Search Results (81)

The registration of preoperative and follow-up brain MRI, which is crucial in illustrating patients’ responses to treatments and providing guidance for postoperative therapy, presents significant challenges. These challenges stem from the considerable deformation of brain tissue and the areas of non-correspondence due to surgical intervention and postoperative changes. We propose a stepwise corrected attention registration network grounded in convolutional neural networks (CNNs). This methodology leverages preoperative and follow-up MRI scans as fixed images and moving images, respectively, and employs a multi-level registration strategy that establishes a precise and holistic correspondence between images, from coarse to fine. Furthermore, our model introduces a corrected attention module into the multi-level registration network that can generate an attention map at the local level through the deformation fields of the upper-level registration network and pathological areas of preoperative images segmented by a mature algorithm in BraTS, serving to strengthen the registration accuracy of non-correspondence areas. A comparison between our scheme and the leading approach identified in the MICCAI’s BraTS-Reg challenge indicates a 7.5% enhancement in the target registration error (TRE) metric and improved visualization of non-correspondence areas. These results illustrate the better performance of our stepwise corrected attention registration network in not only enhancing the registration accuracy but also achieving a more logical representation of non-correspondence areas. Thus, this work contributes significantly to the optimization of the registration of brain MRI between preoperative and follow-up scans. Full article

Small UAV target detection and tracking based on cross-modality image fusion have gained widespread attention. Due to the limited feature information available from small UAVs in images, where they occupy a minimal number of pixels, the precision required for detection and tracking algorithms is particularly high in complex backgrounds. Image fusion techniques can enrich the detailed information for small UAVs, showing significant advantages under extreme lighting conditions. Image registration is a fundamental step preceding image fusion. It is essential to achieve accurate image alignment before proceeding with image fusion to prevent severe ghosting and artifacts. This paper specifically focused on the alignment of small UAV targets within infrared and visible light imagery. To address this issue, this paper proposed a cross-modality image registration network based on deep learning, which includes a structure preservation and style transformation network (SPSTN) and a multi-level cross-attention residual registration network (MCARN). Firstly, the SPSTN is employed for modality transformation, transferring the cross-modality task into a single-modality task to reduce the information discrepancy between modalities. Then, the MCARN is utilized for single-modality image registration, capable of deeply extracting and fusing features from pseudo infrared and visible images to achieve efficient registration. To validate the effectiveness of the proposed method, comprehensive experimental evaluations were conducted on the Anti-UAV dataset. The extensive evaluation results validate the superiority and universality of the cross-modality image registration framework proposed in this paper, which plays a crucial role in subsequent image fusion tasks for more effective target detection. Full article

Internet of Things (IoT) technology is evolving over the peak of smart infrastructure with the participation of IoT devices in a wide range of applications. Traditional IoT authentication methods are vulnerable to threats due to wireless data transmission. However, IoT devices are resource- and energy-constrained, so building lightweight security that provides stronger authentication is essential. This paper proposes a novel, two-layered multi-factor authentication (2L-MFA) framework using blockchain to enhance IoT devices and user security. The first level of authentication is for IoT devices, one that considers secret keys, geographical location, and physically unclonable function (PUF). Proof-of-authentication (PoAh) and elliptic curve Diffie–Hellman are followed for lightweight and low latency support. Second-level authentication for IoT users, which are sub-categorized into four levels, each defined by specific factors such as identity, password, and biometrics. The first level involves a matrix-based password; the second level utilizes the elliptic curve digital signature algorithm (ECDSA); and levels 3 and 4 are secured with iris and finger vein, providing comprehensive and robust authentication. We deployed fuzzy logic to validate the authentication and make the system more robust. The 2L-MFA model significantly improves performance, reducing registration, login, and authentication times by up to 25%, 50%, and 25%, respectively, facilitating quicker cloud access post-authentication and enhancing overall efficiency. Full article

Objective: This study aimed to evaluate the effect of health education intervention (HEI) on maternal health service utilization (MHSU) in southern Ethiopia. Methods: From 10 January to 1 August 2023, a community-based, two-arm, parallel-group cluster randomized controlled trial (cRCT) was conducted among pregnant mothers in the Northern Zone of Sidama National Regional State, Ethiopia. We utilized multilevel mixed-effects modified Poisson regression with robust variance to control for the effects of clustering and potential confounders. The level of significance was adjusted for multiple comparisons. Results: The overall utilization of at least one antenatal care (ANC) visit was 90.2% in the treatment group and 59.5% in the comparator group (χ² = 89.22, p < 0.001). Health facility delivery (HFD) utilization was considerably different between the treatment group (74.3%) and the comparator group (50.8%) (χ² = 70.50, p < 0.001). HEI significantly increased ANC utilization (adjusted risk ratio [ARR]: 1.32; 99% CI: 1.12–1.56) and HFD utilization (ARR: 1.24; 99% CI: 1.06–1.46). The utilization of at least one postnatal care (PNC) service was 65.4% in the treatment group and 52.1% in the comparator group (χ² = 19.51, p = 0.01). However, after controlling for the effects of confounders and clustering, the impact of HEI on PNC utilization was insignificant between the two groups (ARR: 1.15; 99% CI: 0.89–1.48). Conclusion: A community-based HEI significantly increased ANC and HFD utilization but did not increase PNC utilization. Expanding the HEI with certain modifications will have a superior effect on improving MHSU. Trial registration number: NCT05865873. Full article

Spatial registration is a prerequisite for data fusion. Existing methods primarily focus on similar sensor scenarios and rely on accurate data association assumptions. To address the heterogeneous sensor registration in complex data association scenarios, this paper proposes a Gaussian mixture probability hypothesis density (GM-PHD)-based algorithm for heterogeneous sensor bias registration, accompanied by an adaptive measurement iterative update algorithm. Firstly, by constructing augmented target state motion and measurement models, a closed-form expression for prediction is derived based on Gaussian mixture (GM). In the subsequent update, a two-level Kalman filter is used to achieve an approximate decoupled estimation of the target state and measurement bias, taking into account the coupling between them through pseudo-likelihood. Notably, for heterogeneous sensors that cannot directly use sequential update techniques, sequential updates are first performed on sensors that can obtain complete measurements, followed by filtering updates using extended Kalman filter (EKF) sequential update techniques for incomplete measurements. When there are differences in sensor quality, the GM-PHD fusion filter based on measurement iteration update is sequence-sensitive. Therefore, the optimal subpattern assignment (OSPA) metric is used to optimize the fusion order and enhance registration performance. The proposed algorithms extend the multi-target information-based spatial registration algorithm to heterogeneous sensor scenarios and address the impact of different sensor-filtering orders on registration performance. Our proposed algorithms significantly improve the accuracy of bias estimation compared to the registration algorithm based on significant targets. Under different detection probabilities and clutter intensities, the average root mean square error (RMSE) of distance and angular biases decreased by 11.8% and 8.6%, respectively. Full article

Infrared and visible remote sensing image registration is significant for utilizing remote sensing images to obtain scene information. However, it is difficult to establish a large number of correct matches due to the difficulty in obtaining similarity metrics due to the presence of radiation variation between heterogeneous sensors, which is caused by different imaging principles. In addition, the existence of sparse textures in infrared images as well as in some scenes and the small number of relevant trainable datasets also hinder the development of this field. Therefore, we combined data-driven and knowledge-driven methods to propose a Radiation-variation Insensitive, Zero-shot learning-based Registration (RIZER). First, RIZER, as a whole, adopts a detector-free coarse-to-fine registration framework, and the data-driven methods use a Transformer based on zero-shot learning. Next, the knowledge-driven methods are embodied in the coarse-level matches, where we adopt the strategy of seeking reliability by introducing the HNSW algorithm and employing a priori knowledge of local geometric soft constraints. Then, we simulate the matching strategy of the human eye to transform the matching problem into a model-fitting problem and employ a multi-constrained incremental matching approach. Finally, after fine-level coordinate fine tuning, we propose an outlier culling algorithm that only requires very few iterations. Meanwhile, we propose a multi-scene infrared and visible remote sensing image registration dataset. After testing, RIZER achieved a correct matching rate of 99.55% with an RMSE of 1.36 and had an advantage in the number of correct matches, as well as a good generalization ability for other multimodal images, achieving the best results when compared to some traditional and state-of-the-art multimodal registration algorithms. Full article

In the last ten years, technological innovations have led to the development of new, advanced sensory stimulation (SS) tools, such as PC-based rehabilitative programs or virtual reality training. These are meant to stimulate residual cognitive abilities and, at the same time, assess cognition and awareness, also in patients with a minimally conscious state (MCS). Our purpose was to evaluate the clinical and neurophysiological effects of multi-sensory and emotional stimulation provided by Neurowave in patients with MCS, as compared to a conventional SS treatment. The psychological status of their caregivers was also monitored. In this retrospective study, we have included forty-two MCS patients and their caregivers. Each MCS subject was included in either the control group (CG), receiving a conventional SS, or the experimental group (EG), who was submitted to the experimental training with the Neurowave. They were assessed before (T0) and after the training (T1) through a specific clinical battery, including both motor and cognitive outcomes. Moreover, in the EG, we also monitored the brain electrophysiological activity (EEG and P300). In both study groups (EG and CG), the psychological caregiver’s aspects, including anxiety levels, were measured using the Zung Self-Rating Anxiety Scale (SAS). The intra-group analysis (T0-T1) of the EG showed statistical significances in all patients’ outcome measures, while in the CG, we found statistical significances in consciousness and awareness outcomes. The inter-group analysis between the EG and the CG showed no statistical differences, except for global communication skills. In conclusion, the multi-sensory stimulation approach through Neurowave was found to be an innovative rehabilitation treatment, also allowing the registration of brain activity during treatment. Full article

The role of hydrogen as a clean energy source is a promising but also a contentious issue. The global energy production is currently characterized by an unprecedented shift to renewable energy sources (RES) and their technologies. However, the local and environmental benefits of such RES-based technologies show a wide variety of technological maturity, with a common mismatch to local RES stocks and actual utilization levels of RES exploitation. In this literature review, the collected documents taken from the Scopus database using relevant keywords have been organized in homogeneous clusters, and are accompanied by the registration of the relevant studies in the form of one figure and one table. In the second part of this review, selected representations of typical hydrogen energy system (HES) installations in realistic in-field applications have been developed. Finally, the main concerns, challenges and future prospects of HES against a multi-parametric level of contributing determinants have been critically approached and creatively discussed. In addition, key aspects and considerations of the HES-RES convergence are concluded. Full article

Background: Chronic spinal cord injury (SCI) significantly accelerates morbidity and mortality, partly due to the increased risk of cardiometabolic diseases (CMD), including neurogenic obesity, dyslipidemia, and impaired glucose metabolism. While exercise and dietary interventions have shown some transient benefits in reducing CMD risk, they often fail to improve clinically relevant disease markers and cardiovascular events. Moreover, SCI also places caregiving demands on their caregivers, who themselves experience health and functional decline. This underscores the need for more substantial interventions that incorporate appropriate physical activity, heart-healthy nutrition, and behavioral support tailored to the SCI population. Objectives: This randomized clinical trial (RCT) protocol will (1) assess the health and functional effects, user acceptance, and satisfaction of a 6-month comprehensive therapeutic lifestyle intervention (TLI) adapted from the National Diabetes Prevention Program (DPP) for individuals with chronic SCI and (2) examine the impact of a complementary caregiver program on the health and function of SCI caregivers and evaluate user acceptance and satisfaction. Caregivers (linked with their partners) will be randomized to ‘behavioral support’ or ‘control condition’. Methods: Dyadic couples comprise individuals with SCI (18–65 years, >1-year post-injury, ASIA Impairment Scale A-C, injury levels C5-L1) and non-disabled SCI caregivers (18–65 years). Both groups undergo lock-step circuit resistance training, a calorie-restricted Mediterranean-style diet, and 16 educational sessions focused on diet/exercise goals, self-monitoring, psychological and social challenges, cognitive behavioral therapy, and motivational interviewing. The outcome measures encompass the cardiometabolic risks, cardiorespiratory fitness, inflammatory stress, multidimensional function, pain, life quality, independence, self-efficacy, program acceptance, and life satisfaction for SCI participants. The caregiver outcomes include multidimensional function, pain, quality of life, independence, and perceived caregiver burden. Discussion/Conclusions: This study evaluates the effects and durability of a structured, multi-modal intervention on health and function. The results and intervention material will be disseminated to professionals and consumers for broader implementation. Trial Registration: ClinicalTrials.gov, ID: NCT02853149 Registered 2 August 2016. Full article

The accurate and efficient segmentation of large-scale urban point clouds is crucial for many higher-level tasks, such as boundary line extraction, point cloud registration, and deformation measurement. In this paper, we propose a novel supervoxel segmentation approach to address the problem of under-segmentation in local regions of point clouds at various resolutions. Our approach introduces distance constraints from boundary points to supervoxel planes in the merging stage to enhance boundary segmentation accuracy between non-coplanar supervoxels. Additionally, supervoxels with roughness above a threshold are re-segmented using random sample consensus (RANSAC) to address multi-planar coupling within local areas of the point clouds. We tested the proposed method on two publicly available large-scale point cloud datasets. The results show that the new method outperforms two classical methods in terms of boundary recall, under-segmentation error, and average entropy in urban scenes. Full article

Background: With the removal of many barriers to direct-to-consumer telehealth during the COVID-19 pandemic, which resulted in a historic surge in the adoption of telehealth into ongoing practice, health systems must now identify the most efficient and effective way to sustain these visits. The Medical University of South Carolina Center for Telehealth developed a Telehealth Centralized Support team as part of a strategy to mature the support infrastructure for the continued large-scale use of outpatient virtual care. The team was deployed as the Center for Telehealth rolled out a new ambulatory telehealth software platform to monitor clinical activity, support patient registration and virtual rooming, and ensure successful visit completion. Methods: A multi-method, program-evaluation approach was used to describe the development and composition of the Telehealth Centralized Support Team in its first 18 months utilizing the Reach, Effectiveness, Adoption, Implementation, Maintenance framework. Results: In the first 18 months of the Telehealth Centralized Support team, over 75,000 visits were scheduled, with over 1500 providers serving over 46,000 unique patients. The team was successfully deployed over a large part of the clinical enterprise and has been well received across the health system. It has proven to be a scalable model to support enterprise-level virtual health care delivery. Conclusions: While further research is needed to evaluate the long-term program outcomes, the results of its early implementation suggest great promise for improved telehealth patient and provider satisfaction, the more equitable delivery of virtual services, and more cost-effective means for supporting virtual care. Full article

A single receptive field limits the expression of multilevel receptive field features in point cloud registration, leading to the pseudo-matching of objects with similar geometric structures in low-overlap scenes, which causes a significant degradation in registration performance. To handle this problem, a point cloud registration network that incorporates dense graph convolution and a mutilevel interaction Transformer (GCMTN) in pursuit of better registration performance in low-overlap scenes is proposed in this paper. In GCMTN, a dense graph feature aggregation module is designed for expanding the receptive field of points and fusing graph features at multiple scales. To make pointwise features more discriminative, a multilevel interaction Transformer module combining Multihead Offset Attention and Multihead Cross Attention is proposed to refine the internal features of the point cloud and perform feature interaction. To filter out the undesirable effects of outliers, an overlap prediction module containing overlap factor and matching factor is also proposed for determining the match ability of points and predicting the overlap region. The final rigid transformation parameters are generated based on the distribution of the overlap region. The proposed GCMTN was extensively verified on publicly available ModelNet and ModelLoNet, 3DMatch and 3DLoMatch, and odometryKITTI datasets and compared with recent methods. The experimental results demonstrate that GCMTN significantly improves the capability of feature extraction and achieves competitive registration performance in low-overlap scenes. Meanwhile, GCMTN has value and potential for application in practical remote sensing tasks. Full article

Current management guidelines for ascending thoracic aortic aneurysms (aTAA) recommend intervention once ascending or sinus diameter reaches 5–5.5 cm or shows a growth rate of >0.5 cm/year estimated from echo/CT/MRI. However, many aTAA dissections (aTAAD) occur in vessels with diameters below the surgical intervention threshold of <55 mm. Moreover, during aTAA repair surgeons observe and experience considerable variations in tissue strength, thickness, and stiffness that appear not fully explained by patient risk factors. To improve the understanding of aTAA pathophysiology, we established a multi-disciplinary research infrastructure: The Maastricht acquisition platform for studying mechanisms of tissue–cell crosstalk (MAPEX). The explicit scientific focus of the platform is on the dynamic interactions between vascular smooth muscle cells and extracellular matrix (i.e., cell–matrix crosstalk), which play an essential role in aortic wall mechanical homeostasis. Accordingly, we consider pathophysiological influences of wall shear stress, wall stress, and smooth muscle cell phenotypic diversity and modulation. Co-registrations of hemodynamics and deep phenotyping at the histological and cell biology level are key innovations of our platform and are critical for understanding aneurysm formation and dissection at a fundamental level. The MAPEX platform enables the interpretation of the data in a well-defined clinical context and therefore has real potential for narrowing existing knowledge gaps. A better understanding of aortic mechanical homeostasis and its derangement may ultimately improve diagnostic and prognostic possibilities to identify and treat symptomatic and asymptomatic patients with existing and developing aneurysms. Full article

In large-scale laying hen farming, timely detection of dead chickens helps prevent cross-infection, disease transmission, and economic loss. Dead chicken detection is still performed manually and is one of the major labor costs on commercial farms. This study proposed a new method for dead chicken detection using multi-source images and deep learning and evaluated the detection performance with different source images. We first introduced a pixel-level image registration method that used depth information to project the near-infrared (NIR) and depth image into the coordinate of the thermal infrared (TIR) image, resulting in registered images. Then, the registered single-source (TIR, NIR, depth), dual-source (TIR-NIR, TIR-depth, NIR-depth), and multi-source (TIR-NIR-depth) images were separately used to train dead chicken detecting models with object detection networks, including YOLOv8n, Deformable DETR, Cascade R-CNN, and TOOD. The results showed that, at an IoU (Intersection over Union) threshold of 0.5, the performance of these models was not entirely the same. Among them, the model using the NIR-depth image and Deformable DETR achieved the best performance, with an average precision (AP) of 99.7% (IoU = 0.5) and a recall of 99.0% (IoU = 0.5). While the IoU threshold increased, we found the following: The model with the NIR image achieved the best performance among models with single-source images, with an AP of 74.4% (IoU = 0.5:0.95) in Deformable DETR. The performance with dual-source images was higher than that with single-source images. The model with the TIR-NIR or NIR-depth image outperformed the model with the TIR-depth image, achieving an AP of 76.3% (IoU = 0.5:0.95) and 75.9% (IoU = 0.5:0.95) in Deformable DETR, respectively. The model with the multi-source image also achieved higher performance than that with single-source images. However, there was no significant improvement compared to the model with the TIR-NIR or NIR-depth image, and the AP of the model with multi-source image was 76.7% (IoU = 0.5:0.95) in Deformable DETR. By analyzing the detection performance with different source images, this study provided a reference for selecting and using multi-source images for detecting dead laying hens on commercial farms. Full article

To ensure the success of energy transition and achieve the target of reducing the carbon footprint of energy systems, the management of energy systems needs to be decentralized. Public blockchains offer favorable features to support energy sector democratization and reinforce citizens’ trust, such as tamper-proof energy data registration and sharing, decentralization, transparency, and support for peer-to-peer (P2P) energy trading. However, in blockchain-based P2P energy markets, transactional data are public and accessible, which raises privacy concerns related to prosumers’ energy profiles while lacking scalability and featuring high transactional costs. In this paper, we employ secure multi-party computation (MPC) to assure privacy on a P2P energy flexibility market implementation in Ethereum by combining the prosumers’ flexibility orders data and storing it safely on the chain. We provide an encoding mechanism for orders on the energy market to obfuscate the amount of energy traded by creating groups of prosumers, by splitting the amount of energy from bids and offers, and by creating group-level orders. The solution wraps around the smart contracts-based implementation of an energy flexibility marketplace, assuring privacy features on all market operations such as order submission, matching bids and offers, and commitment in trading and settlement. The experimental results show that the proposed solution is effective in supporting P2P energy flexibility trading, reducing the number of transactions, and gas consumption with a limited computational time overhead. Full article