检索结果-内蒙古大学图书馆

17th Asian Conference on Computer Vision, ACCV 2024

作者： Viriyasaranon, Thanaporn Ma, Serie Choi, Jang-Hwan Department of Computational Medicine Graduate Program in System Health Science and Engineering Ewha Womans University Seoul Korea Republic of Division of Mechanical and Biomedical Engineering Graduate Program in System Health Science and Engineering Ewha Womans University Seoul Korea Republic of Department of Artificial Intelligence Ewha Womans University Seoul Korea Republic of

ISBN: (纸本)9789819609000

The precise detection of cephalometric landmarks on two-dimensional (2D) radiographs or three-dimensional (3D) computed tomography (CT) images is a fundamental step in various medical fields, especially in research on orthodontics and maxillofacial surgery. Deep learning-based detectors have demonstrated remarkable accuracy in 2D cephalometric analysis, whereas conventional single-view approaches are limited by their reliance on information from a single perspective. This study proposes GeoRefineNet, a novel multistage framework that leverages information from multiple CT scans acquired at various angles. By incorporating geometric knowledge through a 3D heatmap reconstruction process, GeoRefineNet improves robustness, accuracy, and adaptability to various cephalometric configurations. The proposed framework predicts 3D landmark positions on CT images, effectively addressing challenges associated with high-dimensional input data and limited training examples. GeoRefineNet surpasses the existing state-of-the-art models in the 2D and 3D domains, as demonstrated by its superior performance on numerical and clinical datasets. These findings indicate that GeoRefineNet offers a promising avenue for improving the accuracy and reliability of cephalometric landmark detection fostering further advances in clinical diagnosis and treatment planning. Our code is available at https://***/Thanaporn09/***. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Bioinspired magnetic cilia:from materials to applications

引用

Microsystems & Nanoengineering 2023年第6期9卷 107-128页

作者： Seongjin Park Geonjun Choi Minsu Kang Woochan Kim Jangho Kim Hoon Eui Jeong Department of Mechanical Engineering Ulsan National Institute of Science and Technology(UNIST)Ulsan44919Republic of Korea Department of Convergence Biosystems Engineering Chonnam National UniversityGwangju61186Republic of Korea Interdisciplinary Program in IT-Bio Convergence System Chonnam National UniversityGwangju61186Republic of Korea

Microscale and nanoscale cilia are ubiquitous in natural systems where they serve diverse biological *** artificial magnetic cilia have emerged as a highly promising technology with vast potential applications,ranging from soft robotics to highly precise *** this review,we comprehensively discuss the roles of cilia in nature and the various types of magnetic particles utilized in magnetic cilia;additionally,we explore the top-down and bottom-up fabrication techniques employed for their ***,we examine the various applications of magnetic cilia,including their use in soft robotics,droplet and particle control systems,fluidics,optical devices,and ***,we present our conclusions and the future outlook for magnetic cilia research and development,including the challenges that need to be overcome and the potential for further integration with emerging technologies.

关键词： magnetic overcome precise

来源：评论

学校读者我要写书评

暂无评论

A motion-level-aware denoising framework for x-ray fluoroscopic images

A motion-level-aware denoising framework for x-ray fluorosco...

引用

Medical Imaging 2023: Physics of Medical Imaging

作者： Jo, Geonhui Jang, Minhee Jeon, Sun-Young Kim, Wonjin Choi, Jang-Hwan Department of Computer Science and Engineering Ewha Womans University Seoul03760 Korea Republic of Division of Mechanical and Biomedical Engineering Graduate Program in System Health Science and Engineering Ewha Womans University Seoul03760 Korea Republic of

ISBN: (纸本)9781510660311

Fluoroscopy in a low-dose tube output is used to reduce the damage associated with radiation exposure. However, lowering the radiation dose inevitably increases random noise in x-ray images, resulting in poor diagnostic image quality, which requires noise reduction for accurate diagnosis. Also, in the case of non-static objects, the image is blurred due to motion. The most-used denoiser with a recursive filter (RF) preserves details well when applied to temporal data, but it is vulnerable to motion blur. Existing convolutional neural network (CNN)-based algorithms with single-frame input cannot use the temporary context, and others with multi-frame input are good for motion detection but poor for detail preservation. Therefore, we propose a motion-level-aware denoising framework to combine the results of RF- and CNN-based algorithms depending on the pixel-wise magnitude of motion to complement each other. The data we use are fluoroscopy images taken in continuous time, and we aim at many-to-one so that one frame is denoised by considering sequential frames. Also, since both RF- and CNN-based algorithms used in our architecture are many-to-one methods, they can consider spatiotemporal information. In the multi-frame input, the difference in intensity of each pixel between frames is calculated to obtain a moving map. Depending on the factor value from the moving map, the final image is obtained by reflecting the outputs of the RF- and CNN-based algorithms. If the factor value is high, the pixel intensity of the final image is like the CNN-based output, which is good for motion detection, and vice versa, it more reflects the intensity of RF output, which is excellent in perceptual quality. Therefore, it prevents motion blur and does not over-smooth microdetails, such as bones and muscles. The results show that combining the two outputs together records higher peak signal-to-noise ratio (PSNR) and has better perceptual quality for diagnosis than using only one method. F

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Bioprinting Methods for Fabricating In Vitro Tubular Blood Vessel Models

引用

Cyborg and Bionic systems 2023年第1期4卷 178-195页

作者： Seon-Jin Kim Min-Gyun Kim Jangho Kim Jessie SJeon Jinsoo Park Hee-Gyeong Yi Department of Rural and Biosystems Engineering College of Agriculture and Life SciencesChonnam National UniversityGwangjuRepublic of Korea Department of Convergence Biosystems Engineering College of Agriculture and Life SciencesChonnam National UniversityGwangjuRepublic of Korea Interdisciplinary Program in IT-Bio Convergence System Chonnam National UniversityGwangju 61186Republic of Korea Department of Mechanical Engineering Korea Advanced Institute of Science and TechnologyDaejeonRepublic of Korea Department of Mechanical Engineering Chonnam National UniversityRepublic of Korea

Dysfunctional blood vessels are implicated in various diseases,including cardiovascular diseases,neurodegenerative diseases,and *** studies have attempted to prevent and treat vascular diseases and understand interactions between these diseases and blood vessels across different organs and *** studies were conducted using 2-dimensional(2D)in vitro and animal ***,these models have difficulties in mimicking the 3D microenvironment in human,simulating kinetics related to cell activities,and replicating human pathophysiology;in addition,3D models involve remarkably high ***,in vitro bioengineered models(BMs)have recently gained *** created through biofabrication based on tissue engineering and regenerative medicine are breakthrough models that can overcome limitations of 2D and animal *** can also simulate the natural microenvironment in a patient-and target-specific *** this review,we will introduce 3D bioprinting methods for fabricating bioengineered blood vessel models,which can serve as the basis for treating and preventing various vascular ***,we will describe possible advancements from tubular to vascular ***,we will discuss specific applications,limitations,and future perspectives of fabricated BMs.

关键词： Blood organs printing

来源：评论

学校读者我要写书评

暂无评论

3D scaffolds-specific cellular mechanoresponse as a pivotal regulating factor in tissue engineering

引用

JMST Advances 2024年第2期6卷 121-134页

作者： Ahn, Yejin Chang, Hyewon Baek, Jieung Department of Biological Sciences Pusan National University Busan Republic of Korea Division of Mechanical and Biomedical Engineering Ewha Womans University Seoul Republic of Korea Graduate Program in System Health Science and Engineering Ewha Womans University Seoul Republic of Korea

In tissue engineering, the mechanical properties of the extracellular matrix (ECM) or scaffolds have increasingly been considered to impact therapeutic efficacy by regulating cell behaviors, including differentiation, proliferation, migration, and adhesion. However, the understanding of how cells sense, integrate, and convert the mechanical cues from the ECM cues into biochemical signals to control certain cell behaviors is still elusive, especially in 3D, which more closely mimics the natural microenvironment than 2D systems. This review highlights the key differences between 2 and 3D in the contexts of mechanoregulative cell behaviors such as cell adhesion, spreading, migration, and force transmission. Furthermore, critical designing factors that needs to be considered for the fabrication of 3D tissue engineering scaffolds is discussed: stiffness, viscoelasticity, degradability, and the immobilization of biomolecules. Although mechanotransduction in 3D is actively being studied, understanding cellular mechanotransduction in 3D and designing of mechanoregulative 3D scaffolds still presents several challenges, including varying mechanical properties depending on different tissues, dynamic mechanical environments, and integration of multimodal cues. Interdisciplinary methodologies encompassing material engineering, cell biology, and mechanical engineering would serve to mitigate these challenges and augment our understanding of mechanoregulation governing cellular behaviors, thus fostering advancements in biomedical applications in the future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous aerial perching and unperching using omnidirectional tiltrotor and switching controller

Autonomous aerial perching and unperching using omnidirectio...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Dongjae Lee Sunwoo Hwang Jeonghyun Byun Seung Jae Lee H. Jin Kim Department of Aerospace Engineering Seoul National University (SNU) Seoul South Korea Department of Mechanical System Design Engineering Seoul National University of Science and Technology (SEOULTECH) Seoul South Korea Department of Aerospace Engineering and Interdisciplinary Program in Artificial Intelligence (IPAI) Seoul National University Seoul Korea

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Aerial unperching of multirotors has received little attention as opposed to perching that has been investigated to elongate operation time. This study presents a new aerial robot capable of both perching and unperching autonomously on/from a ferromagnetic surface during flight, and a switching controller to avoid rotor saturation and mitigate overshoot during transition between free-flight and perching. To enable stable perching and unperching maneuvers on/from a vertical surface, a lightweight (≈ 1 kg), fully actuated tiltrotor that can hover at 90 ◦ pitch angle is first developed. We design a perching/unperching module composed of a single servomotor and a magnet, which is then mounted on the tiltrotor. A switching controller including exclusive control modes for transitions between free-flight and perching is proposed. Lastly, we propose a simple yet effective strategy to ensure robust perching in the presence of measurement and control errors and avoid collisions with the perching site immediately after unperching. We validate the proposed framework in experiments where the tiltrotor successfully performs perching and unperching on/from a vertical surface during flight. We further show effectiveness of the proposed transition mode in the switching controller by ablation studies where large overshoot and even collision with a perching site occur. To the best of the authors’ knowledge, this work presents the first autonomous aerial unperching framework using a fully actuated tiltrotor.

关键词： Measurement uncertainty Rotors Switches Control systems Autonomous aerial vehicles Task analysis Servomotors

来源：评论

学校读者我要写书评

暂无评论

multi-kernel and multi-scale learning based deep ensemble model for predicting recurrence of non-small cell lung cancer

引用

PeerJ Computer science 2023年 9卷

作者： Kim, Gihyeon Park, Young Mi Yoon, Hyun Jung Choi, Jang-Hwan Department of Computational Medicine Graduate Program in System Health Science and Engineering Ewha Womans University Seoul Korea Republic of Department of Molecular Medicine College of Medicine Ewha Womans University Seoul Korea Republic of Department of Radiology Veterans Health Service Medical Center Seoul Korea Republic of Division of Mechanical and Biomedical Engineering Graduate Program in System Health Science and Engineering Ewha Womans University Seoul Korea Republic of Department of Artificial Intelligence Ewha Womans University Seoul Korea Republic of

Predicting recurrence in patients with non-small cell lung cancer (NSCLC) before treatment is vital for guiding personalized medicine. Deep learning techniques have revolutionized the application of cancer informatics, including lung cancer timeto-event prediction. Most existing convolutional neural network (CNN) models are based on a single two-dimensional (2D) computational tomography (CT) image or three-dimensional (3D) CT volume. However, studies have shown that using multiscale input and fusing multiple networks provide promising performance. This study proposes a deep learning-based ensemble network for recurrence prediction using a dataset of 530 patients with NSCLC. This network assembles 2DCNNmodels of various input slices, scales, and convolutional kernels, using a deep learning-based feature fusion model as an ensemble strategy. The proposed framework is uniquely designed to benefit from (i) multiple 2D in-plane slices to provide more information than a single central slice, (ii) multi-scale networks and multi-kernel networks to capture the local and peritumoral features, (iii) ensemble design to integrate features from various inputs and model architectures for final prediction. The ensemble of five 2D-CNN models, three slices, and two multi-kernel networks, using 5×5 and 6×6 convolutional kernels, achieved the best performance with an accuracy of 69.62%, area under the curve (AUC) of 72.5%, F1 score of 70.12%, and recall of 70.81%. Furthermore, the proposed method achieved competitive results compared with the 2D and 3D-CNN models for cancer outcome prediction in the benchmark studies. Our model is also a potential adjuvant treatment tool for identifying NSCLC patients with a high risk of recurrence. © 2023 Kim et al.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Synthetic Data-Empowered Supervised Machine Learning Modeling for a Binary Fracture Risk Assessment from 2D-DXA Analysis

SSRN

引用

SSRN 2023年

作者： Choi, Heesun Quagliato, Luca Chung, Yoon-Sok Lee, Taeyong Division of Mechanical and Biomedical Engineering Ewha Womans University Seoul03760 Korea Republic of Division of Mechanical and Biomedical Engineering Graduate Program in System Health Science and Engineering Ewha Womans University Seoul03760 Korea Republic of Department of Endocrinology and Metabolism Ajou University School of Medicine Suwon16499 Korea Republic of

Background and Objectives: Bone fracture risk assessment for osteopenia and osteoporotic patients is essential for the adoption of early countermeasures and avoiding discomfort and hospitalization. Currently employed methodologies, such as FRAX®, provides a risk assessment over a five to ten years period without showing the main variables influencing the prediction nor how they can be targeted in the short term. Thus, a lesser black-box approach where the fracture risk can be assessed in real-time from a commonly employed analysis, id est the dual-energy X-ray absorptiometry (2D-DXA), would be of help to clinicians and patients alike. Accordingly, this study presents three real-time machine learning (ML) assessment models, with distinct complexity, architectures, and performances, capable of predicting a binary fracture risk based on a femur head-hip joint 2D-DXA scan. Methods: A ~10,000 adult Korean gathered between 2017 and 2021 and composed of ~90% female and ~10% male ranging from 50 to 99 years of age was considered. 10% of the data is relevant to subjects who experienced skeletal fractures, among which 245 cases are femur fractures. The 2D-DXA analyses of the femur head-hip joint region carried out on patients allowed collecting 23 parameters, including the patient’s age, BMI, and gender, associated with one binary variable, defined in terms of non-fracture (NFX) or fracture (FX), to be employed as the training dataset for the three ML models employed and optimized in this research. The 2D-DXA results’ database (DB) was employed to train three ML classifiers with a binary (NFX/FX) output layer, namely the Extreme Gradient Boosting (XGB), the K-Nearest Neighbor (KNN), and Deep Neural Network (DNN). To avoid overfitting due to the higher number of NFX data with respect to FX one, two features augmentation techniques based on the Synthetic Minority Over-sampling Technique (SMOTE) and Oversample using Adaptive Synthetic (ADASYN) oversamplers were employed. For all

关键词： Fracture

来源：评论

学校读者我要写书评

暂无评论

A Study on Giant Magnetostrictive Actuator for Interior Sound Control system of the Ultra-Compact Mobility: Fundamental Consideration on Formation of the Giant Magnetostrictive Phases Depending on Heat Treatment Condition

A Study on Giant Magnetostrictive Actuator for Interior Soun...

引用

International Conference on Electrical Machines and systems (ICEMS)

作者： Taro Kato Ryusei Naganuma Koki Bando Kentaro Sawada Wu Wenbao Ikkei Kobayashi Jumpei Kuroda Daigo Uchino Kazuki Ogawa Keigo Ikeda Ayato Endo Hideaki Kato Takayoshi Narita Mitusaki Furui Department of Mechanical Engineering Tokyo University of Technology Hachioji-shi Tokyo Japan Sustainable Engineering Program Graduate School of Engineering Tokyo University of Technology Hachioji-shi Tokyo Japan Course of Mechanical Engineering Tokai University Hiratsuka-shi Kanagawa Japan Course of Science and Technology Tokai University Hiratsuka-shi Kanagawa Japan Department of Mechanical Engineering National Institute of Technology (KOSEN) Numazu College Numazu-shi Shizuoka Japan Department of Electronic Robotics Aichi University of Technology Gamagori-shi Aichi Japan Department of Mechanical Engineering Hokkaido University of Science Sapporo Hokkaido Japan Department of Electrical Engineering Fukuoka Institute of Technology Fukuoka-shi Fukuoka Japan Department of Mechanical System Engineering Tokai University Hiratsuka-shi Kanagawa Japan

ISBN: (数字)9784886864406

ISBN: (纸本)9798350379105

An active noise control system using giant magnetostrictive actuator has been proposed as a countermeasure for interior noise of the ultra-compact mobilities, which is a new transportation tools. In this paper, as basic research toward the development of the proposed giant magnetostrictive actuator for active noise control, we conduct experiments on the material properties when terbium, dysprosium, and iron powder, which make up the giant magnetostrictive material, are mixed and the heat treatment conditions are changed. In this study, the heat treatment temperature was varied from $800^{\circ}\mathrm{C}$ to $1100^{\circ}\mathrm{C}$ in $100^{\circ}\mathrm{C}$ incrementsbased on the equilibrium state temperature of each material, and the heat treatment time was set in 30-minute increments from 1 hour to 3 hours. As a result, TbFe2 was confirmed after heat treatment at an electric furnace temperature of $1000^{\circ}\mathrm{C}$ for 3 hours, although its strength was insufficient.

关键词： Actuators Heat treatment Powders Temperature Magnetostriction Noise Terbium Iron Resistance heating Material properties

来源：评论

学校读者我要写书评

暂无评论

A Study on Giant Magnetostrictive Actuator for Interior Soun...

引用

27th International Conference on Electrical Machines and systems, ICEMS 2024

作者： Kato, Taro Naganuma, Ryusei Bando, Koki Sawada, Kentaro Wenbao, Wu Kobayashi, Ikkei Kuroda, Jumpei Uchino, Daigo Ogawa, Kazuki Ikeda, Keigo Endo, Ayato Kato, Hideaki Narita, Takayoshi Furui, Mitusaki Tokyo University of Technology Department of Mechanical Engineering 1404-1 Katakura Hachioji-shi Tokyo192-0982 Japan Sustainable Engineering Program Graduate School of Engineering Tokyo University of Technology 1404-1 Katakura Hachioji-shi Tokyo192-0982 Japan Tokai University Kitakaname 4-1-1 Kanagawa Hiratsuka-shi259-1292 Japan Tokai University Kitakaname 4-1-1 Kanagawa Hiratsuka-shi259-1292 Japan Numazu College Department of Mechanical Engineering Ohoka 3600 Shizuoka Numazu-shi410-0022 Japan Aichi University of Technology Department of Electronic Robotics 50-2 Manori Nishisako-machi Aichi Gamagori-shi443-0047 Japan Hokkaido University of Science Department of Mechanical Engineering 7-Jo 15-4-1 Maeda Teine Hokkaido Sapporo006-8585 Japan Fukuoka Institute of Technology Department of Electrical Engineering Wajiro Higashi 3-30-1 Higashi-ku Fukuoka Fukuoka-shi811-0295 Japan Tokai University Department of Mechanical System Engineering Kitakaname 4-1-1 Kanagawa Hiratsuka-shi259-1292 Japan

ISBN: (纸本)9784886864406

An active noise control system using giant magnetostrictive actuator has been proposed as a countermeasure for interior noise of the ultra-compact mobilities, which is a new transportation tools. In this paper, as basic research toward the development of the proposed giant magnetostrictive actuator for active noise control, we conduct experiments on the material properties when terbium, dysprosium, and iron powder, which make up the giant magnetostrictive material, are mixed and the heat treatment conditions are changed. In this study, the heat treatment temperature was varied from 800°C to 1100°C in 100°C incrementsbased on the equilibrium state temperature of each material, and the heat treatment time was set in 30-minute increments from 1 hour to 3 hours. As a result, TbFe2 was confirmed after heat treatment at an electric furnace temperature of 1000°C for 3 hours, although its strength was insufficient. © 2024 The Institute of Electrical Engineers of Japan.

关键词： Active noise control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：