Filters








21,445 Hits in 5.0 sec

3D Active Shape Model Segmentation with Nonlinear Shape Priors [chapter]

Matthias Kirschner, Meike Becker, Stefan Wesarg
2011 Lecture Notes in Computer Science  
The Active Shape Model (ASM) is a segmentation algorithm which uses a Statistical Shape Model (SSM) to constrain segmentations to 'plausible' shapes.  ...  In this work, we investigate 3D ASM segmentation with a nonlinear SSM based on Kernel PCA.  ...  One of the most popular segmentation algorithms with a shape prior is the Active Shape Model (ASM) [1] , which uses a linear, landmark-based Statistical Shape Model (SSM).  ... 
doi:10.1007/978-3-642-23629-7_60 fatcat:6jps4n7klnf6vmnydwytvyckwm

LOCALLY ADAPTIVE AUTOREGRESSIVE ACTIVE MODELS FOR SEGMENTATION OF 3D ANATOMICAL STRUCTURES

Charles Florin, Nikos Paragios, Gareth Funka-Lea, James Williams
2007 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro  
A quantitative comparative study with 3D Active Shape Models demonstrate the potential of the method.  ...  In this paper, we introduce a novel family of shape prior models that aim to capture such varying support.  ...  undergo large shape variations and with weak image support, a local segmentation, constrained by a 3D statistical model (the 3D autoregression) performs better than a global 3D approach.  ... 
doi:10.1109/isbi.2007.357072 dblp:conf/isbi/FlorinPFW07 fatcat:kbjugueamjhjphbuvg4dkdzzhe

A Nonrigid Kernel-Based Framework for 2D-3D Pose Estimation and 2D Image Segmentation

R Sandhu, S Dambreville, A Yezzi, A Tannenbaum
2011 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Thus, we propose to solve the 2D-3D pose estimation and 2D image segmentation via nonlinear manifold learning of 3D embedded shapes for a general class of objects or deformations for which one may not  ...  In this work, we present a nonrigid approach to jointly solving the tasks of 2D-3D pose estimation and 2D image segmentation.  ...  of a single 3D shape prior.  ... 
doi:10.1109/tpami.2010.162 pmid:20733218 pmcid:PMC3655730 fatcat:7k2cibldfjdqzkxipeyz2bo73u

Rotationally resliced 3D prostate TRUS segmentation using convex optimization with shape priors

Wu Qiu, Jing Yuan, Eranga Ukwatta, Aaron Fenster
2015 Medical Physics (Lancaster)  
A convex optimization method driven by histogram matching is then used to segment the prostate contour in this slice with a nonlinear statistical shape prior learned by KPCA, which is described in detail  ...  Since the used affine registration was not able to recover nonlinear deformation, the mean shape was shrunk by 15 pixels [the inside contour in Fig. 4(a) ] to model more accurate prior PDFs based on its  ... 
doi:10.1118/1.4906129 pmid:25652500 fatcat:jsixylyosnds3nznhjgm3qqjee

A level set-based global shape prior and its application to image segmentation

Lei Zhang, Qiang Ji
2009 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
We apply this global shape prior to segmentation of three sequences of Electron Tomography membrane images.  ...  In this work, we propose a global shape prior representation and incorporate it into a level set based image segmentation framework.  ...  are the produced segmentation results using the model with the proposed prior term; c), e) and g) are the produced segmentation results using the model with Chan's prior.  ... 
doi:10.1109/cvprw.2009.5204275 dblp:conf/cvpr/ZhangJ09a fatcat:px5fckbmt5a3zc3clgw5bqavna

A level set-based global shape prior and its application to image segmentation

Lei Zhang, Qiang Ji
2009 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
We apply this global shape prior to segmentation of three sequences of Electron Tomography membrane images.  ...  In this work, we propose a global shape prior representation and incorporate it into a level set based image segmentation framework.  ...  are the produced segmentation results using the model with the proposed prior term; c), e) and g) are the produced segmentation results using the model with Chan's prior.  ... 
doi:10.1109/cvpr.2009.5204275 fatcat:pseyodjszngb7f2r2sa7xtpz2q

Level Set Segmentation with Shape and Appearance Models Using Affine Moment Descriptors [chapter]

Carlos Platero, María Carmen Tobar, Javier Sanguino, José Manuel Poncela, Olga Velasco
2011 Lecture Notes in Computer Science  
We propose a level set based variational approach that incorporates shape priors into edge-based and region-based models. The evolution of the active contour depends on local and global information.  ...  Finally, we illustrate the benefits of the our approach on the liver segmentation from CT images.  ...  Liver segmentation from 3D CT Images Liver segmentation from 3D CT images is usually the first step in the computerassisted diagnosis and surgery systems for liver diseases.  ... 
doi:10.1007/978-3-642-21257-4_14 fatcat:g5bkobtgnravphdzaeupilkqla

Simultaneous Monocular 2D Segmentation, 3D Pose Recovery and 3D Reconstruction [chapter]

Victor Adrian Prisacariu, Aleksandr V. Segal, Ian Reid
2013 Lecture Notes in Computer Science  
We define an image and level set based energy function, which we minimise with respect to 3D pose and shape, 2D segmentation resulting automatically as the projection of the recovered shape under the recovered  ...  We propose a novel framework for joint 2D segmentation and 3D pose and 3D shape recovery, for images coming from a single monocular source.  ...  It is therefore unlikely that a full unconstrained 3D shape recovery could be performed successfully with no prior knowledge of pose or segmentation.  ... 
doi:10.1007/978-3-642-37331-2_45 fatcat:x7atakixu5fzje3d6muq5acy2e

Multi-Structure Deep Segmentation with Shape Priors and Latent Adversarial Regularization [article]

Arnaud Boutillon, Bhushan Borotikar, Christelle Pons, Valérie Burdin, Pierre-Henri Conze
2021 arXiv   pre-print
The novel shape priors based adversarial regularization (SPAR) exploits latent shape codes arising from ground truth and predicted masks to guide the segmentation network towards more consistent and plausible  ...  Based on a newly devised shape code discriminator, our adversarial regularization scheme enforces the deep network to follow a learnt shape representation of the anatomy.  ...  In the context of medical imaging, segmentation allows the generation of 3D models of anatomical structures which are then used to guide clinical decisions.  ... 
arXiv:2101.10173v1 fatcat:fdkexc262rbyplkswk2haojl54

3D image segmentation of deformable objects with joint shape-intensity prior models using level sets

J YANG
2004 Medical Image Analysis  
We propose a novel method for 3D image segmentation, where a Bayesian formulation, based on joint prior knowledge of the object shape and the image gray levels, along with information derived from the  ...  We define a maximum a posteriori (MAP) estimation model using the joint prior information of the object shape and the image gray levels to realize image segmentation.  ...  Schultz for help with the visualization and manual tracing of the MR data. The authors also thank Hemant Tagare for the many thoughtful discussions and comments.  ... 
doi:10.1016/j.media.2004.06.008 pmid:15450223 pmcid:PMC2832842 fatcat:kyjaa5iquzaqjaxxxqbxd3dbr4

Lateral Ventricle Segmentation of 3D Pre-term Neonates US Using Convex Optimization [chapter]

Wu Qiu, Jing Yuan, Jessica Kishimoto, Eranga Ukwatta, Aaron Fenster
2013 Lecture Notes in Computer Science  
The proposed segmentation approach makes use of convex optimization technique in combination with a subject-specific shape model.  ...  To the best of our knowledge, this paper reports the first study on semi-automatic segmentation of lateral ventricles in neonates with IVH from 3D US images.  ...  shape prior.  ... 
doi:10.1007/978-3-642-40760-4_70 fatcat:dfdxtqshnnctpock7eubmetu3y

Robust shape prior modeling based on Gaussian-Bernoulli restricted Boltzmann Machine

Han Zhang, Shaoting Zhang, Kang Li, Dimitris N. Metaxas
2014 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)  
This powerful generative model is effective in capturing complex shape variations and handling nonlinear shape transformations.  ...  Experiments show that our shape modeling method is qualitatively and quantitatively better than other widely-used shape prior methods.  ...  The reason is that the nonlinear activation function of the hidden units allows the model to capture complex shape variations.  ... 
doi:10.1109/isbi.2014.6867861 dblp:conf/isbi/ZhangZLM14 fatcat:x5zzo7wdvzdm7b53bilupxqy5e

Mixture Modeling of Global Shape Priors and Autoencoding Local Intensity Priors for Left Atrium Segmentation [article]

Tim Sodergren and Riddhish Bhalodia and Ross Whitaker and Joshua Cates and Nassir Marrouche and Shireen Elhabian
2019 arXiv   pre-print
Nonetheless, a single multivariate Gaussian is not an adequate model in cases with significant nonlinear shape variation or where the prior distribution is multimodal.  ...  Difficult image segmentation problems, for instance left atrium MRI, can be addressed by incorporating shape priors to find solutions that are consistent with known objects.  ...  Nonetheless, a single multivariate Gaussian is not an adequate model in cases with significant nonlinear shape variation or where the prior distribution is multimodal.  ... 
arXiv:1903.06260v1 fatcat:dgc7ahto5zebbcdthsxdd24xoe

Exploration and Visualization of Segmentation Uncertainty using Shape and Appearance Prior Information

A Saad, G Hamarneh, T Möller
2010 IEEE Transactions on Visualization and Computer Graphics  
The originality of our approach is that the data exploration is guided by shape and appearance knowledge learned from expert-segmented images of a training population.  ...  These widgets furnish the user with contextual information about conformance or deviation from the population statistics.  ...  One of the important algorithms incorporating prior knowledge is the seminal work of active shape model by Cootes et al. [7] .  ... 
doi:10.1109/tvcg.2010.152 pmid:20975177 fatcat:vinyjw2jdbfqrh5unvgoce46cy

3D Object Tracking Using Directional Procrustes Snake

Mehdi kamandar, Seyed Alireza Seyedin, Hossein Khoshbin
2008 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications  
A novel method of parametric active contours with geometric shape prior is presented in this paper.  ...  This extra shape knowledge enhances the model robustness to noise, occlusion and complex background.  ...  Hence, snake converts the segmentation problem to minimizing an energy function. By now, there are two kinds of active contour models: parametric and geometric active models.  ... 
doi:10.1109/ictta.2008.4530072 fatcat:vya7cod7grdgzo6463vb737fqe
« Previous Showing results 1 — 15 out of 21,445 results