检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Wang, Jiancong Xie, Long Yushkevich, Paul Gee, James Penn Image Computing and Science Laboratory University of Pennsylvannia PA19104 United States

Geodesic shooting has been successfully applied to diffeomorphic registration of point sets. Exact computation of the geodesic shooting between point sets, however, requires O(N2) calculations at each time step on the number of points in the point set. We propose an approximation approach based on the Barnes-Hut algorithm to speed up point set geodesic shooting. This approximation can reduce the algorithm complexity to O(Nb+ NlogN). The evaluation of the proposed method in both simulated images and the medial temporal lobe thickness analysis demonstrates a comparable accuracy to the exact point set geodesic shooting while offering up to 3-fold speed up. This improvement opens up a range of clinical research studies and practical problems to which the method can be effectively applied. Copyright © 2019, The Authors. All rights reserved.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of the human hippocampus in 3D from histology and high-resolution ex-vivo MRI

Reconstruction of the human hippocampus in 3D from histology...

引用

IEEE International Symposium on Biomedical Imaging

作者： Daniel H. Adler Alex Yang Liu John Pluta Salmon Kadivar Sylvia Orozco Hongzhi Wang James C. Gee Brian B. Avants Paul A. Yushkevich Penn Image Computing and Science Laboratory Department of Radiology University of Pennsylvania Philadelphia PA USA

In this paper, we present methods for the reconstruction of 3D histological volumes of the human hippocampal formation from histology slices. Inter-slice alignment is guided by a graph-theoretic approach that minimizes the impact of badly distorted slices. The reconstruction is refined by iterative affine and deformable co-registration with a high-resolution MRI of the postmortem tissue sample. We present an evaluation of reconstruction accuracy that is based on measures of similarity between boundaries drawn on both histology and MRI. Our methodology is currently being applied to an MRI atlas of the human hippocampal formation, in which atlas anatomical labels are derived from segmentation of reconstructed histology.

关键词： Magnetic resonance imaging image reconstruction Hippocampus Humans Stacking Hafnium Shape

来源：评论

学校读者我要写书评

暂无评论

"Nonparametric Local Smoothing" is not image registration

引用

BMC Research Notes 2012年第1期5卷 1-5页

作者： Rohlfing, Torsten Avants, Brian Neuroscience Program SRI International Menlo Park CA 94025 333 Ravenswood Avenue United States Penn Image Computing and Science Laboratory (PICSL) Department of Radiology University of Pennsylvania School of Medicine Philadelphia PA 19104 United States

Background: image registration is one of the most important and universally useful computational tasks in biomedical image analysis. A recent article by Xing & Qiu (IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(10):2081-2092, 2011) is based on an inappropriately narrow conceptualization of the image registration problem as the task of making two images look alike, which disregards whether the established spatial correspondence is plausible. The authors propose a new algorithm, Nonparametric Local Smoothing (NLS) for image registration, but use image similarities alone as a measure of registration performance, although these measures do not relate reliably to the realism of the correspondence map. Results: Using data obtained from its authors, we show experimentally that the method proposed by Xing & Qiu is not an effective registration algorithm. While it optimizes image similarity, it does not compute accurate, interpretable transformations. Even judged by image similarity alone, the proposed method is consistently outperformed by a simple pixel permutation algorithm, which is known by design not to compute valid registrations. Conclusions: This study has demonstrated that the NLS algorithm proposed recently for image registration, and published in one of the most respected journals in computer science, is not, in fact, an effective registration method at all. Our results also emphasize the general need to apply registration evaluation criteria that are sensitive to whether correspondences are accurate and mappings between images are physically interpretable. These goals cannot be achieved by simply reporting image similarities. © 2012 Rohlfing and Avants;licensee BioMed Central Ltd.

关键词： Accuracy Correspondence image registration

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Medical image Registration: Magic or Mirage?

arXiv

引用

arXiv 2024年

作者： Jena, Rohit Sethi, Deeksha Chaudhari, Pratik Gee, James C. Computer and Information Science Electrical and Systems Engineering Radiology Penn Image Computing and Science Laboratory United States

Classical optimization and learning-based methods are the two reigning paradigms in deformable image registration. While optimization-based methods boast generalizability across modalities and robust performance, learning-based methods promise peak performance, incorporating weak supervision and amortized optimization. However, the exact conditions for either paradigm to perform well over the other are shrouded and not explicitly outlined in the existing literature. In this paper, we make an explicit correspondence between the mutual information of the distribution of per-pixel intensity and labels, and the performance of classical registration methods. This strong correlation hints to the fact that architectural designs in learning-based methods is unlikely to affect this correlation, and therefore, the performance of learning-based methods. This hypothesis is thoroughly validated with state-of-the-art classical and learning-based methods. However, learning-based methods with weak supervision can perform high-fidelity intensity and label registration, which is not possible with classical methods. Next, we show that this high-fidelity feature learning does not translate to invariance to domain shift, and learning-based methods are sensitive to such changes in the data distribution. Finally, we propose a general recipe to choose the best paradigm for a given registration problem, based on these observations. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Implicit Optimization enables Robust Learnable Features for Deformable image Registration

arXiv

引用

arXiv 2024年

作者： Jena, Rohit Chuadhari, Pratik Gee, James C. University of Pennsylvania PhiladelphiaPA19104 United States Penn Image Computing and Science Laboratory United States

Deep Learning in image Registration (DLIR) methods have been tremendously successful in image registration due to their speed and ability to incorporate weak label supervision at training time. However, existing DLIR methods forego many of the benefits and invariances of optimization methods. The lack of a task-specific inductive bias in DLIR methods leads to suboptimal performance, especially in the presence of domain shift. Our method aims to bridge this gap between statistical learning and optimization by explicitly incorporating optimization as a layer in a deep network. A deep network is trained to predict multi-scale dense feature images that are registered using a black box iterative optimization solver. This optimal warp is then used to minimize image and label alignment errors. By implicitly differentiating end-to-end through an iterative optimization solver, we explicitly exploit invariances of the correspondence matching problem induced by the optimization, while learning registration and label-aware features, and guaranteeing the warp functions to be a local minima of the registration objective in the feature space. Our framework shows excellent performance on in-domain datasets, and is agnostic to domain shift such as anisotropy and varying intensity profiles. For the first time, our method allows switching between arbitrary transformation representations (free-form to diffeomorphic) at test time with zero retraining. End-to-end feature learning also facilitates interpretability of features and arbitrary test-time regularization, which is not possible with existing DLIR methods. Copyright © 2024, The Authors. All rights reserved.

关键词： image registration

来源：评论

学校读者我要写书评

暂无评论

Novel data-driven subtypes and stages of brain atrophy in the ALS-FTD spectrum

引用

Translational Neurodegeneration 2023年第1期12卷 50-69页

作者： Ting Shen Jacob W.Vogel Jeffrey Duda Jeffrey S.Phillips Philip ACook James Gee Lauren Elman Colin Quinn Defne A.Amado Michael Baer Lauren Massimo Murray Grossman David J.Irwin Corey T.McMillan Penn Frontotemporal Degeneration Center Department of NeurologyPerelman School of MedicineUniversity of PennsylvaniaPhiladelphiaPA 19104USA Department of Clinical Sciences SciLifeLabLund University22242 LundSweden Penn Image Computing and Science Lab(PICSL) Department of RadiologyPerelman School of MedicineUniversity of Penn-sylvaniaPhiladelphiaPA 19104USA Department of Neurology Perelman School of MedicineUniversity of PennsylvaniaPhiladelphiaPA 19104USA Digital Neuropathology Laboratory Department of NeurologyPerelman School of MedicineUniversity of PennsylvaniaPhiladelphiaPA 19104USA.

Background TDP-43 proteinopathies represent a spectrum of neurological disorders,anchored clinically on either end by amyotrophic lateral sclerosis(ALS)and frontotemporal degeneration(FTD).The ALS-FTD spectrum exhibits a diverse range of clinical presentations with overlapping phenotypes,highlighting its *** study was aimed to use disease progression modeling to identify novel data-driven spatial and temporal subtypes of brain atrophy and its progression in the ALS-FTD *** We used a data-driven procedure to identify 13 anatomic clusters of brain volume for 57 behavioral variant FTD(bvFTD;with either autopsy-confirmed TDP-43 or TDP-43 proteinopathy-associated genetic variants),103 ALS,and 47 ALS-FTD patients with likely TDP-43.A Subtype and Stage Inference(SuStaIn)model was trained to identify subtypes of individuals along the ALS-FTD spectrum with distinct brain atrophy patterns,and we related subtypes and stages to clinical,genetic,and neuropathological features of *** SuStaIn identified three novel subtypes:two disease subtypes with predominant brain atrophy in either prefrontal/somatomotor regions or limbic-related regions,and a normal-appearing group without obvious brain *** limbic-predominant subtype tended to present with more impaired cognition,higher frequencies of pathogenic variants in TBK1 and TARDBP genes,and a higher proportion of TDP-43 types B,E and *** contrast,the prefrontal/somatomotor-predominant subtype had higher frequencies of pathogenic variants in C9orf72 and GRN genes and higher proportion of TDP-43 type *** normal-appearing brain group showed higher frequency of ALS relative to ALS-FTD and bvFTD patients,higher cognitive capacity,higher proportion of lower motor neuron onset,milder motor symptoms,and lower frequencies of genetic pathogenic *** overall SuStaIn stages also correlated with evidence for clinical progression including longer disease duration,higher King’s stage,and cog

关键词： Amyotrophic lateral sclerosis Frontotemporal degeneration Disease heterogeneity SuStaIn model

来源：评论

学校读者我要写书评

暂无评论

NON-UNIFORM SMOOTHING IN HIPPOCAMPUS-SPECIFIC GROUP FMRI ANALYSIS

NON-UNIFORM SMOOTHING IN HIPPOCAMPUS-SPECIFIC GROUP FMRI ANA...

引用

IEEE International Symposium on Biomedical Imaging

作者： Paul A. Yushkevich John A. Detre James C. Gee Department of Radiology Penn Image Computing and Science Laboratory USA Center for Functional Neuroimaging Departments of Neurology and Radiology University of Pennsylvania Philadelphia PA USA

ISBN: (纸本)9781424406715;1424406714

A framework for generating group-level statistical maps of functional activation in the hippocampus is presented. It aims to maximize the sensitivity and specificity of hippocampal maps by using a deformable model to normalize the hippocampus across subjects and by using a non-uniform smoothing strategy to reduce the confounding effects of extrahippocampal activation. Results of applying this framework with different smoothing parameters are presented in the context of a visual scene encoding study. The significance reported by the method in the hippocampus at low levels of smoothing is greater than when whole-brain analysis is used, while at higher levels of smoothing, whole-brain analysis detects clusters of equally high significance around the hippocampus, but not directly in the hippocampus.

关键词： Smoothing methods Hippocampus Deformable models Magnetic resonance imaging Testing Radiology Solid modeling Kernel image segmentation image analysis

来源：评论

学校读者我要写书评

暂无评论

Multivariate analysis of thalamo-cortical connectivity loss in TBI

Multivariate analysis of thalamo-cortical connectivity loss ...

引用

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

作者： Jeffrey Duda Brian Avants Junghoon Kim Hui Zhang Sunil Patel John Whyte James Gee Penn Image Computing and Science Laboratory University of Pennsylvania USA Junghoon Kim Albert Einstein Healthcare Network Moss Rehabilitation Research Institute USA

Diffusion tensor (DT) images quantify connectivity patterns in the brain while the T1 modality provides high-resolution images of tissue interfaces. Our objective is to use both modalities to build subject-specific, quantitative models of fiber connections in order to discover effects specific to a neural system. The health of this thalamo-cortical network is compromised by traumatic brain injury, and we hypothesize that these effects are due to a primary injury to the thalamus which results in subsequent compromise of radiating fibers. We first use a population-specific average T1 and DT template to label the thalamus and Brodmann areas (BA) 9,10 and 11 in each subject. We also build an expected connection model within this template space that is transferred to subject space in order to provide a prior restriction on probabilistic tracking performed in subject space. We evaluate the effect of traumatic brain injury on this prefrontal-thalamus network by quantifying, in 10 subjects and 8 controls, the mean diffusion and fractional anisotropy along fiber tracts, along with the mean diffusion within the thalamus and cortical regions. We contrast results gained by a template-based tract definition with those gained by performing analysis in the subject space. Both approaches reveal connectivity effects of TBI, specifically a region of reduced FA in the white matter connecting the thalamus to BA 10.

关键词： Brain modeling Brain injuries Diffusion tensor imaging Anisotropic magnetoresistance Performance analysis image analysis Pattern analysis Brain computer interfaces Computer interfaces Computer networks

来源：评论

学校读者我要写书评

暂无评论

Automated Meshing of Anatomical Shapes for Deformable Medial Modeling: Application to the Placenta in 3D Ultrasound

Automated Meshing of Anatomical Shapes for Deformable Medial...

引用

IEEE International Symposium on Biomedical Imaging

作者： Alison M. Pouch Paul A. Yushkevich Abdullah H. Aly Alexander H.F. Woltersom Edidiong Okon Ahmed H. Aly Natalie Yushkevich Shobhana Parameshwaran Jiancong Wang Baris Oguz C. James Gee Ipek Oguz Nadav Schwartz Penn Image Computing and Science Laboratory University of Pennsylvania Philadelphia PA Division of Maternal and Fetal Medicine University of Pennsylvania Philadelphia PA Vanderbilt University Nashville TN

ISBN: (数字)9781538693308

ISBN: (纸本)9781538693315

Deformable medial modeling is an approach to extracting clinically useful features of the morphological skeleton of anatomical structures in medical images. Similar to any deformable modeling technique, it requires a pre-defined model, or synthetic skeleton, of a class of shapes before modeling new instances of that class. The creation of synthetic skeletons often requires manual interaction, and the deformation of the synthetic skeleton to new target geometries is prone to registration errors if not well initialized. This work presents a fully automated method for creating synthetic skeletons (i.e., 3D boundary meshes with medial links) for flat, oblong shapes that are homeomorphic to a sphere. The method rotationally cross-sections the 3D shape, approximates a 2D medial model in each cross-section, and then defines edges between nodes of neighboring slices to create a regularly sampled 3D boundary mesh. In this study, we demonstrate the method on 62 segmentations of placentas in first-trimester 3D ultrasound images and evaluate its compatibility and representational accuracy with an existing deformable modeling method. The method may lead to extraction of new clinically meaningful features of placenta geometry, as well as facilitate other applications of deformable medial modeling in medical image analysis.

关键词： Shape Three-dimensional displays Deformable models Skeleton Geometry Two dimensional displays Anatomical structure

来源：评论

学校读者我要写书评

暂无评论

Domain Generalizer: A few-shot meta learning framework for domain generalization in medical imaging

arXiv

引用

arXiv 2020年

作者： Khandelwal, Pulkit Yushkevich, Paul Department of Bioengineering University of Pennsylvania PhiladelphiaPA United States Penn Image Computing and Science Laboratory Department of Radiology University of Pennsylvania PhiladelphiaPA United States

Deep learning models perform best when tested on target (test) data domains whose distribution is similar to the set of source (train) domains. However, model generalization can be hindered when there is significant difference in the underlying statistics between the target and source domains. In this work, we adapt a domain generalization method based on a model-agnostic meta-learning framework [1] to biomedical imaging. The method learns a domain-agnostic feature representation to improve generalization of models to the unseen test distribution. The method can be used for any imaging task, as it does not depend on the underlying model architecture. We validate the approach through a computed tomography (CT) vertebrae segmentation task across healthy and pathological cases on three datasets. Next, we employ few-shot learning, i.e. training the generalized model using very few examples from the unseen domain, to quickly adapt the model to new unseen data distribution. Our results suggest that the method could help generalize models across different medical centers, image acquisition protocols, anatomies, different regions in a given scan, healthy and diseased populations across varied imaging modalities. Copyright © 2020, The Authors. All rights reserved.

关键词： Computerized 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：