课程文献中心 更多>>

关键词： Subperiosteal implant   CAD/CAM   Digital workflow   Atrophic maxilla   Peri-implantitis   Oral rehabilitation  

摘要： This case report describes the digital workflow and clinical outcomes of a customized CAD/CAM-assisted subperiosteal implant (SPI) used for the rehabilitation of a severely atrophic maxilla. A 53-year-old female patient presented with advanced peri-implantitis affecting multiple maxillary implants. After implant removal and a healing period, a patient-specific titanium SPI was designed and fabricated using cone-beam computed tomography and CAD/CAM technology. The implant was installed under conscious sedation, supporting a provisional prosthesis, followed by a definitive titanium–composite hybrid restoration. The digital workflow allowed precise adaptation of the implant to the patient’s anatomy, minimizing surgical morbidity and eliminating the need for bone grafting.. This case suggests that a customized CAD/CAM-assisted subperiosteal implant (SPI) may represent a feasible treatment alternative in a single-case salvage scenario, achieving favorable aesthetic and functional outcomes in a severely atrophic maxilla where rehabilitation with conventional endosseous implants is not feasible.

关键词： Attention mechanisms   Dual-phase CT   Dual-task learning   Lymph node metastasis   Rectal cancer  

摘要： Accurate preoperative prediction of lymph node metastasis and precise tumor segmentation are critical for treatment planning in rectal cancer. However, existing approaches often rely on single-task models or handcrafted features, limiting generalization and diagnostic robustness. In this work, we propose CAD-Net, a novel cross-phase attention-driven dual-task learning framework that jointly performs tumor segmentation and LNM classification from dual-phase contrast-enhanced CT images. CAD-Net introduces a Cross-phase Attention Feature Interaction Unit to dynamically fuse arterial and portal venous phase features, and a Dual-path Hierarchical Fusion Codec to integrate multi-scale contextual and morphological cues. Additionally, a dual-task consistency loss enforces spatial alignment between segmentation and classification outputs. We evaluate CAD-Net on the public LNMCR dataset, achieving state-of-the-art performance with a Dice score of 87.24% for segmentation and 87.4% accuracy for LNM diagnosis. Ablation and hyperparameter studies demonstrate the contribution of each module, while cosine similarity visualizations confirm improved feature coherence. The findings indicate that CAD-Net is a promising approach for improving preoperative decision-making in rectal cancer management.

关键词： Machine learning   Helical distillation column   Additive manufacturing   Number of stages   Process intensification  

摘要： Traditional workflows in chemical engineering, from design to characterization, have served the field well. Emerging technologies, such as machine learning, now offer opportunities for faster design iterations and better integration of the various development stages. This study demonstrates how machine learning (ML) can reduce this gap by directly integrating experimental data into predictive models. Focusing on a Additive Manufactured helical micro-distillation column design for separating liquid mixtures, several ML models were trained to predict the number of theoretical stages based on geometric parameters and operating conditions. 11 variants were designed, built, and tested to collect 197 experimental data sets to assess the feasibility of five predictive ML models from experimental data. Among the algorithms tested, the Gradient Boosting Regressor achieved the best performance with a coefficient of determination $R^2=0.7934$. The work highlights the behavior of the model across different regimes, identifies key sources of error, and proposes a hybrid experimental–ML workflow for rapid screening of distillation designs. This approach accelerates process development and reduces the need for extensive experimentation, especially in time-consuming tasks such as distillation.

关键词： Snow mechanics   Modified Cam-Clay   Finite strain plasticity   Damage   Healing   Snow traction  

摘要： Reliable prediction of mechanical interactions with hard-packed snow requires constitutive models that capture coupled plasticity, damage, healing, and large deformation. Current constitutive formulations for snow typically neglect either damage-induced degradation or stiffness recovery (healing), particularly under finite-strain conditions relevant to high-speed interactions such as tire-snow contact. While continuum damage-healing models exist for materials such as concrete, asphalt, and polymers, their direct application to snow is hindered by snow’s distinct rapid mechanical degradation and healing behaviour. In this contribution, a finite-strain constitutive model is proposed for hard-packed snow, incorporating both damage and healing effects. The elastic response is described by a Neo-Hookean constitutive law, while plastic deformation is governed by a cohesive extension of Modified Cam-Clay plasticity augmented with exponential hardening. Damage evolution is driven by deviatoric plastic deformation, whereas healing is activated by compressive volumetric plastic deformation. The finite element method (FEM) is used, and mesh objectivity is maintained through a non-local regularization approach. Model parameters are calibrated using numerical triaxial and uniaxial tests. Predictive capability is demonstrated through a blade-cutting simulation using a B-spline material point method (MPM) combined with a level-set contact algorithm. The proposed model successfully captures the interplay between shear-induced damage and compression-induced healing, providing a consistent framework for predictive assessment and optimization of winter tire performance.

关键词： Eye-tracking   Concurrent reader   Chest radiography   Bounding-box display   Interpretation time  

摘要： Computer-aided detection (CAD) systems for chest radiographs are widely used; however, concurrent reader displays such as bounding-box (BB) highlights may influence interpretation. This pilot study used eye tracking to examine which aspects of visual search were affected by these factors.

关键词： Conceptual design  

摘要： With the advancement of transplanting theory and increasing agronomic requirements, gear–linkage/cam mechanisms (GLCMs) have emerged as a feasible solution for achieving complex operational trajectories by introducing transmission ratio variation characteristics. However, systematic design methodologies for such mechanisms remain limited. In this study, a structural synthesis method for GLCMs based on gear pair substitution is proposed, and suitable configurations are selected in combination with kinematic synthesis to design vegetable plug seedling transplanting mechanisms. First, similar edges are identified using the minimum distance matrix constant and the power matrix constant, with verification against established databases to ensure recognition accuracy. Second, a structural synthesis approach for special GLCMs is developed by gradually adding components and kinematic pairs. Through gear pair substitution, structural synthesis of GLCMs with up to three degrees-of-freedom is achieved, while similarity information is employed to avoid generating isomorphic configurations. Finally, an optimal configuration is selected and combined with kinematic synthesis to design a vegetable plug seedling transplanting mechanism, whose feasibility is validated through simulation experiments. Copyright © 2025 by ASME.

关键词： Explainability   Grad-CAM-based deep learning   Operator-centered explanation   Operation support   Trustworthiness  

摘要： Explainable artificial intelligence (XAI) is employed to clarify the rationale behind AI outputs and resolve black-box nature of artificial intelligence (AI). This is intended to enhance trustworthiness and usability of AI-based technology for operation or decision-making support. However, XAI explanations now are often more accessible to developers, who construct, verify, and optimize AI models, than to operators, who need to understand and employ these models for decision-making. Therefore, this study aims to develop a Grad-CAM-based deep learning methodology that provides operator-centered explanations for enhancing explainability of AI outputs and the trustworthiness of the AI technologies for operation support in the context of performing procedure-based operating tasks. In this study, an XAI model based on gradient-weighted class activation mapping and a dilated causal convolutional neural network was developed to identify abnormal states and provide operator-centered explanations within the scope of abnormal operating procedures corresponding to identified abnormal states. Furthermore, representation of operator-centered explanations was addressed to effectively display the AI-supported information from the proposed model on human-system interface for operating tasks.

关键词： Hypertrophic cardiomyopathy   Coronary microvascular dysfunction   Magnetic resonance imaging   Machine learning   Radiomics   HCM   Hypertrophic cardiomyopathy   CMD   Coronary microvascular dysfunction   CMR   Cardiac magnetic resonance   IMR   Microcirculatory resistance index   FFR   Fractional flow reserve   ECG   Electrocardiograms   AUC   Area under curve   ROC   Receive operating characteristic   CFVR   Coronary flow velocity reserve   MPR   Myocardial perfusion reserve   MPRI   Myocardial perfusion reserve index   TR   Epetition time   TE   Echo time   FOV   Field of view   RF   Random forest   CAD   Coronary artery disease   EF   Ejection fraction   EDV   End-diastolic volume   EDVI   End-diastolic volume index   ESV   End-systolic volume   ESVI   End-systolic volume index   SV   Stroke volume   SVI   Stroke volume index   CO   Cardiac output   CI   Cardiac index   LVM   Left ventricular mass   LVMI   Left ventricular mass index   MIVS   Maximum interventricular septum thickness   MWT   Maximum wall thickness   ROI   Region of interest   ICC   Intraclass correlation coefficient   ROC   Receiver operating characteristic   DCA   Decision curve analysis   AUC   Area under the curve   ML   Machine learning   SVM   Support vector machine   CCTA   Coronary computed tomography angiography   ECV   Extracellular volume fraction  

摘要： In hypertrophic cardiomyopathy (HCM), detection of coronary microcirculatory dysfunction (CMD) usually relies on contrast-enhanced cardiac magnetic resonance (CMR). This study sought to develop a practical non-contrast radiomics model to identify CMD, minimizing reliance on contrast agents.

关键词： Digital dentistry   Digital overdenture   CAD/CAM   Monolithic denture  

摘要： The purpose of this retrospective pilot study was to evaluate patient-reported outcomes and satisfaction with palateless monolithic CAD/CAM implant-supported overdentures.