392 Hits in 6.0 sec

A Variational PDE Based Level Set Method for a Simultaneous Segmentation and Non-rigid Registration [chapter]

Jung-ha An, Yunmei Chen, Feng Huang, David Wilson, Edward Geiser
2005 Lecture Notes in Computer Science  
A new variational PDE based level set method for a simultaneous image segmentation and non-rigid registration using prior shape and intensity information is presented.  ...  The segmentation is obtained by finding a non-rigid registration to the prior shape. The non-rigid registration consists of both a global rigid transformation and a local non-rigid deformation.  ...  Description of the Proposed Model A Simultaneous Segmentation and Non-rigid Registration A new variational PDE based level set method for a simultaneous image segmentation and non-rigid registration  ... 
doi:10.1007/11566465_36 fatcat:ts4guqohdzaa3drtn6cu7nl3qm

Simultaneous Registration and Segmentation of Anatomical Structures from Brain MRI [chapter]

Fei Wang, Baba C. Vemuri
2005 Lecture Notes in Computer Science  
Our work is a departure from earlier methods in that we have a unified variational principle wherein non-rigid registration and segmentation are simultaneously achieved; unlike previous methods of solution  ...  In this paper, we present a novel variational formulation of the registration assisted image segmentation problem which leads to solving a coupled set of nonlinear PDEs that are solved using efficient  ...  A variational principle in a level-set based formulation was presented in Pargios et. al., [4] , for segmentation and registration of cardiac MRI data.  ... 
doi:10.1007/11566465_3 fatcat:lvfhn3tsqbh7xhy2iqxurpwauu

Estimation of Vector Fields in Unconstrained and Inequality Constrained Variational Problems for Segmentation and Registration

Gozde Unal, Greg Slabaugh
2008 Journal of Mathematical Imaging and Vision  
Our technique differs from recently popular joint segmentation and registration algorithms, particularly in its coupled set of PDEs derived from the same set of energy terms for registration and segmentation  ...  We also explore the utility of inequality constraints applied to variational problems in vision such as estimation of deformation fields in non-rigid registration and tracking.  ...  Fig. 2 2 Non-rigid mapping between two images defined through the coordinate transformation: T (x) = x + u A joint non-rigid registration and segmentation approach For segmentation of a structure appearing  ... 
doi:10.1007/s10851-008-0064-7 fatcat:mabiob2yojdkvoie6prccnzifq

Simultaneous Registration and Segmentation by L1 Minimization [chapter]

Pratik Shah, Mithun Das Gupta
2012 Lecture Notes in Computer Science  
This paper studies the problem of simultaneously registering and segmenting a pair of images despite the presence of non-smooth boundaries.  ...  For the remaining images in the set, we propose a novel L1 minimization based technique, which leverages the fact that the other image is not closely segmented but has a reasonably 'thin' boundary around  ...  Each pair of image shows the original frame and the bone removed frame. The two pairs in boxes are manually generated. The last two images show the MIP projection before and after bone removal.  ... 
doi:10.1007/978-3-642-35428-1_16 fatcat:2ftrzmieqbb6zjn5fgpoysc2eq

Joint Registration and Segmentation of Neuroanatomic Structures From Brain MRI

Fei Wang, Baba C. Vemuri, Stephan J. Eisenschenk
2006 Academic Radiology  
Materials and Methods-We present a novel variational formulation of the registration assisted image segmentation problem which leads to solving a coupled set of nonlinear Partial Differential Equations  ...  Results-We present several examples (20) on synthetic and Conclusion- The proposed atlas-based segmentation technique is capable of simultaneously achieve the nonrigid registration and the segmentation  ...  Leonard of the University of Florida Neuroscience Department for the hippocampal data sets.  ... 
doi:10.1016/j.acra.2006.05.017 pmid:16935722 pmcid:PMC2921911 fatcat:p24pwmovvjaa5lvlkqe7mkiyiu

Multimodal Bone Cancer Detection Using Fuzzy Classification and Variational Model [chapter]

Sami Bourouis, Ines Chennoufi, Kamel Hamrouni
2013 Lecture Notes in Computer Science  
Our segmentation process involves different steps: a registration step of different image modalities, a fuzzy-possibilistic classification (FPCM) step and a final segmentation step based on a variational  ...  In this paper we investigate this line of research by introducing a new method for segmenting bone cancer.  ...  Unlike the traditional parametric active contours-based methods, geometric level set-based methods are considered an appropriate framework for merging heterogeneous information that provide a consistent  ... 
doi:10.1007/978-3-642-41822-8_22 fatcat:cvdlxl7qhjerhnxcvzvjsmync4

An Active Contour-Based Atlas Registration Model Applied to Automatic Subthalamic Nucleus Targeting on MRI: Method and Validation [chapter]

Valérie Duay, Xavier Bresson, Javier Sanchez Castro, Claudio Pollo, Meritxell Bach Cuadra, Jean-Philippe Thiran
2008 Lecture Notes in Computer Science  
Our simultaneous segmentation and registration model shows mean STN localization errors statistically similar to the most performing registration algorithms tested so far and to the targeting expert's  ...  This paper presents a new non parametric atlas registration framework, derived from the optical flow model and the active contour theory, applied to automatic subthalamic nucleus (STN) targeting in deep  ...  The main source of inspiration of our joint registration and segmentation algorithm is the partial derivative equation (PDE)-based method proposed by Vemuri et al. in [6] 1 .  ... 
doi:10.1007/978-3-540-85990-1_118 fatcat:cowqbghodreefo72wghlcphyqu

A Variational Model for Object Segmentation Using Boundary Information and Shape Prior Driven by the Mumford-Shah Functional

Xavier Bresson, Pierre Vandergheynst, Jean-Philippe Thiran
2006 International Journal of Computer Vision  
In this paper, we propose a variational model for object segmentation using the active contour method, a geometric shape prior and the Mumford-Shah functional.  ...  The minimization of the functional gives a system of coupled ordinary and partial differential equations which steady state, computed in a level set framework, provides the solution of the segmentation  ...  active contours term which simultaneously achieves registration and segmentation.  ... 
doi:10.1007/s11263-006-6658-x fatcat:3z3o2tiwwzfwregfgkthixlv5a

Registration of MRI to intraoperative radiographs for target localization in spinal interventions

T De Silva, A Uneri, M D Ketcha, S Reaungamornrat, J Goerres, M W Jacobson, S Vogt, G Kleinszig, A J Khanna, J-P Wolinsky, J H Siewerdsen
2017 Physics in Medicine and Biology  
Registration performance was found to be robust for segmentation methods exhibiting RMSE < 3 mm and CAR > 0.50.  ...  Methods-Straightforward adaptation of gradient/intensity-based methods appropriate to CT-toradiograph registration is confounded by large mismatch and noncorrespondence in image intensity between MRI and  ...  R01-EB-017226 and academic-industry collaboration with Siemens Healthcare (XP Division, Erlangen Germany).  ... 
doi:10.1088/1361-6560/62/2/684 pmid:28050972 pmcid:PMC5321067 fatcat:xdqttw3abnhy7nsttoetqm5fhu

Shape Statistics for Image Segmentation with Prior

Guillaume Charpiat, Olivier Faugeras, Renaud Keriven
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
We propose a new approach to compute non-linear, intrinsic shape statistics and to incorporate them into a shape prior for an image segmentation task.  ...  Given a sample set of contours, we first define their mean shape as the one which is simultaneously closest to all samples up to rigid motions, and compute it in a gradient descent framework.  ...  The two PDEs are solved simultaneously. The evolution of Γ is done in a level-set framework whereas the parameters of the rigid motions follow a usual gradient descent in R.  ... 
doi:10.1109/cvpr.2007.383009 dblp:conf/cvpr/CharpiatFK07 fatcat:o4e3bl3qlrcfzne64wblzvcgvm

An integrated approach to segmentation and nonrigid registration for application in image-guided pelvic radiotherapy

Chao Lu, Sudhakar Chelikani, Xenophon Papademetris, Jonathan P. Knisely, Michael F. Milosevic, Zhe Chen, David A. Jaffray, Lawrence H. Staib, James S. Duncan
2011 Medical Image Analysis  
non-rigid registration.  ...  Clinical application and evaluation of dose delivery show the superiority of proposed method to the procedure currently used in clinical practice, i.e. manual segmentation followed by rigid registration  ...  We would like to thank the anonymous reviewers for their valuable remarks which benefit the revision of this paper.  ... 
doi:10.1016/ pmid:21646038 pmcid:PMC3164526 fatcat:vaupxjqinvfarhvy64h5lzgwza

Combining the band-limited parameterization and Semi-Lagrangian Runge–Kutta integration for efficient PDE-constrained LDDMM [article]

Monica Hernandez
2020 arXiv   pre-print
The family of PDE-constrained LDDMM methods is emerging as a particularly interesting approach for physically meaningful diffeomorphic transformations.  ...  The accuracy of the resulting methods is evaluated extensively. For all the variants, the proposed combined approach shows a significant increment of the computational efficiency.  ...  The author would like to give special thanks to Wen Mei Hwu from the University of Illinois for interesting ideas in the GPU implementation of the methods, and Nacho Navarro and Rosa Badia from the Barcelona  ... 
arXiv:2006.06823v1 fatcat:zxgnob4sbbbptjavgwbq4ko5ie

Automated Estimation of the Biophysical Target for Radiotherapy Treatment Planning using Multimodality Image Analysis

Issam El Naqa, Deshan Yang, Joseph O Deasy
2007 2007 IEEE International Conference on Image Processing  
We are investigating methods to integrate available information for joint target registration and segmentation of multi-modality images as perceived by the human observer.  ...  Towards this goal, we are exploring multi-valued level set deformable models in conjunction with human perception models for simultaneous delineation of multi-modality images consisting of combinations  ...  ACKNOWLEDGEMENTS This research was partially supported by a grant from the American Cancer Society IRG-58-010-50.  ... 
doi:10.1109/icip.2007.4379883 dblp:conf/icip/El-NaqaYD07 fatcat:7qa7tld4ynb77a7z2u4blbboly

DEFORMOTION Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images [chapter]

Stefano Soatto, Anthony J. Yezzi
2002 Lecture Notes in Computer Science  
Our definition allows us to derive novel and efficient algorithms to register non-identical shapes using region-based methods, and to simultaneously approximate and align structures in greyscale images  ...  The algorithms we propose involve the numerical integration of partial differential equations, which we address within the framework of level set methods.  ...  Belongie for providing us with test data and suggestions. This research is supported in part by NSF grant IIS-9876145, ARO grant DAAD19-99-1-0139 and Intel grant 8029.  ... 
doi:10.1007/3-540-47977-5_3 fatcat:jnnzgwaelzgjlc25louk4sozre

Hierarchical Image Registration With An Active Contour-Based Atlas Registration Model

Abdelkarim Allal, Valérie Duay, Subrahmanyam Gorthi, Nawal Houhou, Jean-Philippe Thiran
2008 Zenodo  
function. 2 The level set method is the non parametric model of the active contour technique.  ...  The difference with our work is that this representation has been proposed for particular variational energy-models and we present a scheme for any type of PDE-based models.  ... 
doi:10.5281/zenodo.41151 fatcat:7oupsl2hdnhzvplhegmsxz346e
« Previous Showing results 1 — 15 out of 392 results