Search Results (46)

Radiotherapy simulation is essential for accurately targeting tumors while preserving healthy tissue, ensuring treatment precision and safety. This study aimed to develop an integrated radiotherapy simulation system capable of automated segmentation, dose estimation, and collision detection within a virtual planning environment to enhance efficiency and reduce costs in radiotherapy treatment planning. The Point Transformer model was applied to organ point cloud data derived from CT medical imaging for automated segmentation. Farthest point sampling (FPS) was employed to downsample the data before training. To enhance the accuracy and anatomical fidelity of the AI-generated segmentation results, reconstruction and refinement algorithms, including k-d tree, outlier removal, marching cubes, and surface smoothing, were implemented. Beam penetration simulation with the ray casting algorithm was employed for correction-based dose estimation. A collision detection module was incorporated to identify potential machine–machine or machine–patient interactions. The entire workflow was executed within a Unity 3D-based virtual simulation environment. As a result, the Point Transformer model demonstrated high segmentation accuracy, achieving Dice scores of 93.86 $\pm$ 1.50% for single-organ and 91.86 $\pm$ 3.25% for multi-organ cases, surpassing the performance of PointNet++. Applying ray casting for the refined surface meshes generated through post-processing enabled accurate dose estimation with discrepancies of 3.5% (brain), 5.9% (liver), and 13.8% (lung) compared to a Pinnacle TPS. The proposed method provides a low-cost and adaptable solution that enables easy modification and further development, making it particularly suitable for widespread applications in radiotherapy research, education, and clinical workflow optimization. Full article

Large-scale Virtual Power Plants (VPPs) are increasingly essential as Distributed Energy Resources (DERs) assume ancillary service duties once supplied by conventional generation, yet scaling a VPP exposes a persistent trilemma among economic efficiency, data privacy, and operational security. Centralized coordination can approach optimal revenue but requires collecting fine-grained DER operational data and creates a single point of compromise. Federated Learning (FL) mitigates raw data centralization by keeping measurements and experience local, but it introduces a fragile trust assumption that the aggregator will correctly and fairly combine model updates. This trust gap is acute in reinforcement learning-based VPP control because aggregation deviations, including selectively dropping updates, manipulating weights, replaying stale models, or injecting a replacement model, can silently bias the learned policy and degrade both profit and compliance. We propose a zero-knowledge federated reinforcement learning framework for trustless VPP coordination in which each DER trains a local deep reinforcement learning agent to solve a multi-objective dispatch problem that balances ancillary service revenue against battery degradation under operational and grid constraints, while the global aggregation step is made externally verifiable. In each round, participants bind membership via signed receipts and commit to their updates, and the aggregator produces a zk-SNARK, proving that the published global parameters equal the agreed aggregation rule applied to the receipt-bound set of committed updates under a fixed-point encoding with range constraints. Verification is lightweight and can be performed independently by each DER, removing the need to trust the aggregator for aggregation integrity without centralizing raw DER operational data or trajectories. The proposed design does not aim to hide model updates from the aggregator. Instead, it provides external verifiability of the aggregation computation while keeping raw measurements and local experience. We formalize the threat model and verifiable security properties for aggregation correctness and update inclusion, present a circuit construction with proof complexity characterized by model dimension and fleet size, and evaluate the approach in power and cyber co-simulation on the IEEE 33 bus feeder with ancillary service signals. Results show near-centralized economic performance under benign conditions and improved robustness to aggregator side deviations compared to standard federated reinforcement learning. Full article

Background: Orbital dermoid cysts are common benign lesions; however, deep-seated or recurrent lesions near the orbital apex pose major surgical challenges due to their proximity to critical neurovascular structures. Lateral orbitotomy remains the reference approach, but accurate osteotomies and stable reconstruction can be difficult to achieve using conventional techniques. This study reports our initial experience using a fully digital, hospital-based point-of-care (POC) workflow to enhance precision and safety in complex orbital dermoid cyst surgery. Methods: We present a case series of three patients with orbital dermoid cysts treated at a tertiary center (2024–2025) using a comprehensive digital workflow. Preoperative assessment included CT and/or MRI followed by virtual surgical planning (VSP) with orbit–tumor segmentation and 3D modeling. Cutting guides and patient-specific implants (PSIs) were manufactured in-house under a certified hospital-based POC protocol. Surgical strategies were tailored to each lesion and included piezoelectric osteotomy, intraoperative navigation, intraoperative CT, and structured-light scanning when indicated. Results: Complete en bloc resection was achieved in all cases without capsular rupture or optic nerve injury. Intraoperative CT confirmed complete lesion removal and accurate PSI positioning and fitting. Structured-light scanning enabled radiation-free postoperative monitoring when used. All patients preserved full ocular motility, visual acuity, and facial symmetry, with no complications or recurrences during follow-up. Conclusions: The integration of VSP, in-house POC manufacturing, and image-guided surgery within a lateral orbitotomy approach provides a reproducible and fully integrated workflow. This strategy appears to improve surgical precision and safety while supporting optimal long-term functional and aesthetic outcomes in challenging orbital dermoid cyst cases. Full article

In building measurement using terrestrial laser scanners (TLSs), acquired 3D point clouds (3DPCs) often contain significant reflection artifacts caused by reflective glass surfaces. Such reflection artifacts significantly degrade the performance of downstream applications. This study proposes a novel strategy, called GRASS, to remove these reflection artifacts. Specifically, candidate glass points are identified based on multi-echo returns caused by glass components. These potential glass regions are then refined through planar segmentation using geometric constraints. Then, we trace laser beam trajectories to identify the reflection affected zones based on the estimated glass planes and scanner positions. Finally, reflection artifacts are identified using dual criteria: (1) Reflection symmetry between artifacts and their source entities across glass components. (2) Geometric similarity through a 3D deep neural network. We evaluate the effectiveness of the proposed solution across a variety of 3DPC datasets and demonstrate that the method can reliably estimate multiple glass regions and accurately identify virtual points. Furthermore, both qualitative and quantitative evaluations confirm that GRASS outperforms existing methods in removing reflection artifacts by a significant margin. Full article

This case report describes mandibular distraction osteogenesis (DO) in a six-year-old patient with first and second branchial arch syndrome and obstructive sleep apnea, in whom 3D surgical planning was combined with ultrasonography (US) for postoperative monitoring. The aim was to illustrate how patient-specific 3D modeling and a structured ultrasonography protocol can support safe mandibular advancement while limiting radiation exposure in a pediatric patient with complex craniofacial deformity. Preoperatively, a 3D-printed model of the mandible, generated from a cone beam computed tomography (CBCT) scan, was used to guide precise osteotomy planning and vector orientation. The surgical procedure was conducted using a Risdon approach and piezoelectric tools to ensure minimal trauma. Postoperative monitoring incorporated serial panoramic radiography and US at predefined time points to assess gap size, callus formation, and vascularity during distraction and consolidation. US identified early callus formation, progressive cortical bridging, and preserved callus vascularity, and, together with radiographic findings, guided the timing of distraction termination and distractor removal at 16 weeks. This case adds to the limited literature on pediatric mandibular DO by demonstrating the feasibility of integrating patient-specific 3D virtual planning with US-based follow-up to improve the safety, precision, and radiation-conscious management of DO in pediatric patients with complex craniofacial deformities. Full article

Despite improved therapeutic concepts, the survival of patients with hepatocellular carcinoma (HCC) is limited. Liver transplantation (LT) is the best possible treatment for suitable patients. This therapy is of particular importance, because it not only removes the cancer but also cures the underlying structural liver disease. Due to the persistent lack of donor organs, however, the oncological prognosis after LT is of particular importance for fair organ allocation. Bonus points on the organ waiting list are rewarded for tumors within a certain tumor extent. In general, macrovascular invasion and extrahepatic tumor manifestation are considered to be contraindications for LT, as survival in these patients is very low. In recent years, however, microvascular invasion and poorly differentiated tumors have also turned out to be unfavorable. Most selection criteria for LT in HCC are still based on very simple imaging criteria like size and number without utilizing additional imaging characteristics inherent to the tumor nodule, which could be processed in a “virtual biopsy”. Recently, diagnostic research has presented the clinical benefit of artificial intelligence (AI) in the use of deep-learning strategies for digital diagnosis of poorly differentiated or microvascular-infiltrated tumors. In addition, evaluation of TACE response is analyzed as a possibility to estimate LT survival. The aim of this review is to provide an overview of recent advances in HCC diagnosis and to classify the clinical relevance of these diagnostic and technical advances. Secondly, we discuss how these advances could affect the organ allocation process. Full article

Background: Evidence of the real-world management of dedifferentiated liposarcoma (DDLPS) is limited by the patient size and coding. The objective of this study is to generate consensus expert opinion on locally advanced or metastatic DDLPS diagnosis, treatment, and unmet needs. Methods: A three-round Delphi consensus panel was conducted with 9 DDLPS clinical experts from November to December 2023. Expert panelists were recruited across academic specialty and traditional settings and US regions. The Delphi panel included two rounds of surveys followed by a consensus building workshop. Surveys contained multiple-choice and free response questions, and statements for level of agreement rating. Panelists rated each statement for level of agreement on a 9-point Likert scale. Statements with ≥75% of scores ≥ 7 achieved consensus, and those that did not achieve consensus agreement were modified or removed from subsequent testing. A virtual workshop was held to discuss areas which did not achieve consensus and refine previously agreed upon statements. Results: In total 25 consensus statements were developed by the Delphi panel. Survey 1 achieved 7 consensus statements across the areas of burden, treatment, and unmet needs of DDLPS. Survey 2 generated an additional 10 consensus statements. During the workshop, eight more statements achieved consensus, and four statements were refined for enhanced clarity and precision. The study findings are limited by the number of Delphi panel participants and consensus statements may not be fully representative of clinician perspectives across the US. Conclusions: Consensus areas identified by the Delphi panel help better understand the decision factors for surgical and non-surgical treatments and anticipated utilization. These results could be used to inform both drug development programs as well as care delivery challenges for liposarcoma patients. Full article

As the global energy structure transitions towards cleaner sources, large-scale integration of wind power has become a trend for modern power systems. However, the impact of low-inertia power electronic converters and the fault propagation effects at critical nodes pose significant challenges to power system stability. To this end, a Kuramoto-like model analysis method, considering node importance, is proposed in this paper. First, virtual node technology is utilized to optimize the power grid topology model. Then an improved PageRank algorithm embedded by a critical node identification method is proposed, which simultaneously considers transmission efficiency, coupling transmission probability, and voltage influence among nodes. On this basis, the traditional uniform coupling assumption is eliminated, thereby reallocating the coupling strength between critical nodes. In addition, the Kron method is applied to simplify the power grid model, constructing a hybrid Kuramoto-like model that integrates second-order synchronous machine oscillators and first-order wind power oscillators. Based on this model, the transient stability of the wind power integrated power system is analyzed. Finally, through estimating the attraction region range of the stable equilibrium point, a transient stability criterion is proposed for fault limit removal time assessment. The simulation results of the improved IEEE 39-bus system show that coupling strength optimization based on node importance reduces the system’s average critical coupling strength by 17%, significantly improving synchronization robustness. Time-domain simulations validate the accuracy of the method, with the relative error of fault removal time estimation controlled within 10%. This research provides a new analytical tool for transient stability analysis of wind power integration. Full article

Dynamic gesture detection is a key topic in computer vision and deep learning, with applications in human–computer interaction and virtual reality. However, traditional methods struggle with long sequences, complex scenes, and multimodal data, facing issues such as high computational cost and background noise. This study proposes an Attention-Enhanced dual-layer LSTM (Long Short-Term Memory) network combined with Grounding SAM (Grounding Segment Anything Model) for gesture detection. The dual-layer LSTM captures long-term temporal dependencies, while a multi-head attention mechanism improves the extraction of global spatiotemporal features. Grounding SAM, composed of Grounding DINO for object localization and SAM (Segment Anything Model) for image segmentation, is employed during preprocessing to precisely extract gesture regions and remove background noise. This enhances feature quality and reduces interference during training. Experiments show that the proposed method achieves 96.3% accuracy on a self-constructed dataset and 96.1% on the SHREC 2017 dataset, outperforming several baseline methods by an average of 4.6 percentage points. It also demonstrates strong robustness under complex and dynamic conditions. This approach provides a reliable and efficient solution for future dynamic gesture-recognition systems. Full article

Background: In 2021, the National Kidney Foundation–American Society of Nephrology (NKF-ASN) recommended the use of the 2021 refit equation without race; however, the effect of the removal is unclear. Our research aimed to examine the implications of antidiabetic dosing and eligibility on the new 2021 equation among Black patients. Methods: This is a retrospective analysis of patients receiving care at the diabetes treatment center (DTC) of an academic medical center. Estimated glomerular filtration rates (eGFRs) based on serum creatinine were calculated using the 2009 and 2021 CKD-EPI equations. A Monte Carlo simulation was performed to create 10,000 virtual patients. Dosing simulations based on each estimate of kidney function were performed for antidiabetics based on product labeling. The proportion and percentage of patients who were eligible based on the estimates were calculated. Results: The percentages of patients ineligible for metformin based on the estimates from the 2009 and 2021 CKD-EPI equations at the DTC were comparable (8.02% and 8.36%, respectively). In our 10,000 simulated virtual patients, the percentage of ineligibility increased only by 1%. For the GFR cut points of 20 mL/min and 25 mL/min, the rates of ineligibility were similar in our cohort and simulated patients. Conclusions: The exclusion of race from the 2021 CKD-EPI equation may slightly reduce medication eligibility among Black patients. Full article

The vertical curve is designed to smooth sudden gradient changes in the longitudinal profile, enhancing train operational safety and passenger comfort. However, dynamic detection in these segments has consistently encountered issues with long-wavelength vertical irregularities exceeding tolerance limits. To investigate the root causes of this phenomenon and develop a targeted solution, a comprehensive vehicle-track dynamics simulation model was first constructed, based on the design principles for intercity railway vertical curves. The inertial reference method was then applied to process the acceleration and relative displacement data between the detection beam and the track, yielding virtual irregularities. These were compared with excitation irregularities to identify key factors affecting detection accuracy in vertical curve segments. Through further analysis of abnormal exceedances in detection data, the reference cancellation method was proposed. By employing smoothing filters and orthogonal least squares fitting, this method effectively removes track alignment components from the acceleration integration results. Detection errors under various conditions were then compared between the two methods to evaluate the feasibility and effectiveness of the reference cancellation approach. Results indicate that regions with increased longitudinal profile detection errors are primarily located at and near gradient transition points. The vertical curve radius was found to be the primary factor influencing the accuracy of long-wavelength irregularity detection. The proposed reference cancellation method effectively reduces detection errors in areas near gradient transition points to levels comparable to other track sections. Compared to the inertial reference method, the reference cancellation method reduces the maximum detection error by up to 71.77% and the root mean square error by up to 86.61%, effectively mitigating the abnormal exceedances associated with vertical curves. Full article

Magnetorheological finishing (MRF) of aspherical optical elements usually requires the coordination between the translational axes and the oscillating axes of the machine tool to realize the processing. For aspheric optical elements whose steepness exceeds the machining stroke of the equipment, there is still no better method to achieve high-precision and high-efficiency error convergence. To solve this problem, an MRF method combining virtual-axis technology and a spiral scanning path is proposed in this paper. Firstly, the distribution law of the magnetic induction intensity inside the polishing wheel is analyzed by simulation, the stability of the removal efficiency of the removal function within the ±7^∘ angle of the normal angle of the polishing wheel is determined, and MRF is expanded from traditional single-point processing to circular arc segment processing. Secondly, the spiral scanning path is proposed for aspherical rotational symmetric optical elements, which can reduce the requirements of the number of machine tool axes and the dynamic performance of machine tools. Finally, an aspherical fused silica optical element with a curvature radius of 400 mm, K value of −1, and aperture of 100 mm is processed. The PV value of this optical element converges from 189.2 nm to 24.85 nm, and the RMS value converges from 24.85 nm to 5.74 nm. The experimental results show that the proposed combined process has the ability to modify curved optical elements and can be applied to ultra-precision machining of high-steepness optical elements. Full article

This study investigates how missing data samples in continuous blood glucose data affect the prediction of postprandial hypoglycemia, which is crucial for diabetes management. We analyzed the impact of missing samples at different times before meals using two datasets: virtual patient data and real patient data. The study uses six commonly used machine learning models under varying conditions of missing samples, including custom and random patterns reflective of device failures and arbitrary data loss, with different levels of data removal before mealtimes. Additionally, the study explored different interpolation techniques to counter the effects of missing data samples. The research shows that missing samples generally reduce the model performance, but random forest is more robust to missing samples. The study concludes that the adverse effects of missing samples can be mitigated by leveraging complementary and informative non-point features. Consequently, our research highlights the importance of strategically handling missing data, selecting appropriate machine learning models, and considering feature types to enhance the performance of postprandial hypoglycemia predictions, thereby improving diabetes management. Full article

Autonomous driving recognition technology that can quickly and accurately recognize even small objects must be developed in high-speed situations. This study proposes an object point extraction method using rule-based LiDAR ring data and edge triggers to increase both speed and performance. The LiDAR’s ring information is interpreted as a digital pulse to remove the ground, and object points are extracted by detecting discontinuous edges of the z value aligned with the ring ID and azimuth. A bounding box was simply created using DBSCAN and PCA to check recognition performance from the extracted object points. Verification of the results of removing the ground and extracting points through Ring Edge was conducted using SemanticKITTI and Waymo Open Dataset, and it was confirmed that both F1 scores were superior to RANSAC. In addition, extracting bounding boxes of objects also showed higher PDR index performance when verified in open datasets, virtual driving environments, and actual driving environments. Full article

Businesses require ways to check asset use in order not to disregard Service-Level Agreements and guarantee that assets are efficiently distributed to specific departments. A method of allocating, managing, and monitoring cloud resources is provided by cloud resource management systems. They permit one to make and oversee pools of assets, allocate those assets to explicit clients or applications, and track how they are being utilized. Users are able to request and provision resources as needed through a self-service interface provided by a good cloud resource management system. When using a cloud provider, businesses that manage their own resources frequently achieve greater efficiency. A portion of the ways in which IT robotization helps organizations deal with their assets involves setting boundaries for the greatest and least number of virtual machines (VMs), setting look-ahead times for VMs to appear, and halting VMs when they are inactive and, at that point, not needed for operations. Moreover, IT organizations might profit from developing a structure of warnings to further develop perceivability and control over asset utilization. Cloud computing is a model used to enable omnipresent, helpful, on-request network admittance to a common pool of configurable processing assets that can be quickly provisioned and delivered with negligible administrative exertion and without specialist organizations. Distributed computing is a financial model for huge corporations, as it removes the requirement for beginning interest in capital or framework costs. Full article