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

Deep-Learning Estimation of Weight Distribution Using Joint Kinematics for Lower-Limb Exoskeleton Control

arXiv

引用

arXiv 2024年

作者： Lhoste, Clément Küçüktabak, Emek Barış Vianello, Lorenzo Amato, Lorenzo Short, Matthew R. Lynch, Kevin M. Pons, Jose L. Legs and Walking Lab Shirley Ryan AbilityLab ChicagoIL United States Center for Robotics and Biosystems Department of Mechanical Engineering Northwestern University Shirley Ryan AbilityLab EvanstonIL United States Shirley Ryan AbilityLab The Biorobotics Institute Scuola Superiore Sant’Anna Pontedera56025 Italy Department of Excellence in Robotics & AI Scuola Superiore Sant’Anna Pisa56127 Italy Shirley Ryan AbilityLab Department of Biomedical Engineering Northwestern University EvanstonIL United States Center for Robotics and Biosystems Department of Mechanical Engineering Northwestern University United States Shirley Ryan AbilityLab Center for Robotics and Biosystems Department of Mechanical Engineering Department of Biomedical Engineering Department of Physical Medicine and Rehabilitation Northwestern University United States

In the control of lower-limb exoskeletons with feet, the phase in the gait cycle can be identified by monitoring the weight distribution at the feet. This phase information can be used in the exoskeleton’s controller to compensate the dynamics of the exoskeleton and to assign impedance parameters. Typically the weight distribution is calculated using data from sensors such as treadmill force plates or insole force sensors. However, these solutions increase both the setup complexity and cost. For this reason, we propose a deep-learning approach that uses a short time window of joint kinematics to predict the weight distribution of an exoskeleton in real time. The model was trained on treadmill walking data from six users wearing a four-degree-of-freedom exoskeleton and tested in real time on three different users wearing the same device. This test set includes two users not present in the training set to demonstrate the model’s ability to generalize across individuals. Results show that the proposed method is able to fit the actual weight distribution with R2 = 0.9 and is suitable for real-time control with prediction times less than 1 ms. Experiments in closed-loop exoskeleton control show that deep-learning-based weight distribution estimation can be used to replace force sensors in overground and treadmill walking. © 2024, CC BY.

关键词： Exoskeleton (robotics)

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

Elliptical Magnetic Nanoparticle Swarm Formation by an Artificial Neural Network-Based Rotating Magnetic Field

引用

IEEE Transactions on Automation Science and engineering 2025年 22卷 16692-16703页

作者： Jongwon Park Uijeong Lee Yunjae Hwang Dahye Lee Sarmad Ahmad Abbasi Hongsoo Choi School of Undergraduate Studies Daegu Gyeongbuk Institute of Science and Technology (DGIST) Daegu Republic of Korea Department of Robotics and Mechatronics Engineering and the DGIST-ETH Microrobot Research Center Daegu Gyeongbuk Institute of Science and Technology Daegu South Korea Department of Biomedical Engineering University of Massachusetts Amherst Amherst MA USA

biomedical applications of magnetic nanoparticle (MNP) swarm control rely on precise manipulation of the swarm using magnetic fields. This approach improves the accessibility and maneuverability of the swarm and enhances targeted therapies and drug delivery. In this study, we applied artificial intelligence to control the shape of elliptical MNP swarms by adjusting the parameters of a rotating magnetic field (RMF). The resulting RMF controlled the major axis and slant angle of the ellipse-shaped swarm. We constructed a dataset of diverse swarm shapes and corresponding RMF parameters, and applied it to train an artificial neural network (ANN). The trained ANN was used to predict the experimental RMF parameters required to achieve the desired shapes of elliptical MNP swarms. After ANN training, differences between the predicted and actual root mean square error (RMSE) values were evaluated to verify the model. The RMSEs of the major and minor axis lengths and slant angle were 0.21 mm, 0.06 mm, and 6.01°, respectively. This simple, inference-based approach to swarm formation yielded higher swarm formation accuracy and allowed fine control of the swarm. Note to Practitioners—Magnetic nanoparticle swarms have shown good potential for precise and non-invasive targeted drug delivery and therapies. The motivation for this work originates from the need for a faster and more efficient process of generating magnetic nanoparticle swarms and their shape control. Currently used approaches for swarm formation rely on generating a table of rotating field parameters corresponding to different swarm shapes and size or automatic closed loop controllers. These processes are slow and can result in collapse of swarm shape due to instantaneous change in the rotating magnetic field parameters. To tackle these drawbacks, we propose a machine learning based model for swarm formation and shape control. The trained artificial neural network not only enabled faster swarm formation due to its fa

关键词： Magnetic fields Shape Artificial neural networks Force Artificial intelligence Training Magnetic nanoparticles Torque Shape control Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A Hybrid EEG-EMG Framework for Humanoid Control using Deep Learning Transformers

A Hybrid EEG-EMG Framework for Humanoid Control using Deep L...

引用

IEEE International Conference on robotics and Biomimetics

作者： Parthan Olikkal Branesh M. Pillai Jackrit Suthakorn Habib Ali Ramana Vinjamuri Department of Computer Science and Electrical Engineering Vinjamuri lab University of Maryland Baltimore County Baltimore MD USA Center for Biomedical and Robotics Technology Mahidol University Salaya Nakorm Pathom Thailand

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

Brain-computer interfaces (BCIs) offer promising solutions for upper limb rehabilitation. Despite advancements in deep learning, traditional models for motor rehabilitation using electroencephalography (EEG) or electromyography (EMG) to control assistive devices require enhancement. This study aims to enhance motor control capabilities by integrating EEG and EMG signals using a Transformer-based deep learning model. Ten able-bodies subjects performed center-out tasks on a low-cost upper limb rehabilitation table, capturing 2D kinematic data, EEG, and EMG signals simultaneously. The tasks varied in complexity across four levels. Preprocessed EEG and EMG signals were fused and given as input to the proposed model, which was evaluated using three performance metrics. Results showed that the EEG-EMG combined model achieved 87.27% accuracy across all the four levels. Furthermore, the model's output successfully controlled a humanoid robot to replicate similar movements. These findings highlight the efficacy of combined EEG-EMG data in improving accuracy and performance in BCI applications, advancing assistive technologies and neurorehabilitation interventions.

关键词： Deep learning Accuracy Humanoid robots Brain modeling Transformers Motors Electromyography Electroencephalography Data models Brain-computer interfaces

来源：评论

学校读者我要写书评

暂无评论

16-Layer 3D Stacking Based on Self-Assembly Technology for HBM Application

16-Layer 3D Stacking Based on Self-Assembly Technology for H...

引用

IEEE International Conference on 3D System Integration, 3DIC

作者： Du Zehua Hiroshi Kikuchi Hayato Hishinuma Tetsu Tanaka Takafumi Fukushima Graduate School of Engineering Tohoku University Sendai Japan Advanced Technology Development Center Yamaha Robotics Holdings Co. Ltd. Tokyo Japan Graduate School of Biomedical Engineering Tohoku University Sendai Japan

ISBN: (数字)9798331516505

ISBN: (纸本)9798331516512

We address a trade-off issue between chip assembly time and positioning accuracy in a traditional pick-and-place method using self-assembly technology driven by liquid surface tension. This method allows 16-layer stacking of 50-um-thin chips fabricated via Plasma Dicing Before Grinding (PDBG). The surface tension of liquid droplets enables sub-50 nm alignment accuracy even with manual chip placement. By identifying key parameters such as pre-alignment position and liquid volume/distribution, we optimize the self-assembly process for High Bandwidth Memory (HBM) applications. Additionally, we discuss the effects of liquid bridges and wetting contrast between the chip surface and sidewall on multi-layer stacking.

关键词： Bridges Liquids Accuracy Self-assembly Three-dimensional displays Stacking System integration Surface tension Plasmas Surface treatment

来源：评论

学校读者我要写书评

暂无评论

BlanketGen - A Synthetic Blanket Occlusion Augmentation Pipeline for Motion Capture Datasets

BlanketGen - A Synthetic Blanket Occlusion Augmentation Pipe...

引用

Bioengineering (ENBENG), Portuguese Meeting in

作者： João Carmona Tamás Karácsony João Paulo Silva Cunha Center for Biomedical Engineering Research INESC TEC Porto Portugal Faculty of Engineering (FEUP) University of Porto Porto Portugal Robotics Institute Carnegie Mellon University Pittsburgh PA USA

Human motion analysis has seen drastic improvements recently, however, due to the lack of representative datasets, for clinical in-bed scenarios it is still lagging behind. To address this issue, we implemented BlanketGen, a pipeline that augments videos with synthetic blanket occlusions. With this pipeline, we generated an augmented version of the pose estimation dataset 3DPW called BlanketGen-3DPW. We then used this new dataset to fine-tune a Deep Learning model to improve its performance in these scenarios with promising results. Code and further information are available at https://***/brain-lab/brain-lab-public/blanket-gen-releases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BlanketSet - A Clinical Real-World In-Bed Action Recognition and Qualitative Semi-Synchronised Motion Capture Dataset

BlanketSet - A Clinical Real-World In-Bed Action Recognition...

引用

Bioengineering (ENBENG), Portuguese Meeting in

Clinical in-bed video-based human motion analysis is a very relevant computer vision topic for several relevant biomedical applications. Nevertheless, the main public large datasets (e.g. ImageNet or 3DPW) used for deep learning approaches lack annotated examples for these clinical scenarios. To address this issue, we introduce BlanketSet, an RGB-IR-D action recognition dataset of sequences performed in a hospital bed. This dataset has the potential to help bridge the improvements attained in more general large datasets to these clinical scenarios. Information on how to access the dataset is available at ***/dataset/nis-2022-004.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Post-Stroke Upper Limb Rehabilitation Through Haptic Feedback in Virtual Reality-Based Gaming

Enhancing Post-Stroke Upper Limb Rehabilitation Through Hapt...

引用

IEEE International Conference on robotics and Biomimetics

作者： Branesh M. Pillai Napas Siripala Kongtup Sai-Aroon Dileep Sivaraman Ramana Vinjamuri Sorayouth Chumnanvej Jackrit Suthakorn Department of Biomedical Engineering Faculty of Engineering Center for Biomedical and Robotics Technology (BART LAB) Mahidol University Thailand Vinjamuri lab in the Department of Computer Science and Electrical Engineering University of Maryland Baltimore County Baltimore MD USA Department of Surgery Neurosurgery Division Faculty of Medicine Ramathibodi Hospital Mahidol University Bangkok Thailand

ISBN: (数字)9798331509644

ISBN: (纸本)9798331509651

This preliminary study explores developing and implementing upper-limb rehabilitation tools utilizing haptic feedback and 3D spatial recognition analysis in a virtual reality (VR) environment. The effectiveness of upper limb rehabilitation in post-stroke patients was investigated by analyzing the joint and gimbal range of motion (ROM), ROM ratios, and force distribution through various drawing tasks. This study evaluated the impact of different drawing patterns on joint and gimbal ROM, and the force applied during rehabilitation exercises. This study revealed significant variability in ROM across different tasks by combining ROM measurements with force data and employing heat maps for visual representation. These findings emphasize the need for task-specific adjustments to improve rehabilitation outcomes. This study highlights the potential of incorporating advanced technologies, such as VR-based tools with haptic feedback and 3D spatial recognition, to enhance patient engagement and rehabilitation effectiveness.

关键词： Limbs Visualization Three-dimensional displays Tracking Force Medical treatment Virtual reality Haptic interfaces Motion control Read only memory

来源：评论

学校读者我要写书评

暂无评论

An Effective Image Enhancement Method for Color Fundus Images 21

An Effective Image Enhancement Method for Color Fundus Image...

引用

Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence

作者： Zhan Wang SongPo Tian Xin Fu JiaZhen He School of Biomedical Engineering Guangdong Medical University China Engineering Research Center for Intelligent Robotics (ERCIR) Jihua Laboratory China

ISBN: (纸本)9781450385053

A method is proposed for adaptive fundus image enhancement so as to restore the color images that are with extremely low or nonuniform brightness. Our proposed method is capable of increasing the brightness, contrast of images without losing original color hue. It includes three steps: luminance enhancement, contrast improvement, and color restoration. All procedures are adapted and modified from conventional image processing algorithms, which are proved simple and less time-consuming. Two public and commonly used fundus image database were partially employed to evaluate the performance of our method. It is concluded that the brightness of images was enhanced by 86.35 % and the contrast was improved by 132.37 % without color distortion.

关键词： biomedical imaging algorithms contrast enhancement Fundus angiography Image restoration

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：