检索结果-内蒙古大学图书馆

Image segmentation network for laparoscopic surgery

Biomimetic Intelligence and robotics 2025年

作者： Kang Peng Yaoyuan Chang Guodong Lang Jian Xu Yongsheng Gao Jiajun Yin Jie Zhao The State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin 150000 China Zhongshan Hospital Affiliated to Dalian University Dalian 116000 China

Surgical image segmentation serves as the foundation for laparoscopic surgical navigation technology. The indistinct local features of biological tissues in laparoscopic image pose challenges for image segmentation. To address this issue, we develop an image segmentation network tailored for laparoscopic surgery. Firstly, we introduce the Mixed Attention Enhancement (MAE) module that sequentially conducts the Channel Attention Enhancement (CAE) module and the Global Feature Enhancement (GFE) module linked in series. The CAE module enhances the network’s perception of prominent channels, allowing feature maps to exhibit clear local features. The GFE module is capable of extracting global features from both the height and width dimensions of images and integrating them into three-dimensional features. This enhancement improves the network’s ability to capture global features, thereby facilitating the inference of regions with indistinct local features. Secondly, we propose the Multi-scale Feature Fusion (MFF) module. This module expands the feature map into various scales, further enlarging the network’s receptive field and enhancing perception of features at multiple scales. In addition, we tested the proposed network on the EndoVis 2018 and a human minimally invasive liver resection image segmentation dataset, comparing it against six other advanced image segmentation networks. The comparative test results demonstrate that the proposed network achieves the most advanced performance on both datasets, proving its potential in improving surgical image segmentation outcome. The codes of MAMNet are available at: https://***/Pang1234567/MAMNet .

关键词： Laparoscopic surgery image Medical image segmentation Convolutional neural networks Attention mechanism Feature fusion

来源：评论

学校读者我要写书评

暂无评论

An Underwater Image Bubble Noise Removal Method Based on Optical Flow

引用

Journal of harbin institute of technology(New Series) 2019年第1期26卷 11-16页

作者： Hao Li Jianguo Tao Yang Luo Liping Deng Zongquan Deng State Key Laboratory of Robotics and System Harbin Institute of Technology

It is very important for underwater robots to accurately detect and locate target objects. However,under many circumstances,it is difficult to clearly observe the target object due to the existence of bubble noise. In this paper,we proposed a method to solve this problem. First,we used the LK optical flow algorithm to calculate the motion vector of the image background and compensate for the background ***,the optical flow field of the bubbles was calculated by the HS optical flow algorithm,and the area where the bubble existed was obtained by binarizing the image. Finally,we used the adjacent frame image to repair the bubble area. We carried out a bubble noise removal experiment. The results show that this method can effectively remove the bubble noise in the image.

关键词： bubble noise optical flow background motion image repair

来源：评论

学校读者我要写书评

暂无评论

Perception and Electrophysiological Properties of Calf under Electrotactile Stimulation

Perception and Electrophysiological Properties of Calf under...

引用

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Ning Wang Xiaoxin Wang Ziliang Zhou Yixuan Sheng Honghai Liu Hongwei Zhang School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Guangdong P. R. China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai P. R. China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

This paper studies electrotactile perceptual characteristics in the lower extremities. We measured the detection threshold (DT) and pain threshold (PT) based on the human calf and established a voltage response model. Via conducting two experiments, we explored the subjective perceptual characteristics of the calf through DT and PT and established a mathematical model describing the voltage response. Besides, accurate voltage model based on different subjects have been proposed. Finally, we compared the model differences among different regions of the calf. The results show that four distinct regions of the calf exhibit similar voltage response characteristics under electrotactile stimulation. This work is expected to provide new theoretical support for selection of regions for electrotactile feedback on the calf and precise control of calf electrotactile perception.

关键词： Analytical models Voltage measurement Accuracy Sensitivity Pain Electrical stimulation Mathematical models Threshold voltage Skin Robots

来源：评论

学校读者我要写书评

暂无评论

Improving Kinematic Flexibility and Walking Performance of a Six-legged Robot by Rationally Designing Leg Morphology

引用

Journal of Bionic Engineering 2019年第4期16卷 608-620页

作者： Jie Chen Zhongchao Liang Yanhe Zhu Jie Zhao School of Mechanical Engineering and Automation Northeastern UniversityShenyang 110819China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

This paper explores the design of leg morphology in a six-legged *** by nature,where animals have different leg morphology,we examined how the difference in leg morphology influences behaviors of the *** this end,a systematic search was conducted by scanning over the parameter space consisting of default angles of leg joints of the six-legged robot,with two main objectives:to maximize the kinematic flexibility and walking performance of the *** show that(1)to have a high kinematic flexibility with both the torso and swing legs,the femur segment should tilt downwards by 5°-10°and the tibia segment should be vertically downwards or with a slight inward tilt;(2)to achieve relatively energy-efficient and steady walking,the tibia segment should be approximately vertically downwards,with the femur segment tilting upwards to lower the torso *** results of this study suggest that behaviors of legged robots can be passively enhanced by careful mechanical design choices,thereby leading to more competent legged machines.

关键词： six-legged robot leg morphology kinematic flexibility walking performance

来源：评论

学校读者我要写书评

暂无评论

Surface accuracy analysis for hexagonal prism modular deployable antenna

引用

Guangxue Jingmi Gongcheng/Optics and Precision Engineering 2021年第12期29卷 2855-2867页

作者： Tian, Da-Ke Fan, Xiao-Dong Jin, Lu Liu, Rong-Qiang Zhang, Ke School of Mechanical Engineering Shenyang Jianzhu University Shenyang110168 China School of Civil Engineering Shenyang Jianzhu University Shenyang110168 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

A surface accuracy analysis model for the support structure of a hexagonal prism modular deployable antenna is proposed because of the large-scale, modular, and high-precision development trend of deployable antennas. The structural composition of the hexagonal modular deployable antenna is elaborated, and the topological rules of the hexagonal modular structure are analyzed. Based on the idea of equal envelope circles and the basic theory of robotics, two mathematical modeling methods of envelope circle, point-surface method and two-point method, are proposed, from which the mathematical model of the intersection point of the equal envelope circle and the mathematical model of the included angle of rib unit are established;the mathematical model for accuracy analysis of the shape surface of the support structure of a modular deployable antenna with a hexagonal prism is built. Finally, the model is verified using a combination of numerical simulations and experimental verifications. The simulation and experimental results show that the enveloping circle can closely fit on the spherical surface, and it is in good agreement with the spherical surface. In the numerical simulation model, the modules of the hexagonal prism are connected accurately. In the experiment, the absolute error of feature points is mainly distributed in 5 to 10 mm, the relative error is mainly concentrated in the range of 0.05% to 0.1%, and the absolute error of the rib unit angle is mostly distributed in the range of 0.05°to 0.1°. The deviation between the measured and the theoretical values is small, and the values are in good agreement. The proposed model can solve the spatial coordinates of all module connection points, which provides a theoretical basis for the analysis and research of the shape accuracy of multi-module deployable antennas. © 2021, Science Press. All right reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Generalized Multi-kernel Maximum Correntropy Kalman Filter for Disturbance Estimation

arXiv

引用

arXiv 2023年

作者： Li, Shilei Shi, Dawei Lou, Yunjiang Zou, Wulin Shi, Ling The Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong The School of Automation Beijing Institute of Technology China The State Key Laboratory of Robotics and System School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen518055 China Xeno Dynamics Control Department Xeno Dynamics Co. Ltd Shenzhen518055 China

Disturbance observers have been attracting continuing research efforts and are widely used in many applications. Among them, the Kalman filter-based disturbance observer is an attractive one since it estimates both the state and the disturbance simultaneously, and is optimal for a linear system with Gaussian noises. Unfortunately, The noise in the disturbance channel typically exhibits a heavy-tailed distribution because the nominal disturbance dynamics usually do not align with the practical ones. To handle this issue, we propose a generalized multi-kernel maximum correntropy Kalman filter for disturbance estimation, which is less conservative by adopting different kernel bandwidths for different channels and exhibits excellent performance both with and without external disturbance. The convergence of the fixed point iteration and the complexity of the proposed algorithm are given. Simulations on a robotic manipulator reveal that the proposed algorithm is very efficient in disturbance estimation with moderate algorithm complexity. Copyright © 2023, The Authors. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Construction of a metastasis model for liver cancer spheroids to hepatobiliary organoids facilitated by holographic acoustic tweezers

引用

Cell Reports Physical Science 2025年第6期6卷

作者： Li, Jialong Liu, Dingyuan Gao, Zeping Sun, Mengting Wang, Shuo Zhang, Lihong Yang, Ye Wang, Hongyu Zheng, Hairong Tian, Ye Ma, Teng Department of Pathophysiology and Key Laboratory of Cardiovascular Pathophysiology Harbin Medical University Harbin 150086 China Institute of Scientific Instrumentation Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 China Key Laboratory of Cardiovascular Medicine Research (Harbin Medical University) Ministry of Education Harbin 150086 China Department of Cardiology the First Affiliated Hospital Cardiovascular Institute Harbin Medical University Harbin 150001 China State Key Laboratory of Biomedical Imaging Science and System Shenzhen 518055 China National Innovation Center for Advanced Medical Devices Shenzhen 518126 China

Constructing an in vitro model that can faithfully recapitulate cancer metastasis to surrounding tissues remains an urgent need and a significant challenge. Here, we develop holographic acoustic tweezers and create a personalized composite acoustic field for liver cancer spheroids, enabling accurate movement under the influence of acoustic radiation force. We also assess the biosafety of three-dimensional holographic acoustic fields on organoids and spheroids at the cellular and genetic levels, optimizing the parameters for manipulation. Additionally, we develop an organoid-spheroid online assembly platform based on holographic acoustic tweezers and three-dimensional cell culture technology and use this platform to construct a reliable liver cancer metastasis model with hepatobiliary organoids and liver cancer spheroids. Furthermore, we demonstrate the versatility of our model by studying the infiltration of liver cancer spheroids into normal and ethanol-treated hepatobiliary organoids. Our findings present a valuable platform for cancer metastasis research. © 2025 The Author(s)

关键词： acoustic radiation force assembloids hepatobiliary organoids holographic acoustic tweezers liver cancer metastasis liver cancer spheroids

来源：评论

学校读者我要写书评

暂无评论

Design, Analysis, and Experiment of a Coupled-Adaptive Underactuated Prosthetic Handbased on Linkage Mechanisms

SSRN

引用

SSRN 2022年

作者： Fan, Shaowei Dai, Jinghui Zhang, Ning Zhang, Ting Cheng, Ming Liu, Bingchen Jiang, Li State Key Laboratory of Robotics and System Harbin Institute of Technology Heilongjiang Harbin150080 China National Research Center for Rehabilitation Technical Aids Beijing100176 China College of Mechanical and Electrical Engineering Soochow University Jiangsu Suzhou215021 China

To reproduce the characteristics of human hand motion, this paper proposes a novel four-degree-of-freedom prosthetic hand that combines the advantages of coupled motion and self-adaptive motion. A coupled-adaptive underactuated finger was developed using a cross-coupled four-link mechanism and an adaptive five-link mechanism. The finger can perform both power and precision grasping excellently. Based on the seesaw mechanism, a differential mechanism among the middle finger, ring finger, and little finger was developed to further reduce the size and weight of the prosthetic hand. To avoid the ejection phenomenon, the stability of the finger is systematically analyzed in this paper using the grasp-state space analysis technique. The stability analysis results indicate that ejection does not occur in the entire workspace of the proposed finger. The grasping experiments indicate that the proposed prosthetic hand possesses excellent stability and adaptability. © 2022, The Authors. All rights reserved.

关键词： Prosthetics

来源：评论

学校读者我要写书评

暂无评论

Privileged Anatomical and Protocol Discrimination in Trackerless 3D Ultrasound Reconstruction

arXiv

引用

arXiv 2023年

作者： Li, Qi Shen, Ziyi Li, Qian Barratt, Dean C. Dowrick, Thomas Clarkson, Matthew J. Vercauteren, Tom Hu, Yipeng Centre for Medical Image Computing Wellcome/EPSRC Centre for Interventional and Surgical Sciences Department of Medical Physics and Biomedical Engineering University College London London United Kingdom State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China School of Biomedical Engineering & Imaging Sciences King’s College London London United Kingdom

Three-dimensional (3D) freehand ultrasound (US) reconstruction without using any additional external tracking device has seen recent advances with deep neural networks (DNNs). In this paper, we first investigated two identified contributing factors of the learned inter-frame correlation that enable the DNN-based reconstruction: anatomy and protocol. We propose to incorporate the ability to represent these two factors - readily available during training - as the privileged information to improve existing DNN-based methods. This is implemented in a new multitask method, where the anatomical and protocol discrimination are used as auxiliary tasks. We further develop a differentiable network architecture to optimise the branching location of these auxiliary tasks, which controls the ratio between shared and task-specific network parameters, for maximising the benefits from the two auxiliary tasks. Experimental results, on a dataset with 38 forearms of 19 volunteers acquired with 6 different scanning protocols, show that 1) both anatomical and protocol variances are enabling factors for DNN-based US reconstruction;2) learning how to discriminate different subjects (anatomical variance) and predefined types of scanning paths (protocol variance) both significantly improve frame prediction accuracy, volume reconstruction overlap, accumulated tracking error and final drift, using the proposed algorithm. © 2023, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Video Flame Recognition Based on Feature Fusion and Extreme Learning Machine 5

Video Flame Recognition Based on Feature Fusion and Extreme ...

引用

5th International Conference on Automation, Control and robotics Engineering, CACRE 2020

作者： Zhong, Chen Tian, Zhijia Ding, Hongjun Wang, Ke Research Institute of Mem Shenyang Fire Science and Technology Shenyang China Harbin Institute of Technology State Key Laboratory of Robotics and Systems Harbin China

ISBN: (纸本)9781728198880

This paper proposes a video flame detection method based on Extreme Learning Machine (ELM). Visual Background Extractor++(ViBE++) algorithm is used to extract the dynamic foreground features of flame video images, and combined with color histogram threshold analysis, the flame region in the image is segmented. By extracting and processing the flame geometrical features such as roundness, sharpness and gravity center, the dynamic and static features of flame image are fused, thus the suspected flame area is screened out. Using the geometric features of suspected flame area and based on ELM model, the training and classification of sample sets are performed. Experimental results show that this method has higher operating speed and accuracy under the condition of less environmental interference. © 2020 IEEE.

关键词： Knowledge acquisition

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：