the resected tissue, which are uploaded into our software. It then converts these scans into holograms that are viewable through a head-mounted AR display. Surgeons navigates the tumor site by re-aligning these holograms with cadavers using gestures or voice commands. This workflow runs concurrently with frozen section analysis. On average, we achieve an uploading time of 2.98 min, visualization time of 1.05 min and re-alignment time of 4.39 min, within the 20 - 30 min window for frozen section analysis. We achieve a mean re-alignment error of 3.1 mm. Our software provides a foundation for new product development in using AR to navigate complex anatomy in surgery.

Semantic communication has attracted significant attention as a key technology for emerging 6G communications. Though it has lots of potentials specially for high volume media communications, still there is no proper quality metric for modelling the semantic noise in semantic communications. This paper proposes an autoencoder based image quality metric to quantify the semantic noise. An autoencoder is initially trained with the reference image to generate the encoder decoder model and calculate its latent vector space. Once it is trained, a semantically generated/received image is inserted to the same autoencoder to create the corresponding latent vector space. Finally, both vector spaces are used to define the Euclidean space between two spaces to calculate the Mean Square Error between two vector spaces, which is used to measure the effectiveness of the semantically generated image. Results indicate that the proposed model has a correlation coefficient of 88% with the subjective quality assessment. Furthermore, the proposed model is tested as a metric to evaluate the image quality in conventional image coding. Results indicate that the proposed model can also be used to replace conventional image quality metrics such as PSNR,SSIM,MSSIM,UQI, VIFP, and SSC whereas these conventional metrics completely failed in semantic noise modelling.

Kidney stones require surgical removal when they grow too large to be broken up externally or to pass on their own. Upper tract urothelial carcinoma are also sometimes treated endoscopically in a similar procedure. These surgeries are difficult, particularly for trainees who often miss tumors, stones or stone fragments, requiring re-operation. One cause of difficulty is the high cognitive strain surgeons experience in creating accurate mental models during the endoscopic operation. Furthermore, there are no patient-specific simulators to facilitate training or standardized visualization tools for ureteroscopy despite its high prevalence. We propose ASSIST-U, a system to automatically create realistic ureteroscopy images and videos solely using preoperative CT images to address these unmet needs. We train a 3D UNet model to automatically segment CT images and construct 3D surfaces. These surfaces are then skeletonized for rendering and camera position tracking. Finally, we train a style transfer model using Contrastive Unpaired Translation (CUT) to synthesize realistic ureteroscopy images. Cross validation on the UNet model achieved a Dice score of 0.853 $\pm$ 0.084 for the CT segmentation step. CUT style transfer produced visually plausible images; the Kernel Inception Distance to real ureteroscopy images was reduced from 0.198 (rendered) to 0.089 (synthesized). We also qualitatively demonstrate the entire pipeline from CT to synthesized ureteroscopy. The proposed ASSIST-U system shows promise for aiding surgeons in visualization of kidney ureteroscopy.

The integration of Augmented Reality (AR) into daily surgical practice is withheld by the correct registration of pre-operative data. This includes intelligent 3D model superposition whilst simultaneously handling real and virtual occlusions caused by the AR overlay. Occlusions can negatively impact surgical safety and as such deteriorate rather than improve surgical care. Robotic surgery is particularly suited to tackle these integration challenges in a stepwise approach as the robotic console allows for different inputs to be displayed in parallel to the surgeon. Nevertheless, real-time de-occlusion requires extensive computational resources which further complicates clinical integration. This work tackles the problem of instrument occlusion and presents, to our best knowledge, the first-in-human on edge deployment of a real-time binary segmentation pipeline during three robot-assisted surgeries: partial nephrectomy, migrated endovascular stent removal and liver metastasectomy. To this end, a state-of-the-art real-time segmentation and 3D model pipeline was implemented and presented to the surgeon during live surgery. The pipeline allows real-time binary segmentation of 37 non-organic surgical items, which are never occluded during AR. The application features real-time manual 3D model manipulation for correct soft tissue alignment. The proposed pipeline can contribute towards surgical safety, ergonomics and acceptance of AR in minimally invasive surgery.

Efficient communication and collaboration are essential in the operating room for successful and safe surgery. While many technologies are improving various aspects of surgery, communication between attending surgeons, residents, and surgical teams is still limited to verbal interactions that are prone to misunderstandings. Novel modes of communication can increase speed and accuracy, and transform operating rooms. We present a mixed reality (MR) based gaze sharing application on Microsoft HoloLens 2 headset that can help expert surgeons indicate specific regions, communicate with decreased verbal effort, and guide novices throughout an operation. We test the utility of the application with a user study of endoscopic kidney stone localization completed by urology expert and novice surgeons. We observe improvement in the NASA Task Load Index surveys (up to 25.23%), in the success rate of the task (6.98% increase in localized stone percentage), and in gaze analyses (up to 31.99%). The proposed application shows promise in both operating room applications and surgical training tasks.

Endoscopic renal surgeries have high re-operation rates, particularly for lower volume surgeons. Due to the limited field and depth of view of current endoscopes, mentally mapping preoperative computed tomography (CT) images of patient anatomy to the surgical field is challenging. The inability to completely navigate the intrarenal collecting system leads to missed kidney stones and tumors, subsequently raising recurrence rates. We propose a guidance system to estimate the endoscope positions within the CT to reduce re-operation rates. We use a Structure from Motion algorithm to reconstruct the kidney collecting system from the endoscope videos. In addition, we segment the kidney collecting system from CT scans using 3D U-Net to create a 3D model. We can then register the two collecting system representations to provide information on the relative endoscope position. We demonstrate correct reconstruction and localization of intrarenal anatomy and endoscope position. Furthermore, we create a 3D map supported by the RGB endoscope images to reduce the burden of mental mapping during surgery. The proposed reconstruction pipeline has been validated for guidance. It can reduce the mental burden for surgeons and is a step towards our long-term goal of reducing re-operation rates in kidney stone surgery.

This work present a proof-of-concept of a robotic-driven intra-operative scanner designed for knee cartilage lesion repair, part of a system for direct in vivo bioprinting. The proposed system is based on a photogrammetric pipeline, which reconstructs the cartilage and lesion surfaces from sets of photographs acquired by a robotic-handled endoscope, and produces 3D grafts for further printing path planning. A validation on a synthetic phantom is presented, showing that —despite the cartilage smooth and featureless surface— the current prototype can accurately reconstruct osteochondral lesions and their surroundings with mean error values of 0.199 ± 0.096 mm but with noticeable concentration on areas with poor lighting or low photographic coverage. The system can also accurately generate grafts for bioprinting, although with a slight tendency to underestimate the actual lesion sizes, producing grafts with coverage errors of -12.2 ± 3.7, -7.9 ± 4.9 and -15.2 ± 3.4 % for the medio-lateral, antero-posterior and craneo-caudal directions respectively. Improvements in lighting and acquisition for enhancing reconstruction accuracy are planned as future work, as well as integration into a complete bioprinting pipeline and validation with ex vivo phantoms.

Hand pose estimation based on a single RGB image has low accuracy due to the complexity of the pose, local self-similarity of finger features, and occlusion. A multiscale feature fusion network (MS-FF) for monocular vision gesture pose estimation is proposed to address this problem. The network can take full advantage of different channel information to enhance important gesture information, and it can simultaneously extract features from feature maps of different resolutions to obtain as much detailed feature information and deep semantic information as possible. The feature maps are merged to obtain the hand pose results. The InterHand2.6M dataset and Rendered Handpose Dataset (RHD) are used to train the MS-FF. Compared with the other methods (which can estimate interacting hand poses from a single RGB image), the MS-FF obtains the smallest average error of hand joints on RHD, verifying its effectiveness.

This letter proposes a polarization microwave correlation imaging method based on the orthogonal complement space. It utilizes the orthogonal complement space of the HV antenna radiation field to cross-multiply the echo information, enabling simultaneous correlation imaging and instantaneous polarization measurement of the target. Currently, there is a significant research gap in polarization-driven microwave correlation imaging methods, and the existing relevant studies focus on enhancing the randomness of the radiation field using polarized antenna elements, without incorporating polarization information into the imaging process. Through simulation analysis, this method further improves the quality of microwave correlation imaging and its ability to resist interference. Moreover, under low time-frequency products, the peak sidelobe level (PSL) and isolation (I) of this method are approximately 3.5 dB and 12.5 dB higher, respectively, than those of traditional instantaneous polarization measurement (TIPM)methods.

The capacitance mismatch problem limits the accuracy improvement of high-precision SAR ADCs (Successive Approximation Register Analog-to-Digital Converters). To address the capacitance array mismatch in SAR ADCs, this paper proposes a novel capacitor calibration scheme based on the Time-to-Digital Converter (TDC). This scheme achieves calibration accuracy as high as 0.01\% and can be flexibly designed to meet the accuracy requirements of SAR ADCs. Simulation results indicate that the capacitance mismatch issue of a redundant capacitor 13-bit SAR ADC can be completely eliminated, and the effective number of bits (ENOB) can approach the ideal value of 13.18 bits. Additionally, the analog component of this scheme utilizes four inverter chains, two D flip-flops, and four counters, without requiring a large area for auxiliary calibration capacitors.