检索结果-内蒙古大学图书馆

9th International Conference on Control, Decision and Information Technologies, CoDIT 2023

作者： Nguyen, Ngoc Thinh Gangavarapu, Pranav Tej Ernst, Floris Institute for Robotics and Cognitive Systems Luebeck Germany

ISBN: (纸本)9798350311402

In this paper, we present a new approach to calculate the B-spline-to-Bézler conversion matrix which converts the control points of a uniform B-spline curve into the control points of an equivalent Bézier curve. It takes into account the order of the curve intervals and hence can provide the conversion of the whole curve at once. The algorithm is implemented so that the computation time only increases proportionally with the number of control points until a constant value before getting saturated. Applications include but are not limited to the efficient usage in different optimal path planning algorithms for navigation in 2D non-convex polytopic region as being presented. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Feature Description using Autoencoders for Fast 3D Ultrasound Tracking

Feature Description using Autoencoders for Fast 3D Ultrasoun...

引用

作者： Wulff, Daniel Ernst, Floris Institute for Robotics and Cognitive Systems Ratzeburger Allee 160 Lubeck Germany

3D ultrasound imaging is a promising modality for therapy guidance, e.g. in radiation therapy. It is able to provide volumetric soft tissue images in real-Time. However, due to low image quality, high noise ratio and high data dimensionality, real-Time capable US image processing methods like target tracking are challenging. In this study, a feature-based tracking approach is investigated. The FAST feature detector is used to detect local image features in 3D ultrasound images. Two different feature descriptors are tested and evaluated in terms of target tracking: The BRIEF descriptor as well as a slicedwasserstein autoencoder. On the basis of a feature matching algorithm, tracking experiments are executed and evaluated using eight labeled 3D US sequences. The mean tracking error measured is 2.08±1.50mm and 2.29±1.59mm using the autoencoder and the BRIEF descriptor, respectively. The results indicate that using an autoencoder for feature description improves the tracking performance compared to a binary descriptor. The proposed tracking method could be executed in fast runtimes of 137 ms and 256 ms per image on average making it real-Time capable. © 2024 by Walter de Gruyter Berlin/Boston.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Target Tracking in 4D Ultrasound using Localization Networks

Target Tracking in 4D Ultrasound using Localization Networks

引用

作者： Krause, Cassandra Wulff, Daniel Ernst, Floris Institute for Robotics and Cognitive Systems Ratzeburger Allee 160 Lubeck Germany

In radiation therapy, breathing and other influences cause a constant movement of the tissue to be irradiated. Thus, a continuous position control is required which could be handled by the usage of 3D ultrasound imaging. For this purpose, two approaches for target tracking in 3D ultrasound (US) sequences of the liver are analyzed in this study. Therefore, an image-by-image localization of the target is performed using a deep localization network. A singletarget and a multiple-target approach are investigated where deep localization networks are trained for locating one specific and multiple specific targets, respectively. Training the networks and evaluating the tracking algorithm is performed on the basis of a labeled 3D US liver data set in 2-fold crossvalidation experiments. The single-target and multiple-target approaches performed comparable with a mean tracking error of 2.28±1.20mm and 2.23±1.28 mm, respectively. The proposed tracking algorithm is real-time capable with a mean runtime per 3D ultrasound image of 68ms. © 2024 by Walter de Gruyter Berlin/Boston.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Real-time MR-based 3D motion monitoring using raw k-space data 7

Real-time MR-based 3D motion monitoring using raw k-space da...

引用

7th International Conference on Medical Imaging with Deep Learning, MIDL 2024

作者： Krusen, Marius Ernst, Floris Institute for Robotics and Cognitive Systems University of Lübeck Lübeck Germany

Due to its great soft-tissue contrast and non-invasive nature, magnetic resonance imaging (MRI) is uniquely qualified for motion monitoring during radiotherapy. However, real-time capabilities are limited by its long acquisition times, particularly in 3D, and require highly undersampling k-space resulting in lower image resolution and image artifacts. In this paper, we propose a simple recurrent neural network (RNN) architecture to continually estimate target motion from single k-space spokes. By directly using the incoming k-space data, additional image reconstruction steps are avoided and less data is required between estimations achieving a latency of only a few milliseconds. The 4D XCAT phantom was used to generate realistic data of the abdomen affected by respiratory and cardiac motion and a simulated lesion inserted into the liver acted as the target. We show that using a Kooshball trajectory to sample 3D k-space gives superior results compared to a stack-of-stars (SoS) trajectory. The RNN quickly learns the motion pattern and can give new motion estimations at a frequency of more than 230 Hz, demonstrating the feasibility of drastically improving latency of MR-based motion monitoring systems. © 2024 CC-BY 4.0, M. Krusen & F. Ernst.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Nullspace Control for Automatic Ultrasound Gel Supply

Nullspace Control for Automatic Ultrasound Gel Supply

引用

作者： Osburg, Jonas Ernst, Floris Institute for Robotics and Cognitive Systems Ratzeburger Allee 160 Lübeck Germany

Ultrasound gel is used as a coupling medium in ultrasound procedures, thereby ensuring the entry of sound waves into the body of the patient and providing ultrasound images of high quality. In this paper, we present an approach to automatically supply ultrasound gel during robot guided ultrasound examinations. For this purpose, we combine a simple mechanical design consisting of a gel tube and a push mechanism with a specialized control strategy exploiting the robotic nullspace of 7 DoF redundant manipulator. Functionality is demonstrated by robotic ultrasound scans on phantoms, with gel being automatically applied when needed. © 2024 by Walter de Gruyter Berlin/Boston.

关键词： Redundant manipulators

来源：评论

学校读者我要写书评

暂无评论

Generalized Automatic Probe Alignment based on 3D Ultrasound

引用

Current Directions in Biomedical Engineering 2022年第1期8卷 58-61页

作者： Osburg, Jonas Wulff, Daniel Ernst, Floris Institute for Robotics and Cognitive Systems Ratzeburger Allee 160 Lubeck Germany

Acquiring reproducible ultrasound images of high quality is challenging in ultrasound imaging. While physicians can rely on their experience, robot-assisted systems must be able to automatically align the ultrasound probe with the correct orientation. This paper describes a method to align the central axis of the probe to the surface normal at the point of contact. This is done by analyzing the area of ultrasound volumes directly below the transducer of the probe. A convolutional neural network is trained to estimate the inclination of the probe orientation towards the direction of the surface normal. Experiments on two different phantoms indicate that the mean absolute angle error between the estimated rotation and the ground truth surface normal are 5.0 ± 2.8. The method is able to keep the probe-surface contact continuous and the results indicate that the method is invariant to anatomical structures. © 2022 by Walter de Gruyter Berlin/Boston.

关键词： Probes

来源：评论

学校读者我要写书评

暂无评论

Landmark-Based Generation of Common Ultrasound Views and 17-Segment Model from Cardiac Computed Tomography

引用

Current Directions in Biomedical Engineering 2023年第1期9卷 61-64页

作者： Janorschke, Christian Xie, Jingyang Lu, Xinyu Schweikard, Achim Grehn, Melanie Blanck, Oliver Institute for Robotics and Cognitive Systems Universität zu Lübeck Ratzeburger Allee 160 Lübeck Germany Institute for Robotics and Cognitive Systems Universität zu Lübeck Germany Department of Radiation Oncology University Medical Center Schleswig-Holstein Kiel Germany

Complex medical therapies can require a multitude of imaging modalities and are often supervised by a team with different medical backgrounds. This necessitates the conversion of medical data between technical systems and visualizations. In the case of stereotactic arrhythmia radioablation therapy (STAR-Therapy) of the left ventricle, electroanatomical mapping, ultrasound (US) and computed tomography (CT) are the central imaging modalities that are needed for defining the target volume as well as for the examination and validation pre and post treatment. In the interest of developing a motion management system for STAR-Therapy, a way to transfer information and visualizations between these modalities and to compare data from different patients is needed. For this purpose, we present a landmark-based approach for the generation of commonly used ultrasound views and the 17-segment model from cardiac computed tomography (CCT) data. The developed tool can already be used to aid the examination process by extracting function-based views from CT datasets, comparing them to live US imaging, localize CT structures within the 17-segment model or to transfer information like motion or strain data from one modality to the other. In the future, it will be used in the development of a live or predictive management system for cardiac and respiratory motion. © 2023 the author(s), published by Walter de Gruyter Berlin/Boston.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Balanced Resonate-and-Fire Neurons 41

Balanced Resonate-and-Fire Neurons

引用

41st International Conference on Machine Learning, ICML 2024

作者： Higuchi, Saya Kairat, Sebastian Bohté, Sander M. Otte, Sebastian Adaptive AI Lab Institute of Robotics and Cognitive Systems University of Lübeck Germany Amsterdam Netherlands

The resonate-and-fire (RF) neuron, introduced over two decades ago, is a simple, efficient, yet biologically plausible spiking neuron model, which can extract frequency patterns within the time domain due to its resonating membrane dynamics. However, previous RF formulations suffer from intrinsic shortcomings that limit effective learning and prevent exploiting the principled advantage of RF neurons. Here, we introduce the balanced RF (BRF) neuron, which alleviates some of the intrinsic limitations of vanilla RF neurons and demonstrates its effectiveness within recurrent spiking neural networks (RSNNs) on various sequence learning tasks. We show that networks of BRF neurons achieve overall higher task performance, produce only a fraction of the spikes, and require significantly fewer parameters as compared to modern RSNNs. Moreover, BRF-RSNN consistently provide much faster and more stable training convergence, even when bridging many hundreds of time steps during backpropagation through time (BPTT). These results underscore that our BRF-RSNN is a strong candidate for future large-scale RSNN architectures, further lines of research in SNN methodology, and more efficient hardware implementations. Copyright 2024 by the author(s)

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Target tracking in 4D US based on template matching and target forecasting using spatio-temporal autoencoders 23

Target tracking in 4D US based on template matching and targ...

引用

23rd IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2023

作者： Wulff, Daniel Sarau, Ricardo Ernst, Floris Institute for Robotics and Cognitive Systems University of Lübeck Lübeck Germany

ISBN: (纸本)9798350393118

4D ultrasound (US) imaging is a promising imaging modality for diagnosis as well as therapy guidance. It provides volumetric images of soft-tissue structures in real-time without harming the patient with ionizing radiation. Soft tissue targets in the liver are affected by breathing-induced movements resulting in high dimensional motion patterns including deformations affecting the target appearance. Thus, using 4D US for target tracking in radiation therapy to enhance the treatment accuracy is promising but challenging. In this study, a novel approach for target tracking in 4D US is proposed based on predicting the appearance of the target for the next US frame. A spatiotemporal autoencoder as well as a recurrent neural network are implemented and trained based on a labeled 4D US data set with a mean spatial resolution of 1.0×0.7×1.5 mm3 for predicting volumetric target patches and target locations. Four template matching-based tracking algorithms are implemented and evaluated in terms of tracking accuracy. The results indicate that using predicted targets for template matching reduce the tracking error by 62 %, on average. By using a naive template matching algorithm, a mean tracking error of 7.55±12.31 mm was measured. In contrast, using predicted targets, a mean tracking error of 2.85±2.04 mm was determined. Since the proposed spatio-temporal autoencoder is independent of the tracking algorithm, it can be combined with any tracking algorithm, making it a promising approach for improving target tracking accuracy. © 2023 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Embedded Hierarchical MPC for Autonomous Navigation

引用

IEEE Transactions on robotics 2025年 41卷 3556-3574页

作者： Benders, Dennis Kohler, Johannes Niesten, Thijs Babuska, Robert Alonso-Mora, Javier Ferranti, Laura Delft University of Technology department of Cognitive Robotics CD Delft2628 Netherlands ETH Zürich Institute for Dynamic Systems and Control CH 8092 Switzerland Czech Technical University in Prague Czech Institute of Informatics Robotics and Cybernetics Czech Republic

To efficiently deploy robotic systems in society, mobile robots must move autonomously and safely through complex environments. Nonlinear model predictive control (MPC) methods provide a natural way to find a dynamically feasible trajectory through the environment without colliding with nearby obstacles. However, the limited computation power available on typical embedded robotic systems, such as quadrotors, poses a challenge to running MPC in real time, including its most expensive tasks: constraints generation and optimization. To address this problem, we propose a novel hierarchical MPC scheme that consists of a planning and a tracking layer. The planner constructs a trajectory with a long prediction horizon at a slow rate, while the tracker ensures trajectory tracking at a relatively fast rate. We prove that the proposed framework avoids collisions and is recursively feasible. Furthermore, we demonstrate its effectiveness in simulations and lab experiments with a quadrotor that needs to reach a goal position in a complex static environment. The code is efficiently implemented on the quadrotor's embedded computer to ensure real-time feasibility. Compared to a state-of-the-art single-layer MPC formulation, this allows us to increase the planning horizon by a factor of 5, which results in significantly better performance. © 2004-2012 IEEE.

关键词： Mobile robots

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：