Filters








2,164 Hits in 8.7 sec

Automatically Extract the Left Ventricular Myocardium by Using Active Contour Model
IJARCCE - Computer and Communication Engineering

Jackulin DuraiRani.A, Sivaranjini .B, Rekha. A
2015 IJARCCE  
This paper completely describes the fully automatic segmentation system for left ventricular myocardium segmentation from CT images by using active contour model.  ...  After that, the heart muscle surfaces square measure initialized from the localization result and evolved by applying forces from the image intensities with a constraint supported the initial heart muscle  ...  For example, active shape models that gives a statistical shape model for a set of affiliated shapes with the principal component analysis (PCA) technique, and used for myocardium segmentation.  ... 
doi:10.17148/ijarcce.2015.4302 fatcat:rt6o333wvngfxcmqfq77753vku

Segmentation of Soft atherosclerotic plaques using active contour models [article]

Muhammad Moazzam Jawaid
2016 arXiv   pre-print
Consequently based on detected seed point & intensity behaviour, localized active contour segmentation has been applied to extract complete coronary tree.  ...  In first step automatic seed point has been established based on the fact that coronary artery behaves as tubular structure through axial slices.  ...  Florez et al. [51] presented a deformable cylindrical-simplex-model based algorithm to extract the vascular lumen form 3D MR images.  ... 
arXiv:1608.00116v1 fatcat:5h6n3ervbze47b6oiit66ro4qq

Deformable models in medical image analysis: a survey

Tim McInerney, Demetri Terzopoulos
1996 Medical Image Analysis  
Among model-based techniques, deformable models offer a unique and powerful approach to image analysis that combines geometry, physics, and approximation theory.  ...  Furthermore, they support highly intuitive interaction mechanisms that, when necessary, allow medical scientists and practitioners to bring their expertise to bear on the model-based image interpretation  ...  Acknowledgements We would like to thank Stephanie Sandor and Richard Leahy of the USC Signal and Image Processing Institute for the deformable brain atlas figure, as well as the following individuals for  ... 
doi:10.1016/s1361-8415(96)80007-7 pmid:9873923 fatcat:pb3ros6vcbdhte4ifj7xnbqnfe

Segmentation of the left and right cardiac ventricle using a combined bi-temporal statistical model

Dominik Fritz, Daniel Rinck, Rüdiger Dillmann, Michael Scheuering, Kevin R. Cleary, Robert L. Galloway, Jr.
2006 Medical Imaging 2006: Visualization, Image-Guided Procedures, and Display  
It is based on a combined bi-temporal statistical model of the left and right ventricle using the principal component analysis (PCA) as well as the independent component analysis (ICA) to model global  ...  In contrast to many previous attempts of model based cardiac segmentation we do not create separate models for the left and the right ventricle and for different heart phases, but instead create one single  ...  Herein, the authors model a-priori trained point sets by the application of a Principal Component Analysis (PCA). Registration between the shapes is done by a Procrustes formulation.  ... 
doi:10.1117/12.652991 dblp:conf/miigp/FritzRDS06 fatcat:rhmnebfoo5fqtetqm3f3kdylhi

Automatic Delineation of the Myocardial Wall From CT Images Via Shape Segmentation and Variational Region Growing

Liangjia Zhu, Yi Gao, Vikram Appia, Anthony Yezzi, Chesnal Arepalli, Tracy Faber, Arthur Stillman, Allen Tannenbaum
2013 IEEE Transactions on Biomedical Engineering  
To localize the right ventricle, the active contour model is applied on a heart surface extracted based on the left ventricle segmentation result.  ...  In this paper, we present an automatic method for extracting the myocardial wall of the left and right ventricles from cardiac CT images.  ...  Ernest Garcia of Emory from some useful discussions about the topic of this paper. This work was supported in part by grants from NIH, AFOSR, ARO, ONR, and MDA.  ... 
doi:10.1109/tbme.2013.2266118 pmid:23744658 pmcid:PMC4000443 fatcat:m2aa5bqeafg2hkkuls77t5pebu

Left Ventricle Statistical Models Segmentation of Shape and Appearance for Analysis of Cardiac MRI

Kayte JaypalsingNatthusing, Sumegh Shrikant Tharewal, Mohammed Waseem Ashfaque, Sayyada Sara Banu, Kayte Sangramsing, Manza Ramesh Raybhan
2014 International Journal of Computer Applications  
4D Active Appearance Models on cardiac MRI, using the Simple interactive object extraction (SIOX), have observe a 43-fold increase in fitting accuracy that is on par with fuzzy clustering.  ...  We show the high quality results that are derived by the use of fuzzy clustering, and describe the ways in which it could improve the automated analysis of medical images.  ...  The ASM model finds the main variations in the training data using Principal Component Analysis (PCA), which enables the model to automatically recognize if a contour is a possible/good object contour.  ... 
doi:10.5120/18212-8984 fatcat:m6deegwuorfohli7i3m5r6goru

3-D active appearance models: segmentation of cardiac MR and ultrasound images

S.C. Mitchell, J.G. Bosch, B.P.F. Lelieveldt, R.J. van der Geest, J.H.C. Reiber, M. Sonka
2002 IEEE Transactions on Medical Imaging  
Index Terms-Active appearance model, active shape model, cardiac segmentation, echocardiographic image analysis, magnetic resonance image analysis.  ...  For echocardiographic analysis, the area correlation was 2 = 0 79. The AAM method shows high promise for successful application to MR and echocardiographic image analysis in a clinical setting.  ...  AAM models were trained on image and contour data from 55 subjects, and the model matching performance was subsequently evaluated on the one left-out data set.  ... 
doi:10.1109/tmi.2002.804425 pmid:12564884 fatcat:bt6s3bp23varngj4lv26bk6efe

A review of 3D vessel lumen segmentation techniques: Models, features and extraction schemes

David Lesage, Elsa D. Angelini, Isabelle Bloch, Gareth Funka-Lea
2009 Medical Image Analysis  
We structure our analysis along three axes: models, features and extraction schemes.  ...  We then review the image features that can be extracted to evaluate these models.  ...  Active contours Active contours constitute a popular class of image segmentation techniques that evolve an interface through different forces: external forces, derived from the image, and internal, model-based  ... 
doi:10.1016/j.media.2009.07.011 pmid:19818675 fatcat:rroixlliubb6nfmvlhahdqtniq

Automatic segmentation of the left ventricle and computation of diagnostic parameters using regiongrowing and a statistical model

Dominik Fritz, Daniel Rinck, Roland Unterhinninghofen, Ruediger Dillmann, Michael Scheuering, J. Michael Fitzpatrick, Joseph M. Reinhardt
2005 Medical Imaging 2005: Image Processing  
It is based on a combination of an adaptive slice-based region-growing and a modified Active Shape Model (ASM).  ...  After fitting the ASM to the image, we can use the generated model points to create an exact surface model of the left ventricular myocardium for visualization and for computing the diagnostically relevant  ...  Herein, the authors model a-priori trained point sets by the application of a principal component analysis (PCA). Registration between the shapes is done by Procrustes formulation.  ... 
doi:10.1117/12.595071 dblp:conf/miip/FritzRUDS05 fatcat:v776qzth75anxcbona6bt3pguq

Left ventricular segmentation from MRI datasets with edge modelling conditional random fields

Janto F Dreijer, Ben M Herbst, Johan A du Preez
2013 BMC Medical Imaging  
Many of these are conveniently extracted from Magnetic Resonance Imaging (MRI).  ...  This paper considers automatic segmentation of the left cardiac ventricle in short axis magnetic resonance images.  ...  Additional file 2: Large Sunnybrook montage image. Montage of all end-systole and end-diastole automatic segmentations for the Sunnybrook dataset.  ... 
doi:10.1186/1471-2342-13-24 pmid:23899437 pmcid:PMC3737053 fatcat:g3vohnf77ngnhfomqodtp3keg4

Segmentation of ECG-gated multidetector row-CT cardiac images for functional analysis

Jin Sung Kim, Yonghum Na, Kyongtae T. Bae, Milan Sonka, J. Michael Fitzpatrick
2002 Medical Imaging 2002: Image Processing  
The contour of the ventricular cavity was segmented iteratively from a set of initial coarse boundary points placed on a transaxial CT image and was propagated to adjacent CT images.  ...  The axes were estimated by calculating the principal components of the ventricular boundary points and then confirmed or adjusted by an operator.  ...  MDCT images Segmentation using Region-growing Segmentation using Deformable model 3D volume Reoriented CT images along the short-axis or long axis Principal Component Analysis (PCA) The Overall scheme  ... 
doi:10.1117/12.467142 dblp:conf/miip/KimNB02 fatcat:3q3wxzqcdzcq3oiziljhjglbh4

A 3-D Active Shape Model Driven by Fuzzy Inference: Application to Cardiac CT and MR

H.C. van Assen, M.G. Danilouchkine, M.S. Dirksen, J.H.C. Reiber, B.P.F. Lelieveldt
2008 IEEE Transactions on Information Technology in Biomedicine  
The 3-D ASM was evaluated using 25 CT and 15 MR datasets. Automatically generated contours were compared to expert contours in 100 locations.  ...  Manual quantitative analysis of cardiac left ventricular function using Multislice CT and MR is arduous because of the large data volume.  ...  , y n , z n ) T . (1) From all shapes x i in the training set, a mean shape vector and a covariance matrix are calculated, followed by principal component analysis (PCA) on the covariance matrix to compute  ... 
doi:10.1109/titb.2008.926477 pmid:18779074 fatcat:mq2wxyqynzhgvisgzfxfpt7nbm

A Combined Deep-Learning and Deformable-Model Approach to Fully Automatic Segmentation of the Left Ventricle in Cardiac MRI [article]

M. R. Avendi, A. Kheradvar, H. Jafarkhani
2015 arXiv   pre-print
We validated our method using 45 cardiac MR datasets taken from the MICCAI 2009 LV segmentation challenge and showed that it outperforms the state-of-the art methods.  ...  In this work, we employ deep learning algorithms combined with deformable models to develop and evaluate a fully automatic segmentation tool for the LV from short-axis cardiac MRI datasets.  ...  Acknowledgments This work is partially supported by a grant from American Heart Association (14GRNT18800013).  ... 
arXiv:1512.07951v1 fatcat:jn2v3s6qifewhd5nlzqbt3kpmi

Fully automatic segmentation of 4D MRI for cardiac functional measurements

Yan Wang, Yue Zhang, Wanling Xuan, Evan Kao, Peng Cao, Bing Tian, Karen Ordovas, David Saloner, Jing Liu
2018 Medical Physics (Lancaster)  
The proposed methodology first used the Hough transform and the local Gaussian distribution method (LGD) to segment the LV endocardial contours from cardiac MR images.  ...  This automatic image segmentation approach has been applied to studies on 17 subjects.  ...  The active shape model applies principal component analysis to a set of training shapes in order to extract a certain number of modes that represent shape variations.  ... 
doi:10.1002/mp.13245 pmid:30352129 pmcid:PMC6322927 fatcat:gek6ourtlzb6ppdwf73h6fpyay

Cardiac Motion Recovery via Active Trajectory Field Models

A.D. Gilliam, F.H. Epstein, S.T. Acton
2009 IEEE Transactions on Information Technology in Biomedicine  
to automatically recover cardiac motion from a noisy image sequence.  ...  This novel generative deformable model exploits both image information and prior knowledge of cardiac motion, utilizing a point distribution model derived from a training set of myocardial trajectory fields  ...  An active contour captures a desired image feature by minimizing a corresponding energy functional, typically the weighted sum of an image-based external energy, attracting the contour to features of interest  ... 
doi:10.1109/titb.2008.2009221 pmid:19171529 pmcid:PMC2916732 fatcat:5gfg6vv3frdtbhvc2ijra7n3me
« Previous Showing results 1 — 15 out of 2,164 results