课程文献中心 更多>>

关键词： 数字技术   建筑CAD   教学策略  

摘要： 数字技术正深度融入建筑行业,推动建筑设计流程、技术应用范式与行业人才需求的迭代升级,对从业者的数字素养与建筑CAD技术应用能力提出了更高要求。基于此,文章通过分析数字技术对建筑CAD学科教学的作用,结合教学实践,提出切实可行的教学策略,包括整合数字资源、构建虚拟场景、推行项目教学、运用智能工具、构建线上题库等,以期为完善建筑CAD学科教学模式、提升学生CAD技术应用能力提供参考。

关键词： AI   artificial intelligence   CAM   chorioallantoic membrane   FDA   U.S. Food and Drug Administration   IR   interventional radiology   US   ultrasound  

摘要： Graphical abstract

关键词： 结构参数   计算机视觉   深度学习   纱线密度   织物组织  

摘要： 织物结构参数的高效识别是纺织品智能制造中的关键环节,随着计算机技术的发展,传统算法和深度学习算法已广泛应用于该领域。然而,当前该方向的系统性研究仍较相对缺乏。为此,系统综述织物结构参数自动识别技术的研究现状,深入剖析传统算法与深度学习算法在纱线密度、织物组织及组织循环识别等关键参数识别中的应用与最新进展。探讨当前技术面临的挑战,并对未来研究方向进行展望。相关研究推动了织物结构参数识别技术的进一步发展,为纺织智能制造提供了理论依据与技术支撑。

关键词： calcified lesions   coronary artery disease   intravascular lithotripsy   sex-specific outcomes   CAD   EQ-5D-5L   European Quality of Life 5 Dimension 5 Level   GAD-7   Generalized Anxiety Disorder-7   ID-TLR   ischemia-driven target lesion revascularization   IVL   MACE   major adverse cardiovascular event   MI   myocardial infarction   PCI   percutaneous coronary intervention   SAQ-7   Seattle Angina Questionnaire-7   TLF   target lesion failure  

摘要： Percutaneous coronary intervention of severely calcified coronary lesions is associated with a higher risk of adverse events in women compared with men.

关键词： Boundary representation   Command sequence   Reinforcement learning   Training gym  

摘要： A CAD command sequence is a typical parametric design paradigm in 3D CAD systems where a model is constructed by overlaying 2D sketches with operations such as extrusion, revolution, and Boolean operations. Although there is growing academic interest in the automatic generation of command sequences, existing methods and datasets only support operations such as 2D sketching, extrusion, and Boolean operations. This limitation makes it challenging to represent more complex geometries.

摘要： La réalisation d’acquisitions scintigraphiques corps entier, après injection de 117Lu-PSMA, permet d’évaluer la réponse au traitement. Ces enregistrements, qui étaient jusqu’à présent réalisés sur caméra 360 °CZT en 18 minutes sur le pic à 113 keV (SP-18), peuvent être optimisés en combinant les informations provenant des deux pics en énergie 113/208 keV. Nous avons évalué une réduction du temps d’acquisition à 9 minutes, rendue possible grâce au gain d’un facteur 2 en sensibilité des pics en énergie 113/208 keV (DP-9).

关键词： LMICs   Low- and Middle-Income Countries   AI   Artificial Intelligence   PRISMA-ScR   Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews   OSF   Open Science Framework   MeSH   Medical Subject Headings   IRB   Institutional Review Board   US   Ultrasound   LUS   Lung Ultrasound   RAILUS   Real-time AI-assisted LUS framework   YOLOv5-PBB   You Only Look Once version 5 with Polygonal Bounding Boxes   YOLOv8-PBB   You Only Look Once version 8 with Polygonal Bounding Boxes   FLUEnT   Fused Lung Ultrasound Encoding-based Transformer   VAE   Variational Autoencoder   ResNet-18   Residual Network 18   SOTA   State Of The Art   Smart B-lines   Automatic B-lines detection system (Mindray M9)   POCUS   Point-of-Care Ultrasound   BIRADS   Breast Imaging Reporting and Data System   CBE   Clinical Breast Examination   VSI   Volume Sweep Imaging   CNN   Convolutional Neural Network   CAD   Computer-Aided Detection   SOC   Standard of Care   Inception-v3   Deep CNN architecture used in image analysis   TensorFlow   Open-source machine learning framework   Koios DS   AI software for breast ultrasound analysis   DCIS   Ductal Carcinoma In Situ   TVUS   Transvaginal Ultrasound   ML   Machine Learning   SVM   Support Vector Machine   RadScore   Radiomics Score   CSCC   Cervical Squamous Cell Carcinoma   GA   Gestational Age   AUC-ROC   Area Under the Receiver Operating Characteristic Curve   SegNet   Segmentation Neural Network   UNet   Convolutional neural network for biomedical image segmentation   FCN   Fully Convolutional Network   MobileNetV2   Lightweight CNN architecture   HC   Head Circumference   BPD   Biparietal Diameter   PHUs   Primary Health Units   VGG   Visual Geometry Group Network   ConvNeXt-V2   Convolutional neural network architecture   nnU-Net   No New U-Net   AoI   Aortic Isthmus   MCA   Middle Cerebral Artery   UA   Umbilical Artery   LVIO   Left Ventricular Inflow-Outflow   PI   Pulsatility Index   MAPE   Mean Absolute Percentage Error   FL   Femur Length   OFD   Occipitofrontal Diameter   AC   Abdominal Circumference   PTB   Preterm Birth   CRL   Crown-Rump Length   RMSE   Root Mean Square Error   R   Coefficient of Determination   PE   Preeclampsia   pPE   Preterm Preeclampsia   ePE   Early-on  

摘要： Access to diagnostic imaging in low- and middle-income countries (LMICs) is limited by scarce equipment, geographic barriers, weak digital infrastructure, and shortages of trained personnel. Artificial intelligence (AI) has emerged as a promising tool to mitigate these gaps by improving diagnostic accuracy, assisting non-specialist health workers, and optimizing workflows. This scoping review aimed to synthesize current evidence on the use of AI for interpreting radiological diagnostic images in LMICs.

关键词： CAM   Insomnia classification   rs-fMRI   ST-GCN  

摘要： Chronic Insomnia Disorder (CID) is a common psychiatric condition that significantly affects quality of life. However, its neurobiological mechanisms remain largely unclear. Prior neuroimaging studies have mainly focused on isolated functional connections, with limited attention to within-network interactions. In this study, we propose a method based on Spatial–Temporal Graph Convolutional Networks (ST-GCN) to distinguish CID patients from healthy controls (HC) using resting-state functional MRI (rs-fMRI) data. A spatio-temporal graph is constructed to jointly model spatial and temporal features of brain connectivity. To interpret the model outputs, we further applied Class Activation Mapping (CAM) as a post-hoc analysis tool to identify brain regions most relevant to classification. CAM is not part of the core model but provides insights into discriminative features. The method was evaluated on two independent datasets, achieving classification accuracy above 90%. CAM results highlight the frontoparietal network as a key discriminator between CID and HC, supporting the hyperarousal theory of insomnia. These findings underscore the potential of graph-based deep learning for functional connectivity analysis. For details, see the code at https://***/AkishiroKura/ST-GCN-CID.

关键词： CAD-CAM   Laser sintering   Prosthetic bars   Dental implants   Overdentures   Fracture resistance  

摘要： Implant-supported hybrid metal–resin prostheses are widely used to rehabilitate edentulous patients. However, fractures of the veneering resin and screw complications remain common mechanical failures. Advances in CAD-CAM design and laser sintering technology may improve the structural integrity of these restorations.

关键词： artificial intelligence   chatbot   chemoradiotherapy   continuous activity monitoring   digital oncology   gastrointestinal cancer   head and neck cancer   remote patient monitoring   thoracic cancer  

摘要： Artificial intelligence (AI) is increasingly being explored as a way to improve supportive care during chemoradiotherapy (CRT). Through our CAM 1.0 and CAM 2.0 studies, we examined how AI-supported remote patient monitoring could be integrated into CRT care, revealing both its potential benefits and its challenges in real-world implementation. We observed how AI can facilitate remote patient monitoring beyond routine visits, yet also how it may create additional tasks for providers, magnify digital inequities, and leave patients still seeking human connection. These experiences underscore that AI’s impact in oncology will be defined not only by its technical capabilities but by how it fits into workflows, addresses barriers to access, and preserves the relational aspects of care. This perspectives piece aims to highlight the practical insights from CAM 1.0 and 2.0 that may inform how oncologists, developers, and health systems approach future AI integration into oncology workflows, particularly in the context of CRT. NCT: NCT05318027