Filters








25,509 Hits in 7.3 sec

Validation of Image Segmentation and Expert Quality with an Expectation-Maximization Algorithm [chapter]

Simon K. Warfield, Kelly H. Zou, William M. Wells
2002 Lecture Notes in Computer Science  
We present here an Expectation-Maximization algorithm for computing a probabilistic estimate of the "ground truth" segmentation from a group of expert segmentations, and a simultaneous measure of the quality  ...  This approach readily enables the assessment of an automated image segmentation algorithm, and direct comparison of expert and algorithm performance.  ...  We gratefully acknowledge the contributions of the experts who generated the segmentations of the clinical data, and of Dr.  ... 
doi:10.1007/3-540-45786-0_37 fatcat:cfwh4xmxo5ahzdn4jetpswo2j4

An Expectation Maximization-Like Algorithm for Multi-atlas Multi-label Segmentation [chapter]

Torsten Rohlfing, Daniel B. Russakoff, Calvin R. Maurer
2003 Informatik aktuell  
We present in this paper a novel interpretation of the concept of an "expert" in image segmentation as the pairing of an atlas image and a non-rigid registration algorithm.  ...  We introduce an extension to a recently presented expectation maximization (EM) algorithm for ground truth recovery, which allows us to integrate the segmentations obtained from multiple experts (i.e.,  ...  Instead, they describe an expectation maximization (EM) algorithm that iteratively estimates each expert's quality parameters, i.e., sensitivity and specificity.  ... 
doi:10.1007/978-3-642-18993-7_71 fatcat:dpom3ympkbdn5li5roj5pcel4u

Expectation Maximization Strategies for Multi-atlas Multi-label Segmentation [chapter]

Torsten Rohlfing, Daniel B. Russakoff, Calvin R. Maurer
2003 Lecture Notes in Computer Science  
In order to combine multiple segmentations we introduce two extensions to an expectation maximization (EM) algorithm for ground truth estimation based on multiple experts (Warfield et al., MICCAI 2002)  ...  By applying random deformations, a given ground truth atlas is transformed into multiple segmentations that could result from imperfect registrations of an image to multiple atlas images.  ...  DBR was supported by the Interdisciplinary Initiatives Program, which is part of the Bio-X Program at Stanford University, under the grant "Image-Guided Radiosurgery for the Spine and Lungs."  ... 
doi:10.1007/978-3-540-45087-0_18 fatcat:oj42rf7ctbgnxf7j2gnye3h3xi

Tissue tracking: applications for brain MRI classification

John Melonakos, Yi Gao, Allen Tannenbaum, Joseph M. Reinhardt, Josien P. W. Pluim
2007 Medical Imaging 2007: Image Processing  
We show results of our algorithm on 20 brain MRI datasets along with validation against expert manual segmentations.  ...  In this paper, we show how expectation-maximization weights and neighboring posterior probabilities may be combined to make intuitive use of the Bayesian priors.  ...  ACKNOWLEDGMENTS This work is part of the National Alliance for Medical Image Computing (NAMIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149  ... 
doi:10.1117/12.710063 pmid:24392193 pmcid:PMC3877326 dblp:conf/miip/MelonakosGT07 fatcat:ynejs7zajjbphkszeehxfwpu6m

Incorporating Priors on Expert Performance Parameters for Segmentation Validation and Label Fusion: A Maximum a Posteriori STAPLE [chapter]

Olivier Commowick, Simon K. Warfield
2010 Lecture Notes in Computer Science  
In order to evaluate the quality of segmentations of an image and assess intra-and inter-expert variability in segmentation performance, an Expectation Maximization (EM) algorithm for Simultaneous Truth  ...  This algorithm, originally presented for segmentation validation, has since been used for many applications, such as atlas construction and decision fusion.  ...  This investigation was supported in part by a research grant from CIMIT, grants RG 3478A2/2 and RG 4032A1/1 from NMSS, and by NIH grants R03 EB008680, R01 RR021885, R01 GM074068 and R01 EB008015.  ... 
doi:10.1007/978-3-642-15711-0_4 fatcat:5dgba5bxbbbkpafoxtg2ogz4le

Estimation of inferential uncertainty in assessing expert segmentation performance from STAPLE

Olivier Commowick, Simon K Warfield
2009 Information processing in medical imaging : proceedings of the ... conference  
The evaluation of the quality of segmentations of an image, and the assessment of intra- and inter-expert variability in segmentation performance, has long been recognized as a difficult task.  ...  Recently an Expectation Maximization (EM) algorithm for Simultaneous Truth and Performance Level Estimation (STAPLE), Was developed to compute both an estimate of the reference standard segmentation and  ...  Acknowledgments This investigation was supported in part by a research grant from CIMIT, grant RG 3478A2/2 from the NMSS, and by NIH grants R03 CA126466, R01 RR021885, R01 GM074068, R01 EB008015 and P30  ... 
pmid:19694305 pmcid:PMC3955985 fatcat:66jmchu4vje6xd7hsqf4nvup24

A new automatic algorithm for quantification of myocardial infarction imaged by late gadolinium enhancement cardiovascular magnetic resonance: experimental validation and comparison to expert delineations in multi-center, multi-vendor patient data

Henrik Engblom, Jane Tufvesson, Robert Jablonowski, Marcus Carlsson, Anthony H. Aletras, Pavel Hoffmann, Alexis Jacquier, Frank Kober, Bernhard Metzler, David Erlinge, Dan Atar, Håkan Arheden (+1 others)
2016 Journal of Cardiovascular Magnetic Resonance  
Therefore, the aim of this study was to develop an automatic algorithm for MI quantification in IR and PSIR LGE images and to validate the new algorithm experimentally and compare it to expert delineations  ...  Methods: The new automatic algorithm, EWA (Expectation Maximization, weighted intensity, a priori information), was implemented using an intensity threshold by Expectation Maximization (EM) and a weighted  ...  , Sweden, and Region of Scania, Sweden.  ... 
doi:10.1186/s12968-016-0242-5 pmid:27145749 pmcid:PMC4855857 fatcat:tjilschbyjgybf5sbu6g2pjwb4

Estimation of Inferential Uncertainty in Assessing Expert Segmentation Performance from Staple [chapter]

Olivier Commowick, Simon K. Warfield
2009 Lecture Notes in Computer Science  
The evaluation of the quality of segmentations of an image, and the assessment of intra-and inter-expert variability in segmentation performance, has long been recognized as a dicult task.  ...  Recently an Expectation Maximization (EM) algorithm for Simultaneous Truth and Performance Level Estimation (Staple), was developed to compute both an estimate of the reference standard segmentation and  ...  Acknowledgments This investigation was supported in part by a research grant from CIMIT, grant RG 3478A2/2 from the NMSS, and by NIH grants R03 CA126466, R01 RR021885, R01 GM074068, R01 EB008015 and P30  ... 
doi:10.1007/978-3-642-02498-6_58 fatcat:7a4mnfrbi5dqzar56unr32jloy

Automatic segmentation of myocardium at risk from contrast enhanced SSFP CMR: validation against expert readers and SPECT

Jane Tufvesson, Marcus Carlsson, Anthony H. Aletras, Henrik Engblom, Jean-François Deux, Sasha Koul, Peder Sörensson, John Pernow, Dan Atar, David Erlinge, Håkan Arheden, Einar Heiberg
2016 BMC Medical Imaging  
Automatic segmentation algorithms have been developed and validated for MI by LGE as well as for MaR by T2-weighted imaging. There are, however, no algorithms available for CE-SSFP.  ...  Automatic segmentation was validated against manual delineation by expert readers in 183 patients with reperfused acute MI from two multi-center randomized clinical trials (RCT) (CHILL-MI and MITOCARE)  ...  Several algorithms have been developed and validated for automatic segmentation of MI size in LGE images [3, 9, 10] .  ... 
doi:10.1186/s12880-016-0124-1 pmid:26946139 pmcid:PMC4779553 fatcat:lqfaak3avfaz3dkyfipd43zgny

Automatic segmentation of myocardium at risk from contrast enhanced SSFP CMR: validation against expert readers and SPECT

Jane Tufvesson, Marcus Carlsson, Anthony H Aletras, Henrik Engblom, Jean-Francois Deux, Sasha Koul, Peder Sörensson, John Pernow, Dan Atar, David Erlinge, Håkan Arheden, Einar Heiberg
2016 Journal of Cardiovascular Magnetic Resonance  
Automatic segmentation algorithms have been developed and validated for MI by LGE as well as for MaR by T2-weighted imaging. There are, however, no algorithms available for CE-SSFP.  ...  Automatic segmentation was validated against manual delineation by expert readers in 183 patients with reperfused acute MI from two multi-center randomized clinical trials (RCT) (CHILL-MI and MITOCARE)  ...  Several algorithms have been developed and validated for automatic segmentation of MI size in LGE images [3, 9, 10] .  ... 
doi:10.1186/1532-429x-18-s1-p222 fatcat:r2cpnvqbtrbb7a76jx3wxccvv4

Estimation of Inferential Uncertainty in Assessing Expert Segmentation Performance From STAPLE

O. Commowick, S.K. Warfield
2010 IEEE Transactions on Medical Imaging  
The evaluation of the quality of segmentations of an image, and the assessment of intra-and inter-expert variability in segmentation performance, has long been recognized as a difficult task.  ...  Recently an Expectation Maximization (EM) algorithm for Simultaneous Truth and Performance Level Estimation (STAPLE) was developed to this end to compute both an estimate of the reference standard segmentation  ...  EB008015 and P30 HD018655.  ... 
doi:10.1109/tmi.2009.2036011 pmid:20199913 pmcid:PMC3183509 fatcat:qxlcppwnczdjdbpfgdvpkwl27m

Incorporating Non-rigid Registration into Expectation Maximization Algorithm to Segment MR Images [chapter]

Kilian M. Pohl, William M. Wells, Alexandre Guimond, Kiyoto Kasai, Martha E. Shenton, Ron Kikinis, W. Eric L. Grimson, Simon K. Warfield
2002 Lecture Notes in Computer Science  
The paper introduces an algorithm which allows the automatic segmentation of multi channel magnetic resonance images.  ...  To our knowledge this is the first description of an algorithm capable of automatic cortical parcellation incorporating strong noise reduction and image intensity correction.  ...  Center for Integration of Medicine and Innovative Technology.  ... 
doi:10.1007/3-540-45786-0_70 pmid:28626841 pmcid:PMC5470604 fatcat:s4mo7pe7d5fdxddtjzymqbmmoa

Evaluation of deep learning-based myocardial infarction quantification using Segment CMR software [article]

Olivier Rukundo
2021 arXiv   pre-print
Segment CMR software incorporates the expectation-maximization, weighted intensity, a priori information (EWA) algorithm used to generate the infarct scar volume, infarct scar percentage, and microvascular  ...  Here, Segment CMR software segmentation algorithm is updated with semantic segmentation with U-net to achieve and evaluate fully automated or deep learning-based MI quantification.  ...  The EWA algorithm is an automatic algorithm for quantification of the size of MI imaged by late gadolinium enhancement (LGE)-magnetic resonance imaging (MRI).  ... 
arXiv:2012.09070v3 fatcat:ship4uyvdjcgxn2nxbxidwiplu

New Method for Image Segmentation

Lahouaoui Lalaoui, Tayeb. Mohamadi, Abdelhak Djaalab
2015 Procedia - Social and Behavioral Sciences  
in this paper we describe a modified segmentation method applied to image. An EM algorithm is developed to estimate parameters of the Gaussian mixtures.  ...  Recently, researchers are focusing more on the study of expectation of maximization (EM) due to its useful applications in a number of areas, such as multimedia, image processing, pattern recognition and  ...  Finally, the criterion is applied between image segmentation with algorithm and ground truth given by expert.  ... 
doi:10.1016/j.sbspro.2015.06.210 fatcat:sh5wz4jjtncabfrvk2fk76rmoq

Consensus Based Medical Image Segmentation Using Semi-Supervised Learning And Graph Cuts [article]

Dwarikanath Mahapatra
2018 arXiv   pre-print
Popular approaches use iterative Expectation Maximization (EM) to estimate the final annotation and quantify annotator's performance. Such techniques pose the risk of getting trapped in local minima.  ...  Experimental results on synthetic images, real data of Crohn's disease patients and retinal images show our final segmentation to be accurate and more consistent than competing methods.  ...  or segmentation algorithms, or to assess the annotation quality of different raters through inter-and intra-expert variability [1] .  ... 
arXiv:1612.02166v3 fatcat:l3qceudza5czld5a6hennkjeu4
« Previous Showing results 1 — 15 out of 25,509 results