Subclavian Steal Syndrome Caused by Thrombosis Associated with COVID-19: a Case Report.

Background: Thromboembolic complications are a frequent occurrence during COVID-19. This report presents a patient with signs of subclavian steal syndrome (SSS) caused by a thrombus in the initial part of the right subclavian artery. Pathological occlusive changes, such as thrombosis, are four times more common on the left subclavian. Thrombosis of the subclavian artery occurs in about 1% of the population, but atherosclerotic changes are common and usually asymptomatic. Objective: The aim of this report is to present a patient with signs of subclavian steal syndrome (SSS) caused by a thrombus in the initial part of the right subclavian artery associated with symptoms of COVID-19. Case report: A 56-year-old female patient presented with tremor, numbness and prickling in the right hand, tinnitus, blurred vision, vertigo, syncope, trismus and headaches. The formation of a thrombus caused neurological symptoms in the right hand with a stronger pronounced tremor, headache and syncopal episodes. Routine CT with angiography did not reveal significant subocclusions of the neck arteries or significant ischemic changes in the brain. The patient was treated as Parkinsonismus (disease) with syncopal and collapsing episodes. Due to worsening subjective complaints, CT angiography of the neck and head blood vessels was repeated with iterative 3D reconstruction. The examination, as mentioned above, revealed atherosclerotic changes with thrombosis and stronger subocclusion of the right subclavian artery (RSA) proximal to the origin of the arteria vertebralis. Both vertebral arteries, as well as arteria basilaris, had a normal appearance. During physical exertion of the right arm doppler examination of neck blood vessels revealed the presence of reverse blood flow in the right vertebral artery. Haematological tests and high D-dimer also confirmed the diagnosis. After anticoagulant therapy, the thrombotic mass on the mural calcified RSA plaque disappeared. With the reduced physical strain on the right hand and a lifestyle change, syncopal conditions and headaches stopped. There was a reduction in tremors and tingling in the right hand as well. Conclusion: We reported a case of subclavian steal syndrome caused by thrombosis associated with OVID-19. Thromboembolic complications are common in the course of this disease. The diagnosis was confirmed with advanced diagnostic tools (CTA with 3D reconstruction), laboratory tests (D-dimer) and doppler ultrasound. When routine CT angiography is not completely clear, 3D reconstruction is necessary.

Automatic 3D Building Reconstruction from OpenStreetMap and LiDAR Using Convolutional Neural Networks.

This paper presents the implementation of an automatic method for the reconstruction of 3D building maps. The core innovation of the proposed method is the supplementation of OpenStreetMap data with LiDAR data to reconstruct 3D urban environments automatically. The only input of the method is the area that needs to be reconstructed, defined by the enclosing points in terms of the latitude and longitude. First, area data are requested in OpenStreetMap format. However, there are certain buildings and geometries that are not fully received in OpenStreetMap files, such as information on roof types or the heights of buildings. To complete the information that is missing in the OpenStreetMap data, LiDAR data are read directly and analyzed using a convolutional neural network. The proposed approach shows that a model can be obtained with only a few samples of roof images from an urban area in Spain, and is capable of inferring roofs in other urban areas of Spain as well as other countries that were not used to train the model. The results allow us to identify a mean of 75.57% for height data and a mean of 38.81% for roof data. The finally inferred data are added to the 3D urban model, resulting in detailed and accurate 3D building maps. This work shows that the neural network is able to detect buildings that are not present in OpenStreetMap for which in LiDAR data are available. In future work, it would be interesting to compare the results of the proposed method with other approaches for generating 3D models from OSM and LiDAR data, such as point cloud segmentation or voxel-based approaches. Another area for future research could be the use of data augmentation techniques to increase the size and robustness of the training dataset.

Real-time Semantic 3D Reconstruction for High- Touch Surface Recognition for Robotic Disinfection

Disinfection robots have applications in promoting public health and reducing hospital acquired infections and have drawn considerable interest due to the COVID-19 pan-demic. To disinfect a room quickly, motion planning can be used to plan robot disinfection trajectories on a reconstructed 3D map of the room's surfaces. However, existing approaches discard semantic information of the room and, thus, take a long time to perform thorough disinfection. Human cleaners, on the other hand, disinfect rooms more efficiently by prioritizing the cleaning of high-touch surfaces. To address this gap, we present a novel GPU-based volumetric semantic TSDF (Truncated Signed Distance Function) integration system for semantic 3D reconstruction. Our system produces 3D reconstructions that distinguish high-touch surfaces from non-high-touch surfaces at approximately 50 frames per second on a consumer-grade GPU, which is approximately 5 times faster than existing CPU-based TSDF semantic reconstruction methods. In addition, we extend a UV disinfection motion planning algorithm to incorporate semantic awareness for optimizing coverage of disinfection tra-jectories. Experiments show that our semantic-aware planning outperforms geometry-only planning by disinfecting up to 20% more high-touch surfaces under the same time budget. Further, the real-time nature of our semantic reconstruction pipeline enables future work on simultaneous disinfection and mapping. Code is available at: https://github.com/uiuc-iml/RA-SLAM © 2022 IEEE.

Automatic and Fast Whole Heart Segmentation for 3D Reconstruction

Accurate and fast whole cardiac substructures segmentation from Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) is crucial in developing clinical applications, such as computer-aided surgery and computer-aided diagnosis. However, the segmentation of different substructures is challenging because of the amount of data that should be annotated by experts, the diversity of sizes and shapes of cardiac substructures, and the complexity of the background. This work aims to develop an automatic and fast whole heart segmentation including all cardiac substructures as well as the great vessels. The proposed approach used mainly image processing methods that enable the heart segmentation from sagittal, axial, and coronal views to obtain a 3D reconstruction. Finally, the experiments are conducted on both Automated Cardiac Diagnosis Challenge and CT scans acquired from a patient with COVID-19 at the Cheikh Zaid International University Hospital in Rabat Morocco. © 2022 IEEE.

Automatic evaluation of 3D volume infection rates: Application to the Covid-19 context

Covid-19 is a highly contagious respiratory syndrome, officially declared a global pandemic on 11 March 2020. Due to its rapid spread and the exponential increase in the number of infected and deceased patients, manual diagnosis in the healthcare sector is insufficient to manage each patient individually, even the assessment of lesions by clinicians is approximate. Moreover, to date, no end-to-end tool is proposed for automatic volumetric quantification of Covid lesions. Hence, in this paper we report the implementation of a complete chain for automatic assessment of the degree of Covid-19 lesions. It includes (i) preparation of the private database, (ii) image pre-processing, (iii) automatic segmentation based on U-NET and evaluation of its results by the usual metrics, (iv) 3D reconstruction and finally (v) volumetric quantification of Covid-19 lesions using the digitised images as input. For validation, the process is applied to our own private database that we have created for this purpose. The results obtained are very encouraging. The evaluation of the segmentation for the lung by the metrics DICE, IOU, Precision, Recall and Accuracy yielded respectively: 0.81, 0.90, 0.93, 0.82 and 0.92. Similarly for lesions these values are: 0.89, 0.93, 0.93, 0.81 and 0.93 respectively. © 2022 IEEE.

Augmented Reality for COVID-19 Aid Diagnosis: Ct-Scan segmentation based Deep Learning

The virus new variants of Coronavirus disease 2019 (COVID-19) continue to appear, making the situation more challenging and threatening. The COVID-19 pandemic has profoundly affected health systems and medical centres worldwide. The primary clinical tools used in diagnosing patients presenting with respiratory distress and suspected COVID-19 symptoms are radiology examinations. Recently emerging artificial intelligence (AI) technologies further strengthen the power of imaging tools and help medical specialists. This paper presents an Augmented Reality (AR) tool for COVID-19 aid diagnosis, including Computerised Tomography Ct-scans segmentation based Deep Learning, 3D reconstruction, and AR visualisation. Segmentation is a critical step in AI-based COVID-19 image processing and analysis;we use the popular segmentation networks, including classic U-Net. Quantitative and qualitative evaluation showed reasonable performance of U-Net for lung and COVID-19 lesions segmentation. The AR-COVID-19 aid diagnosis system could be used for medical education professional training and as a support visualisation and reading tool for radiologist. © 2022 IEEE.

A Deep Learning-Based Diagnosis System for COVID-19 Detection and Pneumonia Screening Using CT Imaging

Background: Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) is a global threat impacting the lives of millions of people worldwide. Automated detection of lung infections from Computed Tomography scans represents an excellent alternative;however, segmenting infected regions from CT slices encounters many challenges. Objective: Developing a diagnosis system based on deep learning techniques to detect and quantify COVID-19 infection and pneumonia screening using CT imaging. Method: Contrast Limited Adaptive Histogram Equalization pre-processing method was used to remove the noise and intensity in homogeneity. Black slices were also removed to crop only the region of interest containing the lungs. A U-net architecture, based on CNN encoder and CNN decoder approaches, is then introduced for a fast and precise image segmentation to obtain the lung and infection segmentation models. For better estimation of skill on unseen data, a fourfold cross-validation as a resampling procedure has been used. A three-layered CNN architecture, with additional fully connected layers followed by a Softmax layer, was used for classification. Lung and infection volumes have been reconstructed to allow volume ratio computing and obtain infection rate. Results: Starting with the 20 CT scan cases, data has been divided into 70% for the training dataset and 30% for the validation dataset. Experimental results demonstrated that the proposed system achieves a dice score of 0.98 and 0.91 for the lung and infection segmentation tasks, respectively, and an accuracy of 0.98 for the classification task. Conclusions: The proposed workflow aimed at obtaining good performances for the different system’s components, and at the same time, dealing with reduced datasets used for training. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Comparing Desktop vs. Mobile Interaction for the Creation of Pervasive Augmented Reality Experiences.

This paper presents an evaluation and comparison of interaction methods for the configuration and visualization of pervasive Augmented Reality (AR) experiences using two different platforms: desktop and mobile. AR experiences consist of the enhancement of real-world environments by superimposing additional layers of information, real-time interaction, and accurate 3D registration of virtual and real objects. Pervasive AR extends this concept through experiences that are continuous in space, being aware of and responsive to the user's context and pose. Currently, the time and technical expertise required to create such applications are the main reasons preventing its widespread use. As such, authoring tools which facilitate the development and configuration of pervasive AR experiences have become progressively more relevant. Their operation often involves the navigation of the real-world scene and the use of the AR equipment itself to add the augmented information within the environment. The proposed experimental tool makes use of 3D scans from physical environments to provide a reconstructed digital replica of such spaces for a desktop-based method, and to enable positional tracking for a mobile-based one. While the desktop platform represents a non-immersive setting, the mobile one provides continuous AR in the physical environment. Both versions can be used to place virtual content and ultimately configure an AR experience. The authoring capabilities of the different platforms were compared by conducting a user study focused on evaluating their usability. Although the AR interface was generally considered more intuitive, the desktop platform shows promise in several aspects, such as remote configuration, lower required effort, and overall better scalability.

COVIR: A virtual rendering of a novel NN architecture O-Net for COVID-19 Ct-scan automatic lung lesions segmentation.

With the Coronavirus disease 2019 (COVID-19) spread, causing a world pandemic, and recently, the virus new variants continue to appear, making the situation more challenging and threatening, the visual assessment and quantification by expert radiologists have become costly and error-prone. Hence, there is a need to propose a model to predict the COVID-19 cases at the earliest possible to control the disease spread. In order to assist the medical professionals and reduce workload and the time the COVID-19 diagnosis cycle takes, this paper proposes a novel neural network architecture termed as O-Net to automatically segment chest Computerised Tomography Ct-scans infected by COVID-19 with optimised computing power and memory occupation. The O-Net consists of two convolutional autoencoders with an upsampling channel and a downsampling channel. Experimental tests show our proposal's effectiveness and potential, with a dice score of 0.86, pixel accuracy, precision, specificity of 0.99, 0.99, 0.98, respectively. Performance on the external dataset illustrates generalisation and scalability capabilities of the O-Net model to Ct-scan obtained from different scanners with different sizes. The second objective of this work is to introduce our virtual reality platform, COVIR, that visualises and manipulates 3D reconstructed lungs and segmented infected lesions caused by COVID-19. COVIR platform acts as a reading and visualisation support for medical practitioners to diagnose COVID-19 lung infection. The COVIR platform could be used for medical education professional practice and training. It was tested by Thirteen participants (medical staff, researchers, and collaborators), they conclude that the 3D VR visualisation of segmented Ct-Scan provides an aid diagnosis tool for better interpretation.

A Fitness Education and Scoring System Based on 3D Human Body Reconstruction

Affected by the Covid-19 epidemic, online fitness education has attracted a large number of users. However, when there are a large number of students in a same online classroom, it is difficult to get the coach’s advice and scores in time. To overcome this problem, we propose an AI fitness education system that uses 3D reconstruction technology to restore the shape of the human body and its bones. The skeleton is used for posture scoring. The 3D human body model is reconstructed by our improved VIBE network, with the accurate posture, shape and movement of the coach and students. By adding the loss function of the end limbs to the 3D human body model, compared with the performance of the original VIBE, we reduce the jitter noise in continuous motion. The training results show the accuracy of our improved VIBE. In addition, we have also established a scoring system, which can score the posture of the trainees based on the coach’s posture, and provide feedback through visual tag points. The experimental results show that our method is feasible and worthy of further exploration. © 2021, Springer Nature Switzerland AG.

A remote and immersive setup for pandemic-safe surgical education

Existing challenges in surgical education (See one, do one, teach one) as well as the Covid-19 pandemic make it necessary to develop new ways for surgical training. This is also crucial for the dissemination of new technological developments. As today's live transmissions of surgeries to remote locations always come with high information loss, e.g. stereoscopic depth perception, and limited communication channels. This work describes the implementation of a scalable remote solution for surgical training, called TeleSTAR (Telepresence for Surgical Assistance and Training using Augmented Reality), using immersive, interactive and augmented reality elements with a bi-lateral audio pipeline to foster direct communication. The system uses a full digital surgical microscope with a modular software-based AR interface, which consists of an interactive annotation mode to mark anatomical landmarks using an integrated touch panel as well as an intraoperative image-based stereo-spectral algorithm unit to measure anatomical details and highlight tissue characteristics.We broadcasted three cochlea implant surgeries in the context of otorhinolaryngology. The intervention scaled to five different remote locations in Germany and the Netherlands with lowlatency. In total, more than 150 persons could be reached and included an evaluation of a participant's questionnaire indicating that annotated AR-based 3D live transmissions add an extra level of surgical transparency and improve the learning outcome. © 2021 by Walter de Gruyter Berlin/Boston.

Crystal Structure of the SARS-CoV-2 Non-structural Protein 9, Nsp9.

Many of the SARS-CoV-2 proteins have related counterparts across the Severe Acute Respiratory Syndrome (SARS-CoV) family. One such protein is non-structural protein 9 (Nsp9), which is thought to mediate viral replication, overall virulence, and viral genomic RNA reproduction. We sought to better characterize the SARS-CoV-2 Nsp9 and subsequently solved its X-ray crystal structure, in an apo form and, unexpectedly, in a peptide-bound form with a sequence originating from a rhinoviral 3C protease sequence (LEVL). The SARS-CoV-2 Nsp9 structure revealed the high level of structural conservation within the Nsp9 family. The exogenous peptide binding site is close to the dimer interface and impacted the relative juxtapositioning of the monomers within the homodimer. We have established a protocol for the production of SARS-CoV-2 Nsp9, determined its structure, and identified a peptide-binding site that warrants further study to understanding Nsp9 function.

Conformational flexibility and structural variability of SARS-CoV2 S protein.

Spike (S) glycoprotein of SARS-CoV2 exists chiefly in two conformations, open and closed. Most previous structural studies on S protein have been conducted at pH 8.0, but knowledge of the conformational propensities under both physiological and endosomal pH conditions is important to inform vaccine development. Our current study employed single-particle cryoelectron microscopy to visualize multiple states of open and closed conformations of S protein at physiological pH 7.4 and near-physiological pH 6.5 and pH 8.0. Propensities of open and closed conformations were found to differ with pH changes, whereby around 68% of S protein exists in open conformation at pH 7.4. Furthermore, we noticed a continuous movement in the N-terminal domain, receptor-binding domain (RBD), S2 domain, and stalk domain of S protein conformations at various pH values. Several key residues involving RBD-neutralizing epitopes are differentially exposed in each conformation. This study will assist in developing novel therapeutic measures against SARS-CoV2.