检索结果-内蒙古大学图书馆

IEEE International Symposium on Biomedical Imaging

作者： Sandhitsu R. Das Dawn Mechanic-Hamilton Marc Korczykowski Brian B. Avants John A. Detre James C. Gee Paul A. Yushkevich Penn Image Computing and Science Laboratory Department of Radiology University of Pennsylvania Philadelphia PA USA Center for Functional Neuroimaging Department of Neurology University of Pennsylvania Philadelphia PA USA

Asymmetry analysis of brain activation in functional magnetic resonance imaging (fMRI) experiments is commonly used to determine hemispheric specialization for cognitive function. Asymmetry is typically expressed in terms of differences in the number of suprathreshold voxels activated, normalized to total activation, within specific regions known to subserve the function of interest or over the entire hemisphere. We introduce methodologies for carrying out asymmetry analysis both for region of interest (ROI) and whole brain based studies that take into account information about spatial correspondence of voxels on two sides of the brain. We apply this methodology to make determination of activation asymmetry during a memory encoding task in patients with refractory temporal lobe epilepsy (TLE). Memory lateralization is an important step in the presurgical evaluation of such patients for temporal lobectomy. Using structure specific analysis, our asymmetry scores in hippocampus are found to have a strong correspondence with hemispheric dominance given by Intracortical Amobarbital Testing (IAT), which is the widely accepted gold standard for determining laterality. Whole brain analysis, on the other hand, is used to locate regions in the brain with asymmetric activation in an exploratory analysis. These methods of quantifying asymmetry using spatial correspondence have the potential for generating more robust asymmetry measurements.

关键词： Magnetic analysis image analysis Magnetic resonance imaging Information analysis Encoding Temporal lobe Epilepsy Hippocampus Testing Gold

来源：评论

学校读者我要写书评

暂无评论

Neural Ordinary Differential Equation based Sequential image Registration for Dynamic Characterization

arXiv

引用

arXiv 2024年

作者： Wu, Yifan Dong, Mengjin Jena, Rohit Qin, Chen Gee, James C. Penn Image Computing and Science Laboratory University of Pennsylvania PhiladelphiaPA19104 United States Department of Electrical and Electronic Engineering and I-X Imperial College London United Kingdom

Deformable image registration (DIR) is crucial in medical image analysis, enabling the exploration of biological dynamics such as organ motions and longitudinal changes in imaging. Leveraging Neural Ordinary Differential Equations (ODE) for registration, this extension work discusses how this framework can aid in the characterization of sequential biological processes. Utilizing the Neural ODE’s ability to model state derivatives with neural networks, our Neural Ordinary Differential Equation Optimization-based (NODEO) framework considers voxels as particles within a dynamic system, defining deformation fields through the integration of neural differential equations. This method learns dynamics directly from data, bypassing the need for physical priors, making it exceptionally suitable for medical scenarios where such priors are unavailable or inapplicable. Consequently, the framework can discern underlying dynamics and use sequence data to regularize the transformation trajectory. We evaluated our framework on two clinical datasets: one for cardiac motion tracking and another for longitudinal brain MRI analysis. Demonstrating its efficacy in both 2D and 3D imaging scenarios, our framework offers flexibility and model agnosticism, capable of managing image sequences and facilitating label propagation throughout these sequences. This study provides a comprehensive understanding of how the Neural ODE-based framework uniquely benefits the image registration challenge. Copyright © 2024, The Authors. All rights reserved.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Enhanced generative adversarial network for 3D brain MRI super-resolution

Enhanced generative adversarial network for 3D brain MRI sup...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Jiancong Wang Yuhua Chen Yifan Wu Jianbo Shi James Gee Penn Image Computing and Science Laboratory University of Pennsylvania Philadelphia PA USA Department of Bioengineering University of California Los Angeles CA USA Department of Computer and Information Science University of Pennsylvania Philadelphia PA USA

ISBN: (数字)9781728165530

ISBN: (纸本)9781728165547

Single image super-resolution (SISR) reconstruction for magnetic resonance imaging (MRI) has generated significant interest because of its potential to not only speed up imaging but to improve quantitative processing and analysis of available image data. Generative Adversarial Networks (GAN) have proven to perform well in image recovery tasks. In this work, we followed the GAN framework and developed a generator coupled with discriminator to tackle the task of 3D SISR on T1 brain MRI images. We developed a novel 3D memory-efficient residual-dense block generator (MRDG) that achieves state-of-the-art performance in terms of SSIM (Structural Similarity), PSNR (Peak Signal to Noise Ratio) and NRMSE (Normalized Root Mean Squared Error) metrics. We also designed a pyramid pooling discriminator (PPD) to recover details on different size scales simultaneously. Finally, we introduced model blending, a simple and computational efficient method to balance between image and texture quality in the final output, to the task of SISR on 3D images.

关键词： Three-dimensional displays Gallium nitride Training Generative adversarial networks Spatial resolution Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Structure-Specific Statistical Mapping of White Matter Tracts using the Continuous Medial Representation

Structure-Specific Statistical Mapping of White Matter Tract...

引用

International Conference on Computer Vision (ICCV)

作者： Paul A. Yushkevich Hui Zhang Tony J. Simon James C. Gee Penn Image Computing and Science Laboratory Department of Radiology University of Pennsylvania Philadelphia PA USA Department of Psychiatry and Behavioral Sciences M.I.N.D. Institute University of California Davis CA USA

This paper describes a new statistical analysis framework for diffusion-based white matter studies. The framework is based on a recent unbiased normalization algorithm for diffusion tensor images. Taking advantage of the fact that most human white matter tracts are thin sheet-like structures, this framework uses deformable medial models to represent six of the major tracts in a white matter atlas derived for a given set of images. The medial representation allows one to average tensor-based features along directions perpendicular to the tracts, thus reducing data dimensionality and accounting for errors in normalization. Unlike earlier work in the area of tract-based spatial statistics (Smith et al, 2006), this framework enables the analysis of individual white matter structures, and provides a range of possibilities for computing statistics and visualizing differences between cohorts. The framework is demonstrated in a study of white matter differences in pediatric chromosome 22q deletion syndrome.

关键词： Statistical analysis Skeleton Smoothing methods Solid modeling Performance analysis Tensile stress Data visualization Biological cells Anatomical structure Laboratories

来源：评论

学校读者我要写书评

暂无评论

Multivariate segmentation of brain tissues by fusion of MRI and DTI data

Multivariate segmentation of brain tissues by fusion of MRI ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Suyash P. Awate Hui Zhang Tony J. Simon James C. Gee Penn Image Computing and Science Laboratory Department of Radiology University of Pennsylvania Philadelphia PA USA Department of Psychiatry and Behavioral Sciences M.I.N.D. Institute University of California Sacramento CA USA

This paper proposes a method to improve brain-tissue segmentation, especially in subcortical region, by fusing the information in structural magnetic resonance (MR) images and diffusion tensor (DT) images in a sound statistical framework. The proposed method incorporates the information in DT images by parameterizing the space of diffusion tensors, in a principled and efficient manner, based on a set of independent orthogonal invariants. The proposed method couples the Markov tissue statistics of the structural-MR intensities with the tissue statistics of the DT invariants to define multivarite/joint probability density functions (PDFs) that differentiate brain tissues. The paper shows that while the information in DT images can allow improved differentiation between tissues in the subcortical region, which comprises anatomical structures having smooth (blob-like) shapes, it can produce unreliable results in the cortical regions that depict convoluted sulci/gyri. The proposed method exploits these characteristics of the images by introducing an appropriate anisotropic distance metric in the multivariate feature space.

关键词： Magnetic resonance imaging Diffusion tensor imaging image segmentation Tensile stress Statistics Magnetic resonance Joints Probability density function Anatomical structure Shape

来源：评论

学校读者我要写书评

暂无评论

FireANTs: Adaptive Riemannian Optimization for Multi-Scale Diffeomorphic Matching

arXiv

引用

arXiv 2024年

作者： Jena, Rohit Chaudhari, Pratik Gee, James C. Computer and Information Science University of Pennsylvania United States Electrical and Systems Engineering University of Pennsylvania United States Radiology Perelman School of Medicine University of Pennsylvania United States Penn Image Computing and Science Laboratory University of Pennsylvania United States

The paper proposes FireANTs, the first multi-scale Adaptive Riemannian Optimization algorithm for dense diffeomorphic image matching. One of the most critical and understudied aspects of diffeomorphic image matching algorithms are its highly ill-conditioned nature. We quantitatively capture the extent of ill-conditioning in a typical MRI matching task, motivating the need for an adaptive optimization algorithm for diffeomorphic matching. To this end, FireANTs generalizes the concept of momentum and adaptive estimates of the Hessian to mitigate this ill-conditioning in the non-Euclidean space of diffeomorphisms. Unlike common non-Euclidean manifolds, we also formalize considerations for multi-scale optimization of diffeomorphisms. Our rigorous mathematical results and operational contributions lead to a state-of-the-art dense matching algorithm that can be applied to generic image data with remarkable accuracy and robustness. We demonstrate consistent improvements in image matching performance across a spectrum of community-standard medical and biological correspondence matching challenges spanning a wide variety of image modalities, anatomies, resolutions, acquisition protocols, and preprocessing pipelines. This improvement is supplemented by from 300× up to 3200× speedup over existing state-of-the-art algorithms. For the first time, we perform diffeomorphic matching of sub-micron mouse cortex volumes at native resolution. Our fast implementation also enables hyperparameter studies that were intractable with existing correspondence matching algorithms. © 2024, CC BY.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Enhanced generative adversarial network for 3D brain MRI super-resolution

arXiv

引用

arXiv 2019年

作者： Wang, Jiancong Chen, Yuhua Wu, Yifan Shi, Jianbo Gee, James Penn Image Computing and Science Laboratory University of Pennsylvania PhiladelphiaPA19104 United States Department of Bioengineering University of California Los AngelesCA90095 United States Department of Computer and Information Science University of Pennsylvania PhiladelphiaPA19104 United States

Single image super-resolution (SISR) reconstruction for magnetic resonance imaging (MRI) has generated significant interest because of its potential to not only speed up imaging but to improve quantitative processing and analysis of available image data. Generative Adversarial Networks (GAN) have proven to perform well in recovering image texture detail, and many variants have therefore been proposed for SISR. In this work, we develop an enhancement to tackle GAN-based 3D SISR by introducing a new residual-in-residual dense block (RRDG) generator that is both memory efficient and achieves state-of-the-art performance in terms of PSNR (Peak Signal to Noise Ratio), SSIM (Structural Similarity) and NRMSE (Normalized Root Mean Squared Error) metrics. We also introduce a patch GAN discriminator with improved convergence behavior to better model brain image texture. We proposed a novel the anatomical fidelity evaluation of the results using a pre-trained brain parcellation network. Finally, these developments are combined through a simple and efficient method to balance between image and texture quality in the final output. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Robust regularization for the estimation of intra-voxel axon fiber orientations

Robust regularization for the estimation of intra-voxel axon...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Alonso Ramirez-Manzanares Hui Zhang Mariano Rivera James C. Gee Department of Radiology Penn Image Computing and Science Laboratory University of Pennsylvania Philadelphia PA USA Facultad de Matematicas Universidad de Guanajuato Philadelphia Guanajuato Mexico Centro de Investigacion en Matematicas A.C. Guanajuato Mexico

Diffusion weighted magnetic resonance images allows one to infer white matter axon fiber orientations. Nowadays it is possible to estimate intra-voxel orientations at voxels where fibers cross or split. Though, the recovered orientations could be prone to error because of low signal to noise ratio, the complex fiber structure and/or reduced number of measurements. Spatial regularization can improve the estimations but it must be done carefully such that real information is not removed and false orientations are not introduced. In this work we propose a robust method for regularizing local multi-fiber estimations given by the Diffusion Basis Function method. Our method is based on a robust outlier rejection framework which integrates data while preserves important local information. Additionally, our method constrains the solution orientation-space within a voxel by using the diffusion tensor diffusivity profile as prior information. Our experiments using both in vivo and realistic synthetic data demonstrate the advantage of using the proposed approach.

关键词： Nerve fibers Signal to noise ratio Magnetic resonance imaging Tensile stress Laboratories Radiology Magnetic resonance Noise measurement Noise robustness In vivo

来源：评论

学校读者我要写书评

暂无评论

Surface-based modeling of white matter fasciculi with orientation encoding

Surface-based modeling of white matter fasciculi with orient...

引用

IEEE International Symposium on Biomedical Imaging

作者： Hui Zhang Paul A. Yushkevich Tony J Simon James C. Gee Penn Image Computing and Science Laboratory (PICSL) Department of Radiology University of Pennsylvania Philadelphia PA USA Department of Psychiatry and Behavioral Sciences M.I.N.D. Institute University of California슠Davis Sacramento CA USA

ISBN: (纸本)9781424420025

In this paper, we describe a novel technique for modeling sheet-like white matter (WM) fasciculi using continuous medial representation (cm-rep). In the cm-rep framework, the skeleton of a fasciculus is described by a parametric surface patch. This modeling scheme is particularly appropriate for sheet-like structures, because the shapes of such objects can be effectively captured by their skeletons. We show that dimensionality reduction can be achieved without much loss of spatial specificity by projecting data along the "less interesting" thickness direction onto the skeletons. We demonstrate that local fiber orientation of the modeled fasciculi can be encoded in our framework and show how this information can be leveraged for deriving and analyzing brain connectivity patterns on the skeleton themselves.

关键词： Encoding Skeleton Solid modeling Deformable models Shape Surface fitting Topology Tensile stress image coding Laboratories

来源：评论

学校读者我要写书评

暂无评论

Robust regularizatlon for the estimation of intra-voxel axon fiber orientations

Robust regularizatlon for the estimation of intra-voxel axon...

引用

2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops

作者： Ramirez-Manzanares, Alonso Zhang, Hui Rivera, Mariano Gee, James C. Penn Image Computing and Science Laboratory Dept. of Radiology Univ. of Pennsylvania 3600 Market Street Philadelphia PA 19104 United States Centro de Investigacion en Matematicas A.C. Callejon Jalisco S/N Valenciana Guanajuato Gto. C.P. 36240 Mexico Univ. de Guanajuato Facultad de Matematicas Callejon Jalisco S/N Valenciana Guanajuato Gto. C.P. 36240 Mexico

ISBN: (纸本)9781424423408

Diffusion weighted magnetic resonance images allows one to infer white matter axon fiber orientations. Nowadays it is possible to estimate intra-voxel orientations at voxels where fibers cross or split. Though, the recovered orientations could be prone to error because of low signal to noise ratio, the complex fiber structure and/or reduced number of measurements. Spatial regularizalion can improve the estimations but it must be done carefully such that real information is not removed and false orientations are not introduced. In this work we propose a robust method for regularizing local multi-fiber estimations given by the Diffusion Basis Function method. Our method is based on a robust outlier rejection framework which integrates data while preserves important local information. Additionally, our method constrains the solution orientation-space within a voxel by using the diffusion tensor diffusivity profile as prior information. Our experiments using both in vivo and realistic synthetic data demonstrate the advantage of using the proposed approach. © 2008 IEEE.

关键词： Tensors

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：