Navigation Assistance Research Articles

Bayesian Gabor Network With Uncertainty Estimation for Pedestrian Lane Detection in Assistive Navigation

Automatic pedestrian lane detection is a challenging problem that is of great interest in assistive navigation and autonomous driving. Such a detection system must cope well with variations in lane surfaces and illumination conditions so that a vision-impaired user can navigate safely in unknown environments. This paper proposes a new lightweight Bayesian Gabor Network (BGN) for camera-based detection of pedestrian lanes in unstructured scenes. In our approach, each Gabor parameter is represented as a learnable Gaussian distribution using variational Bayesian inference. For the safety of vision-impaired users, in addition to an output segmentation map, the network provides two full-resolution maps of aleatoric uncertainty and epistemic uncertainty as well-calibrated confidence measures. Our Gabor-based method has fewer weights than the standard CNNs, therefore it is less prone to overfitting and requires fewer operations to compute. Compared to the state-of-the-art semantic segmentation methods, the BGN maintains a competitive segmentation performance while achieving a significantly compact model size (from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.8\times $ </tex-math></inline-formula> to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$237.6\times $ </tex-math></inline-formula> reduction), a fast prediction time (from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.2\times $ </tex-math></inline-formula> to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$67.5\times $ </tex-math></inline-formula> faster), and a well-calibrated uncertainty measure. We also introduce a new lane dataset of 10,000 images for objective evaluation in pedestrian lane detection research.

Financial Instability of Federal Navigator Program Challenges Organizations to Help Uninsured Enroll in Health Insurance Coverage.

Under the Affordable Care Act, the federal Health Insurance Navigator Program aims to reduce the rate of uninsured in the United States. Under this program, navigators help people obtain insurance coverage through federally facilitated Marketplaces. However, the program's financial instability and substantial budget cuts created a severe shortage of navigator assistance for the uninsured and underserved. The COVID-19 pandemic added further pressure to the already-strained program. Our study examined how unstable and unpredictable federal funding and the COVID-19 pandemic affected organizations' navigator work in the federal program in 2020. The results study show (1) that navigator organizations provide vital, year-round resources; (2) that organizations feel pushed to direct scarce resources to grant management and cut service provision; and (3) that there are policy changes that can support navigator organizations in the future. Increased and ongoing federal investment is needed to support this vital health workforce and expand enrollment assistance for underserved communities.

Uptake of lung cancer screening with low-dose computed tomography in China: A multi-centre population-based study.

SummaryBackgroundOptimal uptake rates of low-dose computed tomography (LDCT) scans are essential for lung cancer screening (LCS) to confer mortality benefits. We aimed to outline the process model of the LCS programme in China, identify the high-risk individuals with low uptake based on a prospective multi-centre population-based cohort, and further explore associated structural characteristics.MethodsA total of 221,955 individuals at high-risk for lung cancer from the National Lung Cancer Screening cohort were included. The logistic regression model was performed to identify the individual characteristics associated with the uptake of LCS, defined as whether the high-risk individual undertook LDCT scans in designated hospitals within six months following the initial risk assessment. The linear regression model was adopted to explore the structural characteristics associated with the uptake rates in 186 communities.FindingsThe overall uptake rate was 33·0%. The uptake rate was negatively correlated with the incidence of advanced-stage lung cancer (Pearson's coefficient −0·88, p-value 0·0007). Multivariable regression models found that lower uptake rates were associated with males (OR 0·88, 95%CI 0·85–0·91), current smokers (OR 0·93, 95%CI 0·90–0·96), individuals with depressive symptoms (OR 0·92, 95%CI 0·90–0·94), and the structural characteristics, including longer structural delays in initiating LDCT scans (30–90 days vs. ≤14 days: β −7·17, 95%CI −12·76∼ −1·57; >90 days vs. ≤14 days: β −13·69, 95%CI −24·61∼ −2·76), no media-assisted publicity (β −6·43, 95%CI −11·26∼ −1·60), and no navigation assistance (β −5·48, 95%CI −10·52∼ −0·44).InterpretationMultifaceted interventions are recommended, which focus on poor-uptake individuals and integrate the ‘assessment-to-timely-screening’ approach to minimise structural delays, media publicity, and a navigation assistance along the centralised screening pathway.FundingMinistry of Finance and National Health Commission of the People's Republic of China.

SWALKIT: A generic augmented walker kit to provide haptic feedback navigation assistance to people with both visual and motor impairments.

Feedback solutions are a privileged form of assistance in order to increase mobility and independence of people with both motor and visual impairments. Indeed, it empowers the ability of the person to make decisions and take actions based on the provided information. Moreover, it maintains the use of the walker, and thus the residual locomotor skills. We here propose the SWALKIT, an open-source, cost-efficient, lightweight, easy to install and generic augmented walker kit. The SWALKIT can be equipped on any walker without requiring modifications of the structure or advanced technical knowledge. Vibrotactile feedback is provided through the handles to indicate the proximity of obstacles on the way of the user. The open source project is reproducible thanks to the online repository https://github.com/IH2A/Swalkit. In this paper, we present the design of the SWALKIT based on a user-centered approach following target users and therapists guidelines. Then, we present a technical validation study performed with 14 able-bodied blindfolded participants on a cardboard circuit. They were asked to use a standard walker with and without activation of the SWALKIT system. Results of this pilot study showed the efficiency and reliability of the proposed solution. Finally, we provide feedback after 2 months of daily life use by a target user.

Redesigning navigational aids using virtual global landmarks to improve spatial knowledge retrieval

Although beacon- and map-based spatial strategies are the default strategies for navigation activities, today’s navigational aids mostly follow a beacon-based design where one is provided with turn-by-turn instructions. Recent research, however, shows that our reliance on these navigational aids is causing a decline in our spatial skills. We are processing less of our surrounding environment and relying too heavily on the instructions given. To reverse this decline, we need to engage more in map-based learning, which encourages the user to process and integrate spatial knowledge into a cognitive map built to benefit flexible and independent spatial navigation behaviour. In an attempt to curb our loss of skills, we proposed a navigation assistant to support map-based learning during active navigation. Called the virtual global landmark (VGL) system, this augmented reality (AR) system is based on the kinds of techniques used in traditional orienteering. Specifically, a notable landmark is always present in the user’s sight, allowing the user to continuously compute where they are in relation to that specific location. The efficacy of the unit as a navigational aid was tested in an experiment with 27 students from the University of Technology Sydney via a comparison of brain dynamics and behaviour. From an analysis of behaviour and event-related spectral perturbation, we found that participants were encouraged to process more spatial information with a map-based strategy where a silhouette of the compass-like landmark was perpetually in view. As a result of this technique, they consistently navigated with greater efficiency and better accuracy.

HAPT-EDGE: HAPTICS IN SOFT EFFECTORS FOR SMART INTERACTIVE ASSISTIVE FRAMEWORKS

Tactile sensors help in modeling the intrinsic and external touch sensation. Tactile sensing can refer to the touch in multiple points of contact and refer to the process of detecting and measuring a given property of a contact event in a predetermined area at multiple points of contact. The Haptic system helps in creating a “sense of touch” about the environment through stimuli at a single contact point. Effectors are the end point of robotic frameworks that interact with the real world. From prosthetic hands to precision grippers, effectors made of soft flexible materials have been used for various biomedical applications. The research goal of this project is to integrate haptics in soft effectors for two-way communication in an assistive framework. In this research, we will investigate the use of haptics for creating environmental awareness and for taking the user input. Modeling the user input using the haptics will include interpreting the hand gestures. The proposed framework will use the haptic signals at specific frequencies to provide sensor feedback and interpret the user’s hand gestures as user inputs for navigation assistance. In implementing such a framework, the research will also focus on the use of micro actuators or vibration motors for providing precise feedback. The framework will include custom-made soft effectors, robotic cane/walker, algorithms to model the user input, actuators, and vibration sensitive filaments for closing the loop. This research will significantly contribute to the next generation mobility assistive frameworks with interactive feature.

An Online Combined Compensation Method of Geomagnetic Measurement Error

The online error compensation of the three-axis magnetic sensor is the key to a high accuracy geomagnetic assisted navigation. Traditionally, the least squares or its improved methods are used for error compensation, which are offline and need to assume that measurement errors are Gaussian. In this paper, the geomagnetic measurement error is modeled based on the error source analysis, and then the compensation parameters are converted through the ellipsoid hypothesis. To eliminate the negative effect of abnormal values, iterative least squares is designed to calculate static compensation parameters and corresponding residuals, then different weights are assigned to each geomagnetic measurement data through robust estimation. Also, to avoid data saturation phenomenon and finally complete online error compensation, a forgetting factor is introduced into the iterative least squares, and the dynamic coefficients are constructed by weights of measurement data to derive the online updated compensation parameters. Simulation and experiment results both show that the online combined compensation method possesses higher adaptability, which can eliminate the influence of abnormal data effectively. And its accuracy and stability of error compensation are better than other state-of-the-art methods.

Corrective osteotomy for complex tibial deformity in a patient with hereditary vitamin D-resistant hypophosphatemic rickets (HVDRR) using CT-based navigation system and 3D printed osteotomy model

Planning a three-dimensional (3D) osteotomy using computed tomography (CT) data is useful especially in cases with complex deformities. Furthermore, CT-based navigation system allows the preoperative virtual planning to be replicated in actual surgery. However, one disadvantage when using navigation systems is that when osteotomies are performed on tracker-attached bone, the bone fragments on the side that were cut away cannot be tracked. This is especially problematic when performing multiple osteotomies on bones with complex deformities. We solved this problem by creating a 3D printed bone model that can be referenced intraoperatively and used in combination with the navigation system. We applied these techniques to perform segmental corrective osteotomy for a complex tibial deformity with intramedullary nail (IMN) fixation case of hereditary vitamin D-resistant hypophosphatemic rickets (HVDRR) in an adult man. Due to the patient’s history of multiple surgeries, the affected tibia had a narrow and partially closed medullary canal. Therefore, we planned to use an IMN for correction and fixation of tibial deformity to protect the thin and stretched skin around the deformed tibia. With the assistance of CT-based navigation, we could perform an accurate three-dimensional tibial osteotomy. Moreover, we could perform accurate preparation of closed medullary canal for the IMN placement by referring to the 3D printed bone models. Six months after the operation, the bone union at the osteotomy sites was confirmed and the patient was able to return to his normal life and work.

Computer-Navigated and Robotic-Assisted Total Knee Arthroplasty: Increasing in Popularity Without Increasing Complications

BackgroundData on the clinical impact of computer navigation (CN) and robotic assistance (RA) in total knee arthroplasty (TKA) are mixed. This study aims to describe modern utilization trends in CN-TKA, RA-TKA, and traditionally-instrumented (TD) TKA and to assess for differences in postoperative complications and opioid consumption by procedure type. MethodsA national database was queried to identify primary, elective TKA patients from 2015 to 2020. Trends in procedural utilization rates were assessed. Differences in 90-day postoperative complications and inpatient opioid consumption were assessed. Multivariate regression analyses were performed to account for potential confounders. ResultsOf the 847,496 patients included, 49,317 (5.82%) and 24,460 (2.89%) underwent CN-TKA and RA-TKA, respectively. CN-TKA utilization increased from 5.64% (2015) to 6.41% (2020) and RA-TKA utilization increased from 0.84% (2015) to 5.89% (2020). After adjusting for confounders, CN-TKA was associated with lower periprosthetic joint infection (P = .001), pulmonary embolism (P < .001), and acute respiratory failure (P = .015) risk compared to traditional (TD) TKA. RA-TKA was associated with lower deep vein thrombosis (P < .001), myocardial infarction (P = .013), and pulmonary embolism (P = .001) risk than TD-TKA. Lower postoperative day 1 opioid usage was seen with CN-TKA and RA-TKA than TD-TKA (P < .001). Lower postoperative day 0 opioid consumption was also seen in RA-TKA (P < .001). ConclusionFrom 2015 to 2020, there was a relative 13.7% and 601.2% increase in CN-TKAs and RA-TKAs, respectively. This trend was associated with reductions in hospitalization duration, postoperative complications, and opioid consumption. These data support the safety of RA-TKA and CN-TKA compared to TD-TKA. Further investigation into the specific indications for these technology-assisted TKAs is warranted.

Usability of a navigation application for travel in Quebec City with wheeled mobility device and, further validation of the Evaluation of satisfaction with geospatial assistive technology

Purpose Knowledge of route accessibility is indispensable for “wheeled mobility device” users to travel safely and efficiently; however, current navigation technologies hardly provide adapted information for this population. Aims of the study were to collect data on the usability of a navigation application and to propose a version 1.0 of the Evaluation of satisfaction with geospatial assistive technology (ESGAT), by addressing the criterion, construct and cross-cultural validities. Method A filmed field trial and a methodological study were conducted in parallel. Thirty wheeled mobility device users were filmed planning and making a 10-minute known journey using the HERE WeGo app. The ESGAT, ÉSTGA (French version) and the Computer System Usability Questionnaire were administered. A video observation grid addressed the effectiveness and efficiency during the journey. Descriptive, correlation and multiple match analyses were performed. Results Fourteen men and 16 women averaging 45.9 years old tried out HERE WeGo; 14 were powered wheelchair users. Usability of the app was moderate (good effectiveness, moderate efficiency and quite satisfied). The criterion validity of the ÉSTGA was good (r = 0.598; p < 0.001). The construct validity was average considering the results for factor 1 (α = 0.789, acceptable), factor 2 (α = 0,586, low) and factor 3 (α = 0.409, unacceptable). The cross-cultural validity (French vs English) was moderate (r = 0.861; p < 0.001). Conclusion ESGAT and ÉSTGA 1.0 questionnaires are now available in English and French with a total mean score (11 items), an informatics subscore (mean of 5 items) and a geomatic subscore (mean of 6 items). Their validation should be pursued with new navigation applications. IMPLICATIONS FOR REHABILITATION Clinicians should ask their clients using a wheeled mobility device to test navigation applications to ensure their safety and complete the Evaluation of satisfaction with geospatial assistive technology (ESGAT 1.0), also available in French. Clinicians should inquire about satisfaction for items addressing informatics (Ease of access, Learnability, Hands-free function, Ease of use, Transportability and Appearance) and items addressing geomatic (Content, Geographic information, Effectiveness, Efficiency, Real-time navigation assistance, Aspect of security). Rehabilitation clinicians should inquire about the efficiency of the navigation app, considering avoiding or announcing potential obstacles such as: travelling on the street for a long portion of the trip and not on the sidewalk; verbal indication too soon or too late; incorrect indication; damaged, and congested sidewalk.

A Lightweight and Privacy-Preserving Mutual Authentication and Key Agreement Protocol for Internet of Drones Environment

With accelerated advances in various technologies, drones, better known as unmanned aerial vehicles (UAVs), are increasingly commonplace and consequently have a more pronounced impact on society. For example, Internet of Drones (IoD), a new communication paradigm offering fundamental navigation assistance and access to information, has widespread applications ranging from agricultural drones in farming to surveillance drones in the COVID-19 pandemic. The increasingly prominent role of IoD in our society also reinforces the importance of securing such systems against various data privacy and security threats. Operationally, it can be challenging to adopt conventional off-the-shelf security products in an IoD system due to the underpinning characteristics of drones (e.g., dynamic and open communication channel). Therefore in this article, we propose a lightweight and privacy-preserving mutual authentication and key agreement protocol, hereafter referred to as PMAP. The latter uses a physical unclonable function (PUF) and chaotic system to support mutual authentication and establish a secure session key between communication entities in the IoD system. To be specific, PMAP consists of two schemes, namely: 1) <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${\mathrm{ PMAP}}^{D2Z}$ </tex-math></inline-formula> (that mutually authenticates drone and zone service provider (ZSP) and establishes secure session keys) and 2) <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${\mathrm{ PMAP}}^{D2D}$ </tex-math></inline-formula> (that mutually authenticates drones and establishes secure session keys). In addition, PMAP supports conditional privacy preserving so that the genuine identity of drones can only be revealed by trusted ZSPs. We evaluate the security of PMAP using automated validation of Internet security protocols and application (AVISPA), as well as provide formal and informal security analysis to show the resilience of PMAP against various security attacks. We also evaluate the performance of PMAP through extensive experiments and compare its performance with existing AKA and IBE-Lite schemes, whose findings show that PMAP achieves better performance in terms of computation cost, energy consumption, and communication overhead.

Gaining insight for the design, development, deployment and distribution of assistive navigation systems for blind and visually impaired people through a detailed user requirements elicitation

Gaining insight for the design, development, deployment and distribution of assistive navigation systems for blind and visually impaired people through a detailed user requirements elicitation

Complications Associated With Ventriculoperitoneal Shunt Surgery for Normal Pressure Hydrocephalus Using Stereotactic Navigation and Abdominal Laparoscopy: A Single-Institution Case Series.

Normal pressure hydrocephalus (NPH) is characterized by cerebral ventriculomegaly and the triad of magnetic gait, urinary incontinence, and cognitive impairment. Treatment includes ventriculoperitoneal (VP) shunt surgery. To evaluate complication rates in a cohort of patients undergoing VP shunt surgery with stereotactic proximal catheter navigation and laparoscopic distal catheter placement. This study was a retrospective consecutive cohort analysis of 117 patients with NPH undergoing VP shunt placement using both stereotactic navigation and laparoscopy from 2015 to 2020. Patients with obstructive hydrocephalus and those with central nervous system infection, intraventricular hemorrhage, Ommaya reservoirs, or undergoing shunt revision at initial encounter were excluded. Variables included demographics and comorbidities, NPH symptoms, operative details, radiographic outcomes, and rates of complications, readmissions, and reoperations within 1, 3, and 12 months. Impact of demographics and comorbidities on complication rates was assessed using Fisher exact tests. Zero patients required reoperation within 30 days. One intracranial hemorrhage was detected on immediate postoperative head computed tomography. Four patients ultimately required revision: 2 for catheter repositioning to alleviate abdominal pain, 1 ligation for a colectomy, and 1 removal for shunt infection. Patients with cardiac or other neurological comorbidities had higher rates of readmission and complications. Systemic complications totaled 12% in the first 30 days. The combination of intraoperative stereotactic navigation and laparoscopic assistance leads to low rates of serious complications and reoperations for VP shunt implantation in patients with NPH. These changes to surgical technique are easy to implement and may reduce the risk for this common operation.

Laser Navigation Combined With XperCT Technology Assisted Puncture of Brainstem Hemorrhage.

BackgroundBrainstem hemorrhage has a rapid onset with high mortality and disability rates. In recent years, an increasing number of studies have reported on the surgical treatment of brainstem hemorrhage. The introduction of stereotaxic instruments and navigation systems has improved the accuracy of surgical treatment; however, the popularity of these devices in the primary hospitals is not high. In this study, we introduce laser navigation combined with the XperCT technology to assist in the puncture and drainage of brainstem hemorrhage, aiming to improve surgical accuracy and facilitate the drainage of brainstem hemorrhage in primary hospitals.Material and MethodsA total of five patients (four men and one woman), aged 34–70 years, who underwent hematoma puncture drainage with the assistance of laser navigation combined with XperCT technology at the Binzhou Medical University Hospital, China, between June 2020 and Aug 2021 were included in the study. The brainstem hemorrhages had volumes of 7–18 ml. Statistical analyses of the postoperative puncture deviation distance (distance between the actual puncture end and simulated puncture end) and postoperative improvement were also performed.ResultsThe operations were successfully completed in all five patients. The puncture deviation distance was <6 mm in all five patients and <2 mm in two patients. The postoperative hematoma clearance rate was about 70%−90%. Among four patients with respiratory failure, three had improved breathing and resumed spontaneous breathing. Out of three patients with high fever, one showed a substantial decrease in body temperature. There were no cases of postoperative infection. Of the five patients, two recovered consciousness, one died, and two voluntarily gave up further treatment and were discharged.ConclusionsLaser navigation combined with the XperCT technology could improve the accuracy of surgical puncture. The technique might be convenient for widespread clinical application because of its low trauma, high precision, short operation time, and low operation cost.

The Effect of Peer-Led Navigation Approach as a Form of Task Shifting in Promoting Cervical Cancer Screening Knowledge, Intention, and Practices Among Urban Women in Tanzania: A Randomized Controlled Trial.

BackgroundEven though the government’s priorities in preventing cervical cancer are implemented in urban areas, the screening rate remains unsatisfactory at 6%, compared to 70% recommended by the world health organization. The ongoing public health education has not resulted in sufficient screening rates. The study aims to assess peer-led navigation (PLNav) in promoting cervical cancer screening knowledge, intention, and practices among urban women in Tanzania. Since PLNav is the form of task shifting, it involves delegating cervical-cancer-related tasks from healthcare professionals to community health workers (CHWs).MethodsIt is a community-based randomized controlled trial conducted in Dar es Salaam in Tanzania March-Sept 2020. The PLNav involved the CHWs delivering health education, counselling and navigation assistance to community women (COMW). The CHWs help women who have never undergone cervical cancer screening (CCS) and those who have undergone CCS but with a precancerous cervical lesion to overcome screening barriers. The data related to PLNav were analyzed by descriptive statistics, an independent-samples t-test, repeated measures ANOVA and linear regression.ResultsThe repeated measures ANOVA across time showed that PLNav intervention on mean knowledge score changes was statistically significant in the intervention group compared with the control group’s usual care, [F (1, 43) = 56.9, P < .001]. At the six-month follow-up, 32 (72.7%) out of 44 participants from the intervention group had screened for cervical cancer, and only one participant (2.3%) from the control group screened. The PLNav intervention on CCS uptake changes was statistically significant in the intervention group compared with usual care in the control group [F (1, 43) = 100.4, P < .001]. The effect of time on CCS uptake in the intervention and control groups was statistically significant [F (1.64, 70.62) = 73.4, P < .001].ConclusionPeer-led navigation (PLNav) was effective in promoting cervical cancer screening knowledge, intention, and uptake.

Brief Report: Heterogeneous Preferences for Care Engagement Among People With HIV Experiencing Homelessness or Unstable Housing During the COVID-19 Pandemic.

In San Francisco, HIV viral suppression is 71% among housed individuals but only 20% among unhoused individuals. We conducted a discrete choice experiment at a San Francisco public HIV clinic to evaluate care preferences among people living with HIV (PLH) experiencing homelessness/unstable housing during the COVID-19 pandemic. From July to November 2020, we conducted a discrete choice experiment among PLH experiencing homelessness/unstable housing who accessed care through (1) an incentivized, drop-in program (POP-UP) or (2) traditional primary care. We investigated 5 program features: single provider vs team of providers; visit incentives ($0, $10, and $20); location (current site vs current + additional site); drop-in vs scheduled visits; in-person only vs optional telehealth visits; and navigator assistance. We estimated relative preferences using mixed-effects logistic regression and conducted latent class analysis to evaluate preference heterogeneity. We enrolled 115 PLH experiencing homelessness/unstable housing, 40% of whom lived outdoors. The strongest preferences were for the same provider (β = 0.94, 95% CI: 0.48 to 1.41), visit incentives (β = 0.56 per $5; 95% CI: 0.47 to 0.66), and drop-in visits (β = 0.47, 95% CI: 0.12 to 0.82). Telehealth was not preferred. Latent class analysis revealed 2 distinct groups: 78 (68%) preferred a flexible care model, whereas 37 (32%) preferred a single provider. We identified heterogeneous care preferences among PLH experiencing homelessness/unstable housing during the COVID-19 pandemic, with two-thirds preferring greater flexibility and one-third preferring provider continuity. Telehealth was not preferred, even with navigator facilitation. Including patient choice in service delivery design can improve care engagement, particularly for marginalized populations, and is an essential tool for ending the HIV epidemic.

Research on the internet of vehicles assisted traffic management systems for observing traffic density

Computer vision (CV) in a modern smart city is to be relied upon to deliver interactive and user-satisfying applications. CV is responsible for identifying humans and objects, among others, through which interactive applications are designed. The interacting machine handles visual inputs and processes them to provide quality responses to users. An artificial intelligence (AI) field known as computer vision (CV) is used to train computers in real-world applications to interact with the visual world. The internet of vehicles assisted traffic management system based on computer vision ((IoVTMS-CV) roadside pedestrian process is discussed to monitor and evaluate human movements depending on their location and deviation from previous time intervals. Traffic density and observations were interactively shared with the vehicles through navigation assistance based on these detections. In this method, convolutional neural learning has been used to identify the deviations over different time intervals. The variations were identified as incoherent with the standard patterns defined for roadside traffic management. The experiment's results show it's at least 37% more effective than traditional methods.

Route learning with augmented reality navigation aids

Current trends point towards the development and implementation of augmented reality (AR) navigation assistance systems for drivers. Previous research has found augmented reality can benefit driving performance, but the impact of AR on route learning (spatial knowledge acquisition) has received less attention. The current study used simulated driving scenarios to determine how the type of navigation aid device used (i.e., paper map, electronic map, and AR system) affected driving performance and route learning of 62 driving adults. Route learning was examined at landmark, route, and survey levels. The hypotheses tested were that AR would improve driving performance but diminish route learning compared to paper map use; and that AR would outperform electronic map use in both driving performance and route learning. Results indicated that paper map use led to poorer driving performance and greater route learning. However, map recognition may have been a confounding factor in higher level spatial knowledge acquisition with paper map use. Driving performance and route learning were similar for drivers using the electronic map and AR, but some differences suggested that drivers have reduced uncertainty and hesitation while using AR to navigate in unfamiliar areas.

Development and validation of an automated planning tool for navigated lumbosacral pedicle screws using a convolutional neural network

Background contextNavigation and robotic systems have been increasingly applied to spinal instrumentation but dedicated screw planning is a time-consuming prerequisite to tap the full potential of these techniques. PurposeTo develop and validate an automated planning tool for lumbosacral pedicle screw placement using a convolutional neural network (CNN) to facilitate the planning process. Study Design/SettingRetrospective analysis and processing of CT and screw planning data randomly selected from a consecutive registry of CT-navigated instrumentations from a single academic institution. Patient SampleData from 179 cases was processed for CNN training and validation (155 for training, 24 for validation) leveraging a total of 1182 screws (1052 for training, 130 for validation). Outcome MeasuresQuantitative and qualitative (Gertzbein-Robbins classification [GR]) validation via comparison of automatically and manually planned reference screws, inter-rater and intra-rater variability. MethodsAnnotated data from CT-navigated instrumentation was used to train a CNN operating in a vertebra instance-based approach employing a state-of-the-art U-Net framework. Internal five-fold cross-validation and external validation on an independent cohort not previously involved in training was performed. Quantitative validation of automatically planned screws was performed in comparison to corresponding manually planned screws by calculating the minimal absolute difference (MAD) of screw head and tip points, length and diameter, screw direction and Dice coefficient. Results were evaluated in relation to inter-rater and intra-rater variability of manual screw planning. ResultsAutomated screw planning was successful in all targeted 130 screws. Compared with manually planned screws as a reference, mean MAD of automatically planned screws was 4.61±2.27 mm for screw head, 3.96±2.19 mm for tip points and 5.51±3.64° for screw direction. These differences were either statistically comparable or significantly smaller when compared with interrater variability of manual screw planning (p>.99 for head point and direction, p=.004 for tip point, respectively). Mean Dice coefficient of 0.61±0.16 indicated significantly greater agreement of automatic screws with the manual reference compared with interrater agreement (Dice 0.56±0.18, p<.001). Automatically planned screws were marginally shorter (MAD 3.4±3.2 mm) and thinner (MAD mean 0.3±0.6 mm) compared with the manual reference, but with statistical significance (p<.0001, respectively). Automatically planned screws were GR grade A in 96.2% in qualitative validation. Planning time was significantly shorter with the automatic approach (0:41 min vs. 6:41 min, p<.0001). ConclusionsWe derived and validated a fully automated planning tool for lumbosacral pedicle screws using a CNN. Our validation showed noninferiority to manual screw planning and provided sufficient accuracy to facilitate and expedite the screw planning process. These results offer a high potential to improve workflows in spine surgery when integrated into navigation or robotic assistance systems.

The "Eiffel Tower" technique: novel long-axis sacroplasty under electromagnetic navigation assistance; feasibility and descriptive study.

To describe a novel long-axis multimodal navigation assisted technique - the so-called Eiffel Tower technique - aimed at integrating recent technological improvements for the routine treatment of sacral insufficiency fractures. The long-axis approach described in the present study aimed at consolidating the sacral bone according to biomechanical considerations. The purpose was (i) to cement vertically the sacral alae all along and within the lateral fracture lines, resembling the pillars of a tower, and (ii) to reinforce cranially with a horizontal S1 landing zone (or dense central bone) resembling the first level of the tower. An electromagnetic navigation system was used in combination with CT and fluoroscopic guidance to overtop extreme angulation challenges. All patients treated between January 2019 and October 2021 in a single tertiary center were retrospectively reviewed. A description of the technique is provided. Twelve female patients (median age: 80 years [range: 32 to 94]) were treated for sacral insufficiency fractures with the "Eiffel Tower" technique. The median treatment delay was 8 weeks (range: 3 to 20) and the initial median pain assessed by the visual analogue scale was 7 (range: 6 to 8). Pain was successfully relieved (visual analogue score < 3) for 9 patients (75%) and persisted for 2 patients (17%). One patient was lost during the follow-up. No complication was noted. The "Eiffel Tower" multimodal cementoplasty integrates recent technological developments, in particular electromagnetic navigation, with the purpose of reconstructing the biomechanical chain of the sacral bone. • Sacral insufficiency fractures are common and can be efficiently treated with percutaneous sacroplasty. • The long axis sacroplasty approach can be challenging given both the shape of the sacral bone and the angulation to reach the target lesion. • The "Eiffel Tower" technique is a novel approach using electromagnetic navigation to expand the concept of the long axis route, adding a horizontal S1 landing zone.