检索结果-内蒙古大学图书馆

On Finite Difference Jacobian Computation in Deformable Image Registration

INTERNATIONAL JOURNAL OF COMPUTER VISION 2024年第9期132卷 3678-3688页

作者： Liu, Yihao Chen, Junyu wei, shuwen Carass, Aaron Prince, Jerry Johns Hopkins Univ Dept Elect & Comp Engn Baltimore MD 21218 USA Johns Hopkins Med Inst Russell H Morgan Dept Radiol & Radiol Sci Baltimore MD USA

Producing spatial transformations that are diffeomorphic is a key goal in deformable image registration. As a diffeomorphic transformation should have positive Jacobian determinant vertical bar J vertical bar everywhere, the number of pixels (2D) or voxels (3D) with vertical bar J vertical bar < 0 has been used to test for diffeomorphism and also to measure the irregularity of the transformation. For digital transformations, vertical bar J vertical bar is commonly approximated using a central difference, but this strategy can yield positive vertical bar J vertical bar's for transformations that are clearly not diffeomorphic-even at the pixel or voxel resolution level. To show this, we first investigate the geometric meaning of different finite difference approximations of vertical bar J vertical bar. We show that to determine if a deformation is diffeomorphic for digital images, the use of any individual finite difference approximation of vertical bar J vertical bar is insufficient. We further demonstrate that for a 2D transformation, four unique finite difference approximations of vertical bar J vertical bar's must be positive to ensure that the entire domain is invertible and free of folding at the pixel level. For a 3D transformation, ten unique finite differences approximations of vertical bar J vertical bar's are required to be positive. Our proposed digital diffeomorphism criteria solves several errors inherent in the central difference approximation of vertical bar J vertical bar and accurately detects non-diffeomorphic digital transformations. The source code of this work is available at https://***/yihao6/digital_diffeomorphism.

关键词： Deformable registration Non-rigid registration Digital diffeomorphism Finite difference Interpolation Jacobian determinants

来源：评论

学校读者我要写书评

暂无评论

High-resolution in vivo 4D-OCT fish-eye imaging using 3D-UNet with multi-level residue decoder

引用

BIOMEDICAL OPTICS EXPRESS 2024年第9期15卷 5533-5546页

作者： Zuo, Ruizhi wei, shuwen Wang, Yaning Irsch, Kristina Kang, Jin U. Johns Hopkins Univ Whiting Sch Engn Baltimore MD 21218 USA CNRS Vis Inst Paris France Johns Hopkins Univ Sch Med Baltimore MD USA

Optical coherence tomography (OCT) allows high-resolution volumetric imaging of biological tissues in vivo. However, 3D-image acquisition often suffers from motion artifacts due to slow frame rates and involuntary and physiological movements of living tissue. To solve these issues, we implement a real-time 4D-OCT system capable of reconstructing near-distortion-free volumetric images based on a deep learning-based reconstruction algorithm. The system initially collects undersampled volumetric images at a high speed and then upsamples the images in real-time by a convolutional neural network (CNN) that generates high-frequency features using a deep learning algorithm. We compare and analyze both dual-2D- and 3D-UNet-based networks for the OCT 3D high-resolution image reconstruction. We refine the network architecture by incorporating multi-level information to accelerate convergence and improve accuracy. The network is optimized by utilizing the 16-bit floating-point precision for network parameters to conserve GPU memory and enhance efficiency. The result shows that the refined and optimized 3D-network is capable of retrieving the tissue structure more precisely and enable real-time 4D-OCT imaging at a rate greater than 10 Hz with a root mean square error (RMSE) of similar to 0.03.

关键词： Biomedical imaging High speed imaging Imaging systems Neural networks Three dimensional imaging Tissue imaging

来源：评论

学校读者我要写书评

暂无评论

Forest Carbon Storage Accounting Model Based on Biomass Method 3rd

Forest Carbon Storage Accounting Model Based on Biomass Meth...

引用

3rd International Conference on Environmental Pollution and Governance, ICEPG 2023

作者： Lyu, Zhenhuan Wang, Jiaming wei, shuwen Feng, Xue College of Science Shenyang Agricultural University Liaoning Shenyang110866 China College of Information and Electrical Engineering Shenyang Agricultural University Liaoning Shenyang110866 China Agronomy College Shenyang Agricultural University Liaoning Shenyang110866 China

ISBN: (纸本)9783031529009

As greenhouse gas emissions keep rising, the issue of global warming has gotten much worse in recent years. As a component of the earth's ecology, forests have the ability to store carbon dioxide, which is a crucial step in lowering the amount of greenhouse gases. We simulate the carbon stocks of forests to develop an ideal method for forest carbon sequestration in order to improve the absorption and sequestration of carbon dioxide. We divide the forest, HWP, and depletion sectors of the carbon stock accounting into three categories. First, we use the IPCC volume-biomass technique as the foundational model. Then, we take into account the carbon stocks of various tree species at various ages and include them cumulatively into the model. Next, we convert the parameter for the forest area into the HWP life cycle. Last but not least, we divide them into two categories: harvesting losses and natural losses. Additionally, we present a thorough analysis of the Jilin Province regional profile and depict the distribution of forest resources. We run a sensitivity analysis on the model, and the results indicate that the model is rather sensitive to the carbon stocks in Quercus. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Towards Autonomous Retinal Microsurgery Using RGB-D Images

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第4期9卷 3807-3814页

作者： Kim, Ji Woong wei, shuwen Zhang, Peiyao Gehlbach, Peter Kang, Jin U. Iordachita, Iulian Kobilarov, Marin Johns Hopkins Univ Mech Engn Dept Baltimore MD 21218 USA Johns Hopkins Univ Elect & Comp Engn Dept Baltimore MD 21218 USA Johns Hopkins Wilmer Eye Inst Baltimore MD 21287 USA

Retinal surgery is a challenging procedure requiring precise manipulation of the fragile retinal tissue, often at the scale of tens-of-micrometers. Its difficulty has motivated the development of robotic assistance platforms to enable precise motion, and more recently, novel sensors such as microscope integrated optical coherence tomography (OCT) for RGB-D view of the surgical workspace. The combination of these devices opens new possibilities for robotic automation of tasks such as subretinal injection (SI), a procedure that involves precise needle insertion into the retina for targeted drug delivery. Motivated by this opportunity, we develop a framework for autonomous needle navigation during SI. We develop a system which enables the surgeon to specify waypoint goals in the microscope and OCT views, and the system autonomously navigates the needle to the desired subretinal space in real-time. Our system integrates OCT and microscope images with convolutional neural networks (CNNs) to automatically segment the surgical tool and retinal tissue boundaries, and model predictive control that generates optimal trajectories that respect kinematic constraints to ensure patient safety. We validate our system by demonstrating 30 successful SI trials on pig eyes. Preliminary comparisons to a human operator in robot-assisted mode highlight the enhanced safety and performance of our system.

关键词： Computer vision for medical robotics medical robots and systems vision-based navigation

来源：评论

学校读者我要写书评

暂无评论

A survey on deep learning in medical image registration: New technologies, uncertainty, evaluation metrics, and beyond

引用

MEDICAL IMAGE ANALYSIS 2025年 100卷 103385页

作者： Chen, Junyu Liu, Yihao wei, shuwen Bian, Zhangxing Subramanian, Shalini Carass, Aaron Prince, Jerry L. Du, Yong Johns Hopkins Sch Med Dept Radiol & Radiol Sci Baltimore MD 21205 USA Johns Hopkins Univ Dept Elect & Comp Engn Baltimore MD USA

Deep learning technologies have dramatically reshaped the field of medical image registration over the past decade. The initial developments, such as regression-based and U-Net-based networks, established the foundation for deep learning in image registration. Subsequent progress has been made in various aspects of deep learning-based registration, including similarity measures, deformation regularizations, network architectures, and uncertainty estimation. These advancements have not only enriched the field of image registration but have also facilitated its application in a wide range of tasks, including atlas construction, multi- atlas segmentation, motion estimation, and 2D-3D registration. In this paper, we present a comprehensive overview of the most recent advancements in deep learning-based image registration. We begin with a concise introduction to the core concepts of deep learning-based image registration. Then, we delve into innovative network architectures, loss functions specific to registration, and methods for estimating registration uncertainty. Additionally, this paper explores appropriate evaluation metrics for assessing the performance of deep learning models in registration tasks. Finally, we highlight the practical applications of these novel techniques in medical imaging and discuss the future prospects of deep learning-based image registration.

关键词： Image registration Deep neural networks Medical imaging

来源：评论

学校读者我要写书评

暂无评论

FROM REGISTRATION UNCERTAINTY TO SEGMENTATION UNCERTAINTY 21

FROM REGISTRATION UNCERTAINTY TO SEGMENTATION UNCERTAINTY

引用

21st IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Chen, Junyu Liu, Yihao wei, shuwen Bian, Zhangxing Carass, Aaron Du, Yong Johns Hopkins Univ Baltimore MD 21218 USA

ISBN: (纸本)9798350313345;9798350313338

Understanding the uncertainty inherent in deep learning-based image registration models has been an ongoing area of research. Existing methods have been developed to quantify both transformation and appearance uncertainties related to the registration process, elucidating areas where the model may exhibit ambiguity regarding the generated deformation. However, our study reveals that neither uncertainty effectively estimates the potential errors when the registration model is used for label propagation. Here, we propose a novel framework to concurrently estimate both the epistemic and aleatoric segmentation uncertainties for image registration. To this end, we implement a compact deep neural network (DNN) designed to transform the appearance discrepancy in the warping into aleatoric segmentation uncertainty by minimizing a negative log-likelihood loss function. Furthermore, we present epistemic segmentation uncertainty within the label propagation process as the entropy of the propagated labels. By introducing segmentation uncertainty along with existing methods for estimating registration uncertainty, we offer vital insights into the potential uncertainties at different stages of image registration. We validated our proposed framework using publicly available datasets, and the results prove that the segmentation uncertainties estimated with the proposed method correlate well with errors in label propagation, all while achieving superior registration performance. Code is available at https://***/42VOZER.

关键词： Image registration Registration uncertainty Segmentation uncertainty

来源：评论

学校读者我要写书评

暂无评论

Key Flow First Prioritized Flow Scheduling Strategy in Multi-Tenant Data Centers

引用

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2024年第3期21卷 3264-3277页

作者： Tao, Xudong Qian, Xiaoyan Han, Lei Fan, weibei Shi, Yuzhou Zhu, Xinrui Li, Zhiyu wei, shuwen Xu, Rui Nanjing Univ Aeronaut & Astronaut Coll Civil Aviat Nanjing 211106 Peoples R China Nanjing Univ Posts & Telecommun Sch Comp Nanjing 210023 Peoples R China Nanjing Univ Aeronaut & Astronaut Nanjing 210016 Peoples R China

The mixed flow in multi-tenant data centers presents a challenge for priority flow scheduling due to the coexistence of various requirements such as latency and throughput. To address this issue, we propose Key Flow First (KFF), a balanced scheduling algorithm suitable for mixed flows in multi-tenant data centers. Firstly, KFF categorizes flows into Latency-Sensitive Flows (LS Flow) and Throughput-Demanding Flows (TD Flow) based on the Quality of Service (QoS) of their application sources. Secondly, it further differentiates flows into Mice Flows and Elephants Flows based on the amount of already sent bytes. Thirdly, KFF employs the Multi-Level Feedback Queue (MLFQ) threshold update algorithm and a priority-based strict forwarding mechanism. By avoiding reliance on complex flow priors, KFF consistently maintains reasonable scheduling of mixed flows under different load scenarios. Experimental results demonstrate that KFF effectively reduces the real-time load on the network and achieves good performance in terms of MAX (Shortest Job First (SJF), Earliest Deadline First (EDF)) performance under diverse load conditions. Compared to PIAS, KFF reduces the FCT slow down of deadline flows by nearly 60% under high TD loads;compared to Karuma and Time Deadline Aware pFabric (TDA-pFabric), KFF reduces the flow completion time (FCT) slow down of non-deadline Mice flows by over 90% under high LS loads and meanwhile guaranteeing nearly 0 deadline miss rate.

关键词： Computer networks Data centers Scheduling algorithms Heuristic algorithms Communication system traffic Scheduling Quality of service Data center networks traffic engineering flow scheduling fair queueing

来源：评论

学校读者我要写书评

暂无评论

Correlation Ratio for Unsupervised Learning of Multi-modal Deformable Registration

Correlation Ratio for Unsupervised Learning of Multi-modal D...

引用

Medical Imaging 2025: Image Processing

作者： Chen, Xiaojian Liu, Yihao wei, shuwen Carass, Aaron Du, Yong Chen, Junyu Johns Hopkins University BaltimoreMD21218 United States Vanderbilt University NashvilleTN37235 United States

ISBN: (纸本)9781510685901

In recent years, unsupervised learning for deformable image registration has been a major research focus. This approach involves training a registration network using pairs of moving and fixed images, along with a loss function that combines an image similarity measure and deformation regularization. For multi-modal image registration tasks, the correlation ratio has been a widely-used image similarity measure historically, yet it has been underexplored in current deep learning methods. Here, we propose a differentiable correlation ratio to use as a loss function for learning-based multi-modal deformable image registration. This approach extends the traditionally non-differentiable implementation of the correlation ratio by using the Parzen windowing approximation, enabling backpropagation with deep neural networks. We validated the proposed correlation ratio on a multi-modal neuroimaging dataset. In addition, we established a Bayesian training framework to study how the trade-off between the deformation regularizer and similarity measures, including mutual information and our proposed correlation ratio, affects the registration performance. The source code is freely available at: ***/3XTJrJh. © 2025 SPIE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Stabilizing the phase of swept-source optical coherence tomography by a wrapped Gaussian mixture model

引用

OPTICS LETTERS 2021年第12期46卷 2932-2935页

作者： wei, shuwen Kang, Jin U. Johns Hopkins Univ Elect & Comp Engn 3400 North Charles St Baltimore MD 21218 USA

The phase of an optical coherence tomography (OCT) signal carries critical information about particle micro-displacements. However, swept-source OCT (SSOCT) suffers from phase instability problems due to trigger jitters from the swept source. In this Letter, a wrapped Gaussian mixture model (WGMM) is proposed to stabilize the phase of SSOCT systems. A closed-form iteration solution of the WGMM is derived using the expectation-maximization algorithm. Necessary approximations are made for real-time graphic processing unit implementation. The performance of the proposed method is demonstrated through ex vivo, in vivo, and flow phantom experiments. The results show the robustness of the method in different application scenarios. (C) 2021 Optical Society of America

关键词： Fiber Bragg gratings In vivo imaging Optical coherence tomography Phase measurement Phase unwrapping Swept sources

来源：评论

学校读者我要写书评

暂无评论

High resolution in vivo 4D-OCT fish eye imaging using deep learning

High resolution in vivo 4D-OCT fish eye imaging using deep l...

引用

Optical Coherence Tomography, OCT 2024 - Part of Optica Biophotonics Congress: Biomedical Optics

作者： Zuo, Ruizhi wei, shuwen Wang, Yaning Irsch, Kristina Kang, Jin U. Whiting School of Engineering Johns Hopkins University BaltimoreMD United States CNRS Vision Institute Paris France School of Medicine Johns Hopkins University BaltimoreMD United States

Optical coherence tomograph (OCT) volumetric imaging is slow and prone to involuntary motion. To acquire motion-free in vivo tissue images, a deep-learning based 4D-OCT system is developed with 10Hz C-scan rate and hi... 详细信息

ISBN: (纸本)9781957171340

关键词： Optical coherence tomography

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：