检索结果-内蒙古大学图书馆

Learning to Localize Cross-Anatomy Landmarks in X-Ray Images with a Universal Model

biomedical Engineering Frontiers 2022年第1期3卷 298-308页

作者： Heqin Zhu Qingsong Yao Li Xiao S.Kevin Zhou Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China Center for Medical Imaging RoboticsAnalytic Computing&Learning(MIRACLE)School of Biomedical Engineering&Suzhou Institute for Advanced ResearchUniversity of Science and Technology of ChinaSuzhou 215123China

Objective and Impact *** this work,we develop a universal anatomical landmark detection model which learns once from multiple datasets corresponding to different anatomical *** with the conventional model trained on a single dataset,this universal model not only is more light weighted and easier to train but also improves the accuracy of the anatomical landmark *** accurate and automatic localization of anatomical landmarks plays an essential role in medical image ***,recent deep learning-based methods only utilize limited data from a single *** is promising and desirable to build a model learned from different regions which harnesses the power of big *** model consists of a local network and a global network,which capture local features and global features,*** local network is a fully convolutional network built up with depth-wise separable convolutions,and the global network uses dilated convolution to enlarge the receptive field to model global *** evaluate our model on four 2D X-ray image datasets totaling 1710 images and 72 landmarks in four anatomical *** experimental results show that our model improves the detection accuracy compared to the state-of-the-art *** model makes the first attempt to train a single network on multiple datasets for landmark *** results qualitatively and quantitatively show that our proposed model performs better than other models trained on multiple datasets and even better than models trained on a single dataset separately.

关键词： convolution utilize separable

来源：评论

学校读者我要写书评

暂无评论

GENERATION AND DISTRIBUTION OF PRIME NUMBERS USING A MODIFIED LAGRANGE POLYNOMIAL

arXiv

引用

arXiv 2023年

作者： Sivaraman, Dileep Pillai, Branesh M. Suthakorn, Jackrit Ongwattanakul, Songpol Center for Biomedical and Robotics Technology BART LAB Faculty of Engineering Mahidol University Phutthamonthon District Nakhon Pathom73170 Thailand

A modified Lagrange Polynomial is introduced for polynomial extrapolation, which can be used to estimate the equally spaced values of a polynomial function. As an example of its application, this article presents a prime-generating algorithm based on a 1-degree polynomial that can generate prime numbers from consecutive primes. The algorithm is based on the condition that infinitely many prime numbers exist that satisfy the equation Πn = 2Πn−1 − Πn−2 ± 2 ∀ Πn > 7. where Πn−1 and Πn−2 are the consecutive primes. Copyright © 2023, The Authors. All rights reserved.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Intelligent upper-limb exoskeleton integrated with soft bioelectronics and deep learning for intention-driven augmentation

引用

npj Flexible Electronics 2024年第1期8卷 856-868页

作者： Jinwoo Lee Kangkyu Kwon Ira Soltis Jared Matthews Yoon Jae Lee Hojoong Kim Lissette Romero Nathan Zavanelli Youngjin Kwon Shinjae Kwon Jimin Lee Yewon Na Sung Hoon Lee Ki Jun Yu Minoru Shinohara Frank L.Hammond Woon-Hong Yeo Department of Mechanical Roboticsand Energy EngineeringDongguk UniversitySeoul 04620Republic of Korea IEN Center for Wearable Intelligent Systems and Healthcare Institute for Electronics and NanotechnologyGeorgia Institute of TechnologyAtlantaGA 30332USA School of Electrical and Computer Engineering Georgia Institute of TechnologyAtlantaGA 30332USA George W.Woodruff School of Mechanical Engineering Georgia Institute of TechnologyAtlantaGA 30332USA School of Industrial Design Georgia Institute of TechnologyAtlantaGA 30332USA School of Electrical and Electronic Engineering Yonsei UniversitySeoul 03722Republic of Korea School of Biological Sciences Georgia Institute of TechnologyAtlantaGA 30332USA Wallace H.Coulter Department of Biomedical Engineering Georgia Institute of Technology and Emory University School of MedicineAtlantaGA 30332USA Institute for Materials Parker H.Petit Institute for Bioengineering and BiosciencesInstitute for Robotics and Intelligent MachinesGeorgia Institute of TechnologyAtlantaGA 30332USA

The age and stroke-associated decline in musculoskeletal strength degrades the ability to perform daily human tasks using the upper ***,we introduce an intelligent upper-limb exoskeleton system that utilizes deep learning to predict human intention for strength *** embedded soft wearable sensors provide sensory feedback by collecting real-time muscle activities,which are simultaneously computed to determine the user’s intended *** deep learning predicts four upper-limb joint motions with an average accuracy of 96.2%at a 500–550 ms response rate,suggesting that the exoskeleton operates just by human *** addition,an array of soft pneumatics assists the intended movements by providing 897 newtons of force while generating a displacement of 87mm at *** intent-driven exoskeleton can reduce human muscle activities by 3.7 times on average compared to the unassisted exoskeleton.

关键词： skeleton learning utilize

来源：评论

学校读者我要写书评

暂无评论

Mode-switching single-pixel imaging via a high-performance perovskite-Si dual-mode photodetector

引用

Photonics Research 2024年第12期12卷 2873-2880页

作者： YUJIN LIU DONGXU LIN JINGYANG XING HANYAN ZHAO HONGLING WAN HAO WANG ZHONG JI XUELI CHEN Innovation Center for Advanced Medical Imaging and Intelligent Medicine Guangzhou Institute of TechnologyXidian UniversityGuangzhou 510555China Shenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Systems Department of Mechanical and Energy EngineeringSUSTech Energy Institute for Carbon NeutralitySouthern University of Science and TechnologyShenzhen 518055China Center for Biomedical-Photonics and Molecular Imaging Advanced Diagnostic-Therapy Technology and Equipment Key Laboratory of Higher Education Institutions in Shaanxi ProvinceSchool of Life Science and TechnologyXidian UniversityXi’an 710126China

Visible–near-infrared(VIS-NIR)dual-mode imaging can expand the human perception ***,the development of dual-mode image sensors is still challenging due to complex fabrication processes and readout circuit ***,we design a simple-structured(perovskite-Au/Si/Ag)dual-mode *** unique asymmetric electrode design allows the device to support two operating modes at zero *** device exhibits a detection range covering 400–1100 nm under top illumination mode,with a peak specific detectivity of up to 5.56×1013 *** bottom illumination mode,the device demonstrates pronounced narrowband NIR response *** importantly,we develop a dual-mode single-pixel imaging system based on this device,bypassing the fabrication processes of high-density array image *** system exhibits excellent VISNIR dual-mode imaging results,effectively separating NIR and VIS information and enhancing infrared details in the fused ***,we discover that the system can effectively suppress ringing artifacts,achieving infrared information perception at a low sampling rate,which can accelerate the imaging speed by∼16 times(reduced from∼3.2 s to∼0.2 s).Our proposed dual-mode single-pixel imaging technology offers new means for material identification and intelligent perception.

关键词： mode illumination details

来源：评论

学校读者我要写书评

暂无评论

Soft wearable flexible bioelectronics integrated with an anklefoot exoskeleton for estimation of metabolic costs and physical effort

引用

npj Flexible Electronics 2023年第1期7卷 535-544页

作者： Jihoon Kim Prakyath Kantharaju Hoon Yi Michael Jacobson Hyungkeun Jeong Hojoong Kim Jinwoo Lee Jared Matthews Nathan Zavanelli Hyeonseok Kim Heejin Jeong Myunghee Kim Woon-Hong Yeo IEN Center for Human-Centric Interfaces and Engineering and George W.Woodruff School of Mechanical Engineering Georgia Institute of TechnologyAtlantaGA 30332USA Department of Mechanical and Industrial Engineering the University of Illinois at ChicagoChicagoIL 60607USA Department of Mechanical Roboticsand Energy EngineeringDongguk UniversitySeoulRepublic of Korea Human Systems Engineering The Polytechnic SchoolIra A.Fulton Schools of EngineeringArizona State UniversityMesaAZ 85212USA Wallace H.Coulter Department of Biomedical Engineering Georgia Institute of Technology and Emory University School of MedicineAtlantaGA 30332USA Institute for Robotics and Intelligent Machines Parker H.Petit Institute for Bioengineering and BiosciencesInstitute for MaterialsNeural Engineering CenterGeorgia Institute of TechnologyAtlantaGA 30332USA

Activities and physical effort have been commonly estimated using a metabolic rate through indirect calorimetry to capture breath *** physical effort represents the work hardness used to optimize wearable robotic ***,personalization and rapid optimization of the effort are *** respirometry is the gold standard for estimating metabolic costs,this method requires a heavy,bulky,and rigid system,limiting the system’s field ***,this paper reports a soft,flexible bioelectronic system that integrates a wearable ankle-foot exoskeleton,used to estimate metabolic costs and physical effort,demonstrating the potential for real-time wearable robot adjustments based on *** from a set of activities,including walking,running,and squatting with the biopatch and exoskeleton,determines the relationship between metabolic costs and heart rate variability root mean square of successive differences(HRV-RMSSD)(R=−0.758).Collectively,the exoskeleton-integrated wearable system shows potential to develop a field-deployable exoskeleton platform that can measure wireless real-time physiological signals.

关键词： skeleton wear estimation

来源：评论

学校读者我要写书评

暂无评论

The role of artificial intelligence and IoT in prediction of earthquakes:Review

引用

Artificial Intelligence in Geosciences 2024年第1期5卷 154-172页

作者： Joshua Pwavodi Abdullahi Umar Ibrahim Pwadubashiyi Coston Pwavodi Fadi Al-Turjman Ali Mohand-Said Ecole et Observatoire des Sciences de La Terre ITES UMR7063-CNRS/Universit’e de Strasbourg5 rue Rene Descartes67084StrasbourgFrance Research Center for Science Technology and Engineering(BILTEM)Near East University99138NicosiaTRNCMersin 10Turkey Department of Biomedical Engineering Near East UniversityMersin 10Nicosia99010Turkey Department of Biomedical Engineering Faculty of EngineeringCyprus International UniversityHaspolatNorth Cyprus via Mersin 10Nicosia99258Turkey Artificial Intelligence Engineering Department AI and Robotics InstituteNear East UniversityMersin99138Turkey Research Center for AI and IoT Faculty of EngineeringUniversity of KyreniaMersin 99138Turkey

Earthquakes are classified as one of the most devastating natural disasters that can have catastrophic effects on the environment,lives,and *** has been an increasing interest in the prediction of earthquakes and in gaining a comprehensive understanding of the mechanisms that underlie their generation,yet earthquakes are the least predictable natural *** data,global positioning system,interferometry synthetic aperture radar(InSAR),and seismometers such as microelectromechanical system,seismometers,ocean bottom seismometers,and distributed acoustic sensing systems have all been used to predict earthquakes with a high degree of *** advances in seismic wave recording,storage,and analysis,earthquake time,location,and magnitude prediction remain *** the other hand,new developments in artificial intelligence(AI)and the Internet of Things(IoT)have shown promising potential to deliver more insights and ***,this article reviewed the use of AI-driven Models and IoT-based technologies for the prediction of earthquakes,the limitations of current approaches,and open research *** review discusses earthquake prediction setbacks due to insufficient data,inconsistencies,diversity of earthquake precursor signals,and the earth’s geophysical ***,this study examines potential approaches or solutions that scientists can employ to address the challenges they face in earthquake *** analysis is based on the successful application of AI and IoT in other fields.

关键词： Earthquakes Seismicity Artificial intelligence Internet of things Prediction

来源：评论

学校读者我要写书评

暂无评论

Localization of the Upper Extremity Area on the Primary Motor Cortex with Transcranial Magnetic Stimulation Figure-of-Eight Coil: A Clinical Study

Localization of the Upper Extremity Area on the Primary Moto...

引用

Rehabilitation Engineering and Assistive technology (i-CREATe), International Convention on

作者： Daral Maesincee Jackrit Suthakorn Sorayouth Chumnanvej (BART LAB) Faculty of Engineering Center for Biomedical and Robotics Technology Mahidol University Nakhon Pathom Thailand Department of Surgery Faculty of Medicine Ramathibodi Hospital Mahidol University Bangkok Thailand

ISBN: (数字)9798350355154

ISBN: (纸本)9798350355161

Although stroke has always been a major cause of long-term disability, mostly occurring in the upper extremities, the current conventional rehabilitative options remain both insufficient and ineffective in restoring full motor functions. As a promising alternative solution, transcranial magnetic stimulation (TMS) can non-invasively alter the excitability of and modulate the connections within the lesioned area with electromagnetic fields through a stimulating coil. Nevertheless, identifying the upper extremity area on the primary motor cortex (M1) in different patients remains a challenge due to the heterogeneous nature of the anatomy both in terms of size and location. Therefore, this study offers a method for localizing the region of interest (ROI) through an integrated method of TMS, electromyography (EMG), and optical tracking, supported by data from a clinical study, to provide an accurate and personalized ground truth for future stimulations of the same location in each patient.

关键词： Primary motor cortex Integrated optics Location awareness Coils Target tracking Transcranial magnetic stimulation Stimulated emission Stroke (medical condition) Electromyography Extremities

来源：评论

学校读者我要写书评

暂无评论

Design and evaluation of a multi-finger skin-stretch tactile interface for hand rehabilitation robots

arXiv

引用

arXiv 2024年

作者： Ratschat, Alexandre L. Martín-Rodríguez, Rubén Vardar, Yasemin Ribbers, Gerard M. Marchal-Crespo, Laura The Department of Cognitive Robotics Delft University of Technology Delft Netherlands The Department of Rehabilitation Medicine Erasmus MC University Medical Center Rotterdam Rotterdam Netherlands The ARTORG Center for Biomedical Engineering Research University of Bern Switzerland

Object properties perceived through the tactile sense, such as weight, friction, and slip, greatly influence motor control during manipulation tasks. However, the provision of tactile information during robotic training in neurorehabilitation has not been well explored. Therefore, we designed and evaluated a tactile interface based on a two-degrees-of-freedom moving platform mounted on a hand rehabilitation robot that provides skin stretch at four fingertips, from the index through the little finger. To accurately control the rendered forces, we included a custom magnetic-based force sensor to control the tactile interface in a closed loop. The technical evaluation showed that our custom force sensor achieved measurable shear forces of ± 8 N with accuracies of 95.2-98.4% influenced by hysteresis, viscoelastic creep, and torsional deformation. The tactile interface accurately rendered forces with a step response steady-state accuracy of 97.5-99.4% and a frequency response in the range of most activities of daily living. Our sensor showed the highest measurement-range-to-size ratio and comparable accuracy to sensors of its kind. These characteristics enabled the closed-loop force control of the tactile interface for precise rendering of multi-finger two-dimensional skin stretch. The proposed system is a first step towards more realistic and rich haptic feedback during robotic sensorimotor rehabilitation, potentially improving therapy outcomes. © 2024, CC BY.

关键词： Frequency response

来源：评论

学校读者我要写书评

暂无评论

M-fiducial phantom based fast automatic ultrasound calibration technique: A novel approach for 2D to 3D image registration

引用

Heliyon 2024年第22期10卷 e40290页

作者： Suthakorn, Jackrit Chatrasingh, Maria Wiratkapun, Cholatip Ongwattanakul, Songpol Department of Biomedical Engineering Center for Biomedical and Robotics Technology (BART LAB) Faculty of Engineering Mahidol University Salaya Thailand Department of Radiology Faculty of Medicine Ramathibodi Hospital Mahidol University Bangkok Thailand

This study introduces a novel M-fiducial phantom-based automatic ultrasound (US) calibration technique aimed at improving 2D to 3D image registration in ultrasound-guided procedures. The technique addresses limitations in existing methods by enhancing feature extraction capabilities and improving calibration accuracy. The proposed method utilizes an M-fiducial phantom, an extended version of the standard N-fiducial phantom, designed to facilitate automatic extraction with a linear probe, particularly in small field-of-view scenarios. A closed-form solution incorporating anisotropic scaling enables rapid and precise computation of transformation matrices for ultrasound calibration, and the method was tested across varying ultrasound depths to evaluate performance in point localization, length measurement, and volume estimation. Results show that the automatic extraction method, combined with the anisotropic closed-form solution, offers greater accuracy and reliability compared to manual methods. While in-plane measurements demonstrated high accuracy, out-plane estimations revealed potential limitations, especially with wire phantoms at increased depths. Despite these challenges, the M-fiducial phantom-based technique reduces operator workload and enhances ultrasound calibration precision, making it a promising approach for high-precision ultrasound-guided interventions. Future work should focus on refining the technique and validating its efficacy in clinical applications. © 2024 The Authors

关键词： 3D registration M-Fiducial phantom Non-uniform scaling Point set registration Ultrasound calibration Ultrasound images

来源：评论

学校读者我要写书评

暂无评论

Hybrid Image-Based Motion Tracking and Adaptive Polynomial Kalman Filter for a Bio-Inspired Dual-Sheath Needle System

Hybrid Image-Based Motion Tracking and Adaptive Polynomial K...

引用

IEEE International Conference on robotics and Biomimetics

作者： Dileep Sivaraman Cholatip Wiratkapun Branesh M. Pillai Jackrit Suthakorn Boriphat Methachan Sakol Nakdhamabhorn Songpol Ongwattanakul Department of Biomedical Engineering Center for Biomedical and Robotics Technology (BART LAB) Faculty of Engineering Mahidol University Thailand Department of Radiology Breast Diagnostic Center Division of Diagnostic Radiology Faculty of Medicine Ramathibodi Hospital Mahidol University Bangkok Thailand Functional Materials for Novel Engineering Applications National Science and Technology Development Agency Thailand

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

This preliminary study investigated sensor-fusion methods for accurate motion estimation in a bio-inspired dual-sheath needle system designed for biopsy applications. The needle system draws inspiration from the segmented dual-sheath mechanism of ovipositors found in Hymenoptera species, which allows controlled and precise movement. The aim is to develop a reliable tracking system for both the needle tip and base, which is essential for accurate needle placement during biopsy procedures. A hybrid tracking approach was used to achieve this, combining image-based tracking of the needle tip with an Inertial Measurement Unit (IMU) sensor for needle-base tracking. An Adaptive Polynomial Kalman Filter (APKF) was applied to improve the motion estimation accuracy. Performance tests on a linear-rail system demonstrated the ability of the developed system to provide accurate and consistent motion estimates. The results suggest that this bio-inspired needle system using sensor fusion and advanced filtering holds promise for use in medical robotics, potentially improving the precision of biopsy procedures.

关键词： Accuracy Tracking Motion segmentation Motion estimation Biopsy Needles Robot sensing systems Polynomials Kalman filters biomedical imaging

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：