A shape-space-based approach to tracking myocardial borders and quantifying regional left-ventricular function applied in echocardiography
Abstract
This paper presents a new semi-automatic method for quantifying regional heart function from two-dimensional echocardiography. In the approach, we first track the endocardial and epicardial boundaries using a new variant of the dynamic snake approach. The tracked borders are then decomposed into clinically meaningful regional parameters, using a novel interpretational shape-space motivated by the 16-segment model used in clinical practice for qualitative assessment of heart function. We show how a quantitative and automatic scoring scheme for the endocardial excursion and myocardial thickening can be derived from this. Results illustrating our approach on apical long-axis two-chamber-view data from a patient with a myocardial infarct in the apical anterior/inferior region of the heart are presented. In a case study (five patients, nine data sets) the performance of the tracking and interpretation techniques are compared with manual delineations of borders using a number of quantitative measures of regional comparison.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Conventional machine learning methods such as active contours and deformable templates have been widely used to successfully segment the left ventricle under the condition of using prior knowledge about left ventricle shape and appearance.
“To address these issues, various conventional machine learning methods such as active contours [127] and deformable templates [128] have been widely used to successfully segment the LV, under the condition of using prior knowledge about the LV shape and appearance.”
From Deep Learning in Medical Ultrasound Analysis: A Review (2019) · cites this paper as [128]
Cites
STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT
Martin Bland, J., & Altman, D. (1986) · The Lancet · doi:10.1016/s0140-6736(86)90837-8 · Cited by 47,965 · see citing works
Daubechies, I. (1992) · doi:10.1137/1.9781611970104 · Cited by 15,979
Daubechies, I. C., & Heil, C. (1992) · Computers in Physics · doi:10.1063/1.4823127 · Cited by 15,729 · see citing works
Orthonormal bases of compactly supported wavelets
Daubechies, I. C. (1988) · Communications on Pure and Applied Mathematics · doi:10.1002/cpa.3160410705 · Cited by 8,143 · see citing works
Feature extraction from faces using deformable templates
Yuille, A., Hallinan, P. W., & Cohen, D. S. (1992) · International Journal of Computer Vision · doi:10.1007/bf00127169 · Cited by 1,373 · see citing works
An Introduction to Splines for Use in Computer Graphics and Geometric Modeling
Bartels, R. H., Beatty, J. C., & Barsky, B. A. (1987) · Cumulative Index of Computer Aided Architectural Design · Cited by 1,141 · see citing works
Blake, A., & Isard, M. (1998) · Springer eBooks · doi:10.1007/978-1-4471-1555-7 · Cited by 760 · see citing works
Chambolle, A., Vore, R. A. D., Lee, N.-Y., & Lucier, B. J. (1998) · IEEE Transactions on Image Processing · doi:10.1109/83.661182 · Cited by 733 · see citing works
A methodology for evaluation of boundary detection algorithms on medical images
Chalana, V., & Kim, Y. (1997) · IEEE Transactions on Medical Imaging · doi:10.1109/42.640755 · Cited by 543 · see citing works
Lieberman, A. N., Weiss, J. L., Jugdutt, B. I., Becker, L. C., Bulkley, B. H., Garrison, J. G., Hutchins, G. M., Kallman, C., & Weisfeldt, M. L. (1981) · Circulation · doi:10.1161/01.cir.63.4.739 · Cited by 536 · see citing works
Training Models of Shape from Sets of Examples
Cootes, T. F., Taylor, C., Cooper, D. H., & Graham, J. (1992) · Springer eBooks · doi:10.1007/978-1-4471-3201-1_2 · Cited by 473 · see citing works
A framework for spatiotemporal control in the tracking of visual contours
Blake, A., Curwen, R. W., & Zisserman, A. (1993) · International Journal of Computer Vision · doi:10.1007/bf01469225 · Cited by 381 · see citing works
Recovery of nonrigid motion and structure
Pentland, A., & Horowitz, B. (1991) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.85661 · Cited by 358 · see citing works
Structural Image Restoration through Deformable Templates
Amit, Y., Grenander, U., & Piccioni, M. (1991) · Journal of the American Statistical Association · doi:10.1080/01621459.1991.10475053 · Cited by 325 · see citing works
A multiple active contour model for cardiac boundary detection on echocardiographic sequences
Chalana, V., Linker, D. T., Haynor, D. R., & Kim, Y. (1996) · IEEE Transactions on Medical Imaging · doi:10.1109/42.500138 · Cited by 305 · see citing works
Signal processing and compression with wavelet packets
Coifman, R. R., Meyer, Y., Quake, S. R., & Wickerhauser, M. V. (1994) · Springer eBooks · doi:10.1007/978-94-011-1028-0_18 · Cited by 285 · see citing works
Learning flexible models from image sequences
Baumberg, A., & Hogg, D. (1994) · Lecture notes in computer science · doi:10.1007/3-540-57956-7_34 · Cited by 255 · see citing works
Segmentation of intravascular ultrasound images: a knowledge-based approach
Milan Sonka, A., Zhang, X., Siebes, M., Bissing, M. S., DeJong, S. C., Collins, S. M., & McKay, C. R. (1995) · IEEE Transactions on Medical Imaging · doi:10.1109/42.476113 · Cited by 235 · see citing works
Friedland, N. S., & Adam, D. R. (1989) · IEEE Transactions on Medical Imaging · doi:10.1109/42.41487 · Cited by 200 · see citing works
Tracking points on deformable objects using curvature information
Cohen, I., Ayache, N., & Sulger, P. (1992) · Lecture notes in computer science · doi:10.1007/3-540-55426-2_51 · Cited by 195 · see citing works
Training Models of Shape from Sets of Examples
Cootes, T. F., Taylor, C., Cooper, D. H., & Graham, J. (1992) · British Machine Vision Conference (BMVC) · doi:10.5244/c.6.2 · Cited by 169 · see citing works
2D+T acoustic boundary detection in echocardiography
Mulet-Parada, M., & Noble, J. A. (2000) · Medical Image Analysis · doi:10.1016/s1361-8415(00)00006-2 · Cited by 164 · see citing works
Deformable models with parameter functions for cardiac motion analysis from tagged MRI data
Park, J., Metaxas, D., Young, A. A., & Axel, L. (1996) · IEEE Transactions on Medical Imaging · doi:10.1109/42.500137 · Cited by 163 · see citing works
A Bayesian approach to dynamic contours through stochastic sampling and simulated annealing
Storvik, G. O. (1994) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.329011 · Cited by 160 · see citing works
Bourdillon, P. D. V., Broderick, T. M., Sawada, S. G., Armstrong, W. F., Ryan, T., Dillon, J. C., Fineberg, N. S., & Feigenbaum, H. (1989) · Journal of the American Society of Echocardiography · doi:10.1016/s0894-7317(89)80041-0 · Cited by 156 · see citing works
Computer Analysis of Heart Motion from Two-Dimensional Echocardiograms
Mailloux, G. E., Bleau, A., Bertrand, M., & Petitclerc, R. (1987) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.1987.325967 · Cited by 154 · see citing works
Wall position and thickness estimation from sequences of echocardiographic images
Bioucas‐Dias, J. M., & Leitão, J. M. N. (1996) · IEEE Transactions on Medical Imaging · doi:10.1109/42.481438 · Cited by 142 · see citing works
Chu, C. H., Delp, E. J., & Buda, A. (1988) · IEEE Transactions on Medical Imaging · doi:10.1109/42.3932 · Cited by 139 · see citing works
Automatic tracking of the aorta in cardiovascular MR images using deformable models
Rueckert, D., Burger, P., Forbat, S. M., Mohiaddin, R., & Yang, G. Z. (1997) · IEEE Transactions on Medical Imaging · doi:10.1109/42.640747 · Cited by 109 · see citing works
Shape-based tracking of left ventricular wall motion
McEachen, J. C., & Duncan, J. S. (1997) · IEEE Transactions on Medical Imaging · doi:10.1109/42.585761 · Cited by 105 · see citing works
Deformable templates for feature extraction from medical images
Lipson, P., Yuille, A., O'Keeffe, D. T., Cavanaugh, J., Taaffe, J., & Rosenthal, D. I. (1990) · Lecture notes in computer science · doi:10.1007/bfb0014891 · Cited by 93 · see citing works
An Effective Algorithm for Extracting Serial Endocardial Borders from 2-Dimensional Echocardiograms
Zhang, L., & Geiser, E. A. (1984) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.1984.325359 · Cited by 93 · see citing works
Multiple Resolution Bayesian Segmentation of Ultrasound Images
Ashton, E. A., & Parker, K. J. (1995) · Ultrasonic Imaging · doi:10.1177/016173469501700403 · Cited by 88 · see citing works
Yuille, A., & Hallinan, P. (1993) · Cited by 86 · see citing works
Rallidis, L. S., Cokkinos, P., Tousoulis, D., & Nihoyannopoulos, P. (1997) · Journal of the American College of Cardiology · doi:10.1016/s0735-1097(97)00376-8 · Cited by 78 · see citing works
Multiresolution texture based adaptive clustering algorithm for breast lesion segmentation
Djamal Boukerroui, A., Basset, O., Guérin, N., & Baskurt, A. (1998) · European Journal of Ultrasound · doi:10.1016/s0929-8266(98)00062-7 · Cited by 77 · see citing works
Evaluating a robust contour tracker on echocardiographic sequences
Jacob, G., Noble, J. A., Mulet-Parada, M., & Blake, A. (1999) · Medical Image Analysis · doi:10.1016/s1361-8415(99)80017-6 · Cited by 68 · see citing works
Cardiac material markers from tagged MR images
Kerwin, W. S., & Prince, J. L. (1998) · Medical Image Analysis · doi:10.1016/s1361-8415(98)80015-7 · Cited by 60 · see citing works
Dobutamine stress echocardiography
Krahwinkel, W., Ketteler, T., Godke, J., Wolfertz, J., Ulbricht, L. J., Krakau, I., & Gülker, H. (1997) · European Heart Journal · doi:10.1093/eurheartj/18.suppl_d.9 · Cited by 52 · see citing works
Ayache, N., Cohen, I., & Herlin, I. (1993) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 50 · see citing works
On-line analysis of echocardiographic image sequences
Giachetti, A. (1998) · Medical Image Analysis · doi:10.1016/s1361-8415(98)80023-6 · Cited by 34 · see citing works
Quantitative regional analysis of myocardial wall motion
Jacob, G., Noble, J. A., Kelion, A. D., & BANNING, A. P. (2001) · Ultrasound in Medicine & Biology · doi:10.1016/s0301-5629(01)00350-7 · Cited by 32 · see citing works
A deformable region model using stochastic processes applied to echocardiographic images
Herlin, I., Nguyen, C., & Graffigne, C. (2003) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.1992.223139 · Cited by 31 · see citing works
Effects of nontransmural ischemia on inner and outer wall thickening in the canine left ventricle
Torry, R. J., Myers, J. H., Adler, A. L., Liut, C. L., & Gallagher, K. P. (1991) · American Heart Journal · doi:10.1016/0002-8703(91)90568-3 · Cited by 26 · see citing works
Feature extraction in two-dimensional short-axis echocardiographic images
Wilson, D. C., Geiser, E. A., & Li, J.-H. (1993) · Journal of Mathematical Imaging and Vision · doi:10.1007/bf01248357 · Cited by 22 · see citing works
Amini, A. A., Radeva, P. I., Elayyadi, M., & Li, D. (1998) · Lecture notes in computer science · doi:10.1007/bfb0056193 · Cited by 15 · see citing works
Intensity independent feature extraction and tracking in echocardiographic sequences.
Parada, M. M. (2000) · Cited by 11 · see citing works
Dobutamine Stress Echocardiography
Govind, S. C., & Ramesh, S. S. (2008) · Springer eBooks · doi:10.1007/978-3-540-78674-0_11 · Cited by 7 · see citing works
Parker, G. J. M., Schnabel, J. A., & Barker, G. J. (1999) · Lecture notes in computer science · doi:10.1007/3-540-48714-x_50 · Cited by 7 · see citing works
Cardiac stress testing & imaging : a clinician's guide
Marwick, T. H. (1996) · Churchill Livingstone eBooks · Cited by 6 · see citing works
Cosyns, B., Camp, G. V., Droogmans, S., Weytjens, C., Schoors, D., & Lancellotti, P. (2009) · European Journal of Echocardiography · doi:10.1093/ejechocard/jep112 · Cited by 6 · see citing works
Quantifying regional left ventricular function using spatio-temporal tracking techniques
Jacob, G. (1999) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.5287/ora-rvnp0ao9e · Cited by 2 · see citing works
Flagged first, then by citations
1 of the 53 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Ultrasound image segmentation: a survey
Noble, J. A., & Boukerroui, D. (2006) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2006.877092 · Cited by 1,157 · see citing works
“A variant of this is to use a Kalman filter to blend a spatio-temporal model with feature measurements as in [45], [46].”
MethodInfluentialDeep Learning in Medical Ultrasound Analysis: A Review
Liu, S., Wang, Y., Yang, X., Lei, B., Liu, L., Li, S. X., Ni, D., & Wang, T. (2019) · Engineering · doi:10.1016/j.eng.2018.11.020 · Cited by 798 · see citing works
“To address these issues, various conventional machine learning methods such as active contours [127] and deformable templates [128] have been widely used to successfully segment the LV, under the condition of using prior knowledge about the LV shape and appearance.”
MethodSpatio-temporal nonrigid registration for ultrasound cardiac motion estimation
Ledesma‐Carbayo, M. J., Kybic, J., Desco, M., Santos, A., Sühling, M., Hunziker, P., & Unser, M. A. (2005) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2005.852050 · Cited by 290 · see citing works
“the intrinsic complexity of the data by introducing a priori knowledge by modeling a statistical representation of the possible motions and shapes [24], [25].”
BackgroundSnakes based segmentation of the common carotid artery intima media
Loizou, C. P., Pattichis, C. S., Pantziaris, M., Tyllis, T., & Nicolaides, A. N. (2007) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-006-0140-3 · Cited by 227 · see citing works
“The Bland–Altman test was also used in [10] to compare the results of manual and automated detection in myocardial borders, and the segmented border values between manual and automated detection in brachial ultrasound images [28].”
MethodAn electromechanical model of the heart for image analysis and simulation
Maxime Sermesant, B., Delingette, H., & Ayache, N. (2006) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2006.872746 · Cited by 214 · see citing works
“At the same time, deformable templates evolved toward sophisticated approaches, for instance combined with Bayesian classification and Markov random fields [26], or coupling shape-space and Kalman-filter-based tracking [ 27 ].”
MethodCarneiro, G., Nascimento, J. C., & Freitas, A. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2169273 · Cited by 202 · see citing works
Carneiro, G., Georgescu, B., Good, S., & Comaniciu, D. (2008) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2008.928917 · Cited by 205 · see citing works
“Deformable models can also be used with machine learning techniques to learn shape and motion patterns of anatomical structures [17].”
MethodUltrasound image segmentation and tissue characterization
Noble, J. A. (2009) · Proceedings of the Institution of Mechanical Engineers Part H Journal of Engineering in Medicine · doi:10.1243/09544119jeim604 · Cited by 159 · see citing works
A survey of shaped-based registration and segmentation techniques for cardiac images
Tavakoli, V., & Amini, A. A. (2013) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2012.11.017 · Cited by 150 · see citing works
Myocardial motion analysis from B-mode echocardiograms
Sühling, M., Arigovindan, M., Jansen, C. H. P., Hunziker, P., & Unser, M. A. (2005) · IEEE Transactions on Image Processing · doi:10.1109/tip.2004.838709 · Cited by 147 · see citing works
“borders using active contours [4]–[6] or active appearance models [7].”
MethodLempitsky, V., Verhoek, M., Noble, J. A., & Blake, A. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-01932-6_48 · Cited by 124 · see citing works
“Myocardial segmentation has been performed [ 12 ] by first finding the endocardium in 2D+T echocardiographic slices, then locating the epicardium by searching outward along normals to the endocardium, using PCA shape and motion models.”
MethodCarneiro, G., & Nascimento, J. C. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.96 · Cited by 122 · see citing works
“Below, we review the foremost ideas in this field of research, followed by our contributions.”
BackgroundAn information fusion framework for robust shape tracking
Zhou, X. S., Gupta, A. K., & Comaniciu, D. (2004) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.3 · Cited by 112 · see citing works
“The second approach is the same tracker but adding orthogonal PCA shape model constraints, which represents the current approaches [29], [19], [9] (“ShapeSpace”).”
BackgroundMethodInfluentialRobust Real-Time Myocardial Border Tracking for Echocardiography: An Information Fusion Approach
Comaniciu, D., Zhou, X. S., & Krishnan, S. (2004) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2004.827967 · Cited by 112 · see citing works
“The analysis is based on the vectors formed by concatenating the coordinates of all control points [10], [19].”
BackgroundMethodInfluentialTee, M., Noble, J. A., & Bluemke, D. A. (2013) · Expert Review of Cardiovascular Therapy · doi:10.1586/erc.12.182 · Cited by 96 · see citing works
Contour tracking in echocardiographic sequences via sparse representation and dictionary learning
Huang, X., Dione, D. P., Compas, C. B., Papademetris, X., Lin, B. A., Bregasi, A., Sinusas, A. J., Staib, L. H., & Duncan, J. S. (2013) · Medical Image Analysis · doi:10.1016/j.media.2013.10.012 · Cited by 94 · see citing works
Extraction of Left Ventricular Contours From Left Ventriculograms by Means of a Neural Edge Detector
Suzuki, K., Horiba, I., Sugie, N., & Nanki, M. (2004) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2004.824238 · Cited by 93 · see citing works
Xu, L., Liu, M., Shen, Z., Wang, H., Liu, X., Wang, X., Wang, S., Li, T., Yu, S., Hou, M., et al. (2020) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2019.101690 · Cited by 87 · see citing works
A dynamic elastic model for segmentation and tracking of the heart in MR image sequences
Schaerer, J., Casta, C., Pousin, J., & Clarysse, P. (2010) · Medical Image Analysis · doi:10.1016/j.media.2010.05.009 · Cited by 85 · see citing works
“Jacob et al. (2002) proposed a semi-automatic method for quantifying regional heart function from two-dimensional echocardiography.”
MethodGonzález, B., Valdez, F., Melín, P., & Prado-Arechiga, G. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.03.034 · Cited by 84 · see citing works
Registration-assisted segmentation of real-time 3-D echocardiographic data using deformable models
Zagrodsky, V., Walimbe, V., Castro‐Pareja, C. R., Qin, J. X., Song, J., & Shekhar, R. (2005) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2005.852057 · Cited by 79 · see citing works
“Due to the inherently noisy nature and peculiarities in the intensity pattern of ultrasound images, an accurate initialization is critical even for other LV segmentation approaches [6], [7].”
BackgroundAdaptively Learning Local Shape Statistics for Prostate Segmentation in Ultrasound
Yan, P., Xu, S. Y., Türkbey, B., & Kruecker, J. (2010) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2010.2094195 · Cited by 73 · see citing works
“Dynamic shape priors have been used in previous works for segmenting and tracking the left ventricle in cardiac images [18]–[20].”
MethodZhao, M., Yang, W., Lu, Y., & Wong, K. K. L. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105623 · Cited by 69 · see citing works
Real-time 3D segmentation of the left ventricle using deformable subdivision surfaces
Orderud, F., & Rabben, S. I. (2008) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2008.4587442 · Cited by 68 · see citing works
“Real-time segmentation at a rate of 25 frames per second consumed a CPU load of 8%.”
Zhu, Y. H., Papademetris, X., Sinusas, A. J., & Duncan, J. S. (2010) · Medical Image Analysis · doi:10.1016/j.media.2010.02.005 · Cited by 63 · see citing works
“presented a Kalman filter-based algorithm to track two-dimensional (2-D) endocardial (ENDO) and epicardial (EPI) borders (Jacob et al., 2002).”
BackgroundMethodZhu, X., Wei, Y., Lu, Y., Zhao, M., Yang, K., Wu, S., Zhang, H., & Wong, K. K. L. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105914 · Cited by 61 · see citing works
Early myocardial infarction detection over multi-view echocardiography
Degerli, A., Serkan Kiranyaz, B., Hamid, T., Mazhar, R., & Gabbouj, M. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105448 · Cited by 58 · see citing works
“The number of neighbors is determined in [5, 30] with a gap of 5 increasing at each step, the metric used for computing the distances between neighbors are Manhattan and Euclidean, and the scoring parameters are selected as the performance metric with the highest scoring value.”
BackgroundMethodGifani, P., Behnam, H., Shalbaf, A., & Sani, Z. A. (2010) · Physiological Measurement · doi:10.1088/0967-3334/31/9/002 · Cited by 58 · see citing works
“A number of features that have been developed to characterize cardiac motion abnormalities are based on detection of the end of the left ventricular systole and end-diastole frames of echocardiography image sequences (Jacob et al 2001, 2002, Barcaro et al 2008, Giachetti 1998, Beymer et al 2009).”
BackgroundRajpoot, K., Grau, V., Noble, J. A., Becher, H. H., & Szmigielski, C. A. (2011) · Medical Image Analysis · doi:10.1016/j.media.2011.02.007 · Cited by 56 · see citing works
Heyde, B., Cygan, S., Choi, H. F., Leśniak-Plewińska, B., Barbosa, D. C., Elen, A., Claus, P., Loeckx, D., Kałużyński, K., & D’hooge, J. (2012) · IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control · doi:10.1109/tuffc.2012.2245 · Cited by 55 · see citing works
“one approach consists of segmenting and tracking myocardial borders using active contours [11], active shape models [12] or active appearance motion models [13].”
MethodUltrasonic image analysis and image-guided interventions
Noble, J. A., Navab, N., & Becher, H. H. (2011) · Interface Focus · doi:10.1098/rsfs.2011.0025 · Cited by 53 · see citing works
A coarse-to-fine deformable contour optimization framework
Akgül, Y. S., & Kambhamettu, C. (2003) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2003.1177150 · Cited by 48 · see citing works
“The tracked heart wall contours can be directly used to estimate the heart functions or they can be used in further analysis such as estimation of wall-excursions or wall-thickening as performed in Jacob et al. [ 20 ].”
MethodGastounioti, A., Golemati, S., Stoitsis, J. S., & Nikita, K. S. (2011) · Measurement Science and Technology · doi:10.1088/0957-0233/22/11/114008 · Cited by 45 · see citing works
“Moreover, KF has been implemented to recursively predict and update contour deformations in real time, aiming at automatic tracking of myocardial borders in two-dimensional [10, 11] or threedimensional [12] echocardiography.”
MethodGe, R., Yang, G., Chen, Y., Luo, L., Feng, C., Zhang, H., & Li, S. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101554 · Cited by 45 · see citing works
Image filtering techniques for medical image post-processing: an overview
Behrenbruch, C. P., Petroudi, S., Bond, S., Declerck, J. D., Leong, F. J. W.-M., & Brady, J. M. (2004) · British Journal of Radiology · doi:10.1259/bjr/17464219 · Cited by 43 · see citing works
“A good example is cardiac ultrasound where endocardial and epicardial wall motion can be used to highlight ischaemic regions of the heart [19, 20].”
BackgroundMethodReal-Time Tracking of the Left Ventricle in 3D Echocardiography Using a State Estimation Approach
Orderud, F., Hansgård, J., & Rabben, S. I. (2007) · Springer eBooks · doi:10.1007/978-3-540-75757-3_104 · Cited by 39 · see citing works
González, B. G., Valdez, F., Melín, P., & Prado-Arechiga, G. (2015) · Applied Soft Computing · doi:10.1016/j.asoc.2015.08.034 · Cited by 35 · see citing works
Classification and segmentation of intracardiac masses in cardiac tumor echocardiograms
Strzelecki, M., Materka, A., Dróżdż, J., Krzemińska‐Pakuła, M., & Kasprzak, J. D. (2006) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2005.11.004 · Cited by 35 · see citing works
Ni, B., He, F., & Yuan, Z. (2015) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2015.07.004 · Cited by 34 · see citing works
Echocardiography Image Segmentation: A Survey
Mazaheri, S., Sulaiman, P. S., Rahmat, R. W. O. K., Khalid, F., Kadiman, S., Dimon, M. Z., & Tayebi, R. M. (2013) · International Conference on Advanced Computer Science Applications and Technologies · doi:10.1109/acsat.2013.71 · Cited by 34 · see citing works
“Several other methods have also been evaluated for this segmentation problem, including artificial neural Networks [57, 58], a fuzzy multi-scale edge detector [59] and a Kalman filter based tracking method [60].”
MethodA Dynamical Shape Prior for LV Segmentation from RT3D Echocardiography
Zhu, Y. H., Papademetris, X., Sinusas, A. J., & Duncan, J. S. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04268-3_26 · Cited by 31 · see citing works
“For example, Jacob et al. proposed a second-order autoregressive model to approximate cardiac dynamics [ 4 ].”
MethodDominguez, C. R., Kachenoura, N., Cesare, A. D., Delouche, A., Lim, P., Gérard, O., Herment, A., Diébold, B., & Frouin, F. (2005) · Physics in Medicine and Biology · doi:10.1088/0031-9155/50/14/006 · Cited by 30 · see citing works
“A recent study suggests quantifying endocardial excursion and myocardial thickening in a segmental way by the detection of the endocardium and the epicardium during a cardiac cycle ( Jacob et al 2001, 2002 ).”
BackgroundDarvishi, S., Behnam, H., Pouladian, M., & Samiei, N. (2012) · Research in Cardiovascular Medicine · doi:10.5812/cardiovascmed.6397 · Cited by 29 · see citing works
“To typify universal cardiac functions, a significant number of factors have been investigated to measure ES and ED volumes, SV, global EF ratio, CO and wall thickening, all of which are essential parameters to assess heart function (10-14).”
BackgroundEstimation of Large-Scale Organ Motion in B-Mode Ultrasound Image Sequences: A Survey.
Luca, V. D., Székely, G., & Tanner, C. (2015) · Ultrasound in Medicine and Biology · doi:10.1016/j.ultrasmedbio.2015.07.022 · Cited by 23 · see citing works
Boosting and Nonparametric Based Tracking of Tagged MRI Cardiac Boundaries
Qian, Z., Metaxas, D., & Axel, L. (2006) · Lecture notes in computer science · doi:10.1007/11866565_78 · Cited by 26 · see citing works
“In [ 8 , 9] shape-space based or contour-matching based approaches are proposed.”
BackgroundRealtime Automatic Assessment of Cardiac Function in Echocardiography
Storve, S., Grue, J. F., Samstad, S., Dalen, H., Haugen, B. O., & Torp, H. (2016) · IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control · doi:10.1109/tuffc.2016.2518306 · Cited by 23 · see citing works
“Automatic segmentation has previously been used to quantify LV function [9], [10].”
MethodSmistad, E., & Lindseth, F. (2014) · doi:10.54294/x56vmc · Cited by 22 · see citing works
Shalbaf, A., Behnam, H., Sani, Z. A., & Shojaifard, M. (2013) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-012-9543-x · Cited by 21 · see citing works
“Then, several quantitative features are extracted to characterize the RWM of LV [18–26].”
MethodKalman-filter-based block matching for arterial wall motion estimation from B-mode ultrasound
Gastounioti, A., Golemati, S., Stoitsis, J. S., & Nikita, K. S. (2010) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist.2010.5548454 · Cited by 21 · see citing works
“Kalman filtering has also been used in a dynamic contour tracking approach to reinforce the accuracy in tracking the myocardial boundaries from echocardiographic image sequences [8].”
MethodSegmentation of the left heart ventricle in ultrasound images using a region based snake
Landgren, M., Overgaard, N. C., & Heyden, A. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2001284 · Cited by 19 · see citing works
New Techniques for the Assessment of Regional Left Ventricular Wall Motion
Fernández, M. Á. G., Bermejo, J., David, E. P., López‐Fernández, T., Ledesma‐Carbayo, M. J., Caso, P., Malpica, N., Santos, A., Moreno, M., & Desco, M. (2003) · Echocardiography · doi:10.1046/j.1540-8175.2003.t01-1-03036.x · Cited by 19 · see citing works
Deformable multimodal registration for navigation in beating-heart cardiac surgery
Peoples, J., Bisleri, G., & Ellis, R. E. (2019) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-019-01932-2 · Cited by 18 · see citing works
Lu, Y., Fu, X., Li, X., & Qi, Y. (2020) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc44109.2020.9175618 · Cited by 18 · see citing works
“Other well-established segmentation approaches rely on artificial neural networks [9], [10], fuzzy multiscale edge detection [11], and Kalman filter tracking [12].”
MethodLearning-Based Detection and Tracking in Medical Imaging: A Probabilistic Approach
Wang, Y., Georgescu, B., Chen, T., Wu, W. H., Wang, P., Lu, X., Ionasec, R. I., Zheng, Y., & Comaniciu, D. (2012) · Lecture notes in computational vision and biomechanics · doi:10.1007/978-94-007-5446-1_9 · Cited by 18 · see citing works
“(1), the shape vectors are formed by concatenating the coordinates of all control points [8, 19].”
BackgroundLearning Active Shape Models for Bifurcating Contours
Seise, M., McKenna, S. J., Ricketts, I. W., & Wigderowitz, C. A. (2007) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2007.895479 · Cited by 18 · see citing works
“[5] to track the myocardial borders in ultrasound sequences.”
BackgroundTunneling descent for m.a.p. active contours in ultrasound segmentation
TAO, Z., & Tagare, H. D. (2007) · Medical Image Analysis · doi:10.1016/j.media.2006.11.006 · Cited by 18 · see citing works
“Multi-frame spatio-temporal approaches to ultrasound segmentation are reported in Mulet-Parada and Noble (1998), Guofang et al. (2002), Jacob et al. (2002), and Sanchez-Ortiz et al. (2002).”
Deep learning on sparse manifolds for faster object segmentation
Nascimento, J. C., & Carneiro, G. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2725582 · Cited by 17 · see citing works
Fast Segmentation of the Mitral Valve Leaflet in Echocardiography
Martin, S., Daanen, V., Chavanon, O., & Troccaz, J. (2006) · Lecture notes in computer science · doi:10.1007/11889762_20 · Cited by 16 · see citing works
“Data processed are either in 2D+T or 3D+T ([6], [7], [8], [9] [10] ).”
Huang, X., Lin, B. A., Compas, C. B., Sinusas, A. J., Staib, L. H., & Duncan, J. S. (2012) · IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA) · doi:10.1109/mmbia.2012.6164769 · Cited by 16 · see citing works
Nascimento, J. C., & Carneiro, G. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2922959 · Cited by 14 · see citing works
“Deformable templates [20], [21], [22], [23], [24], [25] introduce the use of more specific prior models regarding the shape and appearance of the object.”
BackgroundReal-Time Multi-model Tracking of Myocardium in Echocardiography Using Robust Information Fusion
Georgescu, B., Zhou, X. S., Comaniciu, D., & Rao, B. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-30136-3_95 · Cited by 16 · see citing works
“The analysis is based on vectors formed by concatenating the coordinates of all control points [7, 1].”
MethodLeft ventricle USG image segmentation using active contour model
Skalski, A., Turcza, P., Zieliński, T. P., Królczyk, J., & Grodzicki, T. K. (2010) · Procedia Computer Science · doi:10.1016/j.procs.2010.04.306 · Cited by 16 · see citing works
“[7] proposed dynamic contour tracker which uses Kalman filter.”
BackgroundMethodCardiac disease detection from echocardiogram using edge filtered scale-invariant motion features
Kumar, R., Wang, F., Beymer, D., & Syeda-Mahmood, T. F. (2010) · 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2010.5543599 · Cited by 16 · see citing works
“Due to these issues, the majority of the existing approaches use feature-based methods, where they first segment the myocardial regions [8, 14] and the motion is then recovered by aligning the segmented shapes.”
MethodFast Automatic Measurement of Mitral Annulus Excursion Using a Pocket-Sized Ultrasound System
Snare, S. R., Mjølstad, O. C., Orderud, F., Haugen, B. O., & Torp, H. G. (2011) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2010.12.012 · Cited by 14 · see citing works
Histotripsy Cardiac Therapy System Integrated with Real-Time Motion Correction
Miller, R. M., Kim, Y., Lin, K.-W., Cain, C. A., Owens, G. E., & Xu, Z. (2013) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2013.08.004 · Cited by 14 · see citing works
“These methods include myocardial border segmentation using deformable models (Jacob et al. 2002), myocardial motion and deformation estimation using phase shift estimation (D'hooge et al.”
MethodOptimization of focused ultrasound and image based modeling in image guided interventions
Almekkawy, M. K. (2014) · University of Minnesota Digital Conservancy (University of Minnesota) · Cited by 14 · see citing works
Algorithm Versus Physicians Variability Evaluation in the Cardiac Chambers Extraction
Silva, J. S., Santos, J. B., Roxo, D., Martins, P., Castela, E., & Martins, R. (2012) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2012.2201949 · Cited by 13 · see citing works
Huang, X., Dione, D. P., Compas, C. B., Papademetris, X., Lin, B. A., Sinusas, A. J., & Duncan, J. S. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33454-2_8 · Cited by 12 · see citing works
Shalbaf, A., Behnam, H., Sani, Z. A., & Shojaifard, M. (2012) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-012-0786-2 · Cited by 12 · see citing works
Vallet, B., Angelini, E. D., & Laine, A. F. (2006) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.653692 · Cited by 11 · see citing works
“For numerical implementation, we normalized these basis functions for the 2 L norm using: 2 2 0 1 26 2 = = 35 105 i i f f (10)”
MethodCardiac Structure Recognition in Ultrasound Images
de Siqueira, M. L., Müller, D., & Navaux, P. O. A. (2007) · International Conference on Systems, Signals and Image Processing · doi:10.1109/iwssip.2007.4381141 · Cited by 10 · see citing works
“[8] and Sugioka et al [15] developed research using patterns to detect cardiac structures using active contours (snakes) in echocardiographic images.”
BackgroundAutomatic 3-D Segmentation of Endocardial Border of the Left Ventricle From Ultrasound Images
Santiago, C., Nascimento, J. C., & Marques, J. S. (2014) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2014.2308424 · Cited by 10 · see citing works
“This approach is also applied in [9] in the context of 2D echocardiography.”
MethodLocal maximum likelihood segmentation of echocardiographic images with Rayleigh distribution
Belaid, A., & Djamal Boukerroui, A. (2018) · Signal Image and Video Processing · doi:10.1007/s11760-018-1251-7 · Cited by 10 · see citing works
“The motion constraint can be injected into the segmentation model following several assumptions: for example, assuming a local or global temporal coherence [2,14], assuming a constant velocity [25], or including time explicitly in the optimization process as in [7].”
A semi-automatic system for segmentation of cardiac M-mode images
Bertelli, L., Cucchiara, R., Paternostro, G., & Prati, A. (2006) · Pattern Analysis and Applications · doi:10.1007/s10044-006-0034-x · Cited by 9 · see citing works
“[16] applied snake to 2-D echocardiography that is probably the more challenging type of acquisition because it results in very noisy images and image information is highly anisotropic and position-dependent.”
BackgroundThree-dimensional finite element model for lesion correspondence in breast imaging
Qiu, Y. J., Li, L., Goldgof, D. B., Sarkar, S., Anton, S. A., & Clark, R. A. (2004) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.535719 · Cited by 9 · see citing works
“In [19] the authors used the active contours to track the endocardial and epicardial borders of the left ventricle.”
Bharali, U., & Ghosh, D. (2006) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2006.345402 · Cited by 9 · see citing works
“Reference [ 8 ] presents a method for tracking endocardial and epicardial boundaries using dynamic snake model.”
MethodShalbaf, A., Behnam, H., Sani, Z. A., & Shojaifard, M. (2013) · Medical Physics · doi:10.1118/1.4799840 · Cited by 8 · see citing works
Segmentation Methods of Echocardiography Images for Left Ventricle Boundary Detection
Mazaheri, S., Sulaiman, P. S., Wirza, R., Dimon, M. Z., Khalid, F., & Tayebi, R. M. (2015) · Journal of Computer Science · doi:10.3844/jcssp.2015.957.970 · Cited by 8 · see citing works
“tracking method (Jacob et al., 2002).”
MethodSimultaneous Registration and Modeling of Deformable Shapes
Xiao, J., Georgescu, B., Zhou, X. S., Comaniciu, D., & Takeo Kanade, A. (2006) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2006.280 · Cited by 8 · see citing works
“The previous solutions to the coupled registration and modeling problems generally consist of two separate steps [3, 14, 9, 2].”
BackgroundMethodPairwise Active Appearance Model and Its Application to Echocardiography Tracking
Zhou, S., Shao, J., Georgescu, B., & Comaniciu, D. (2006) · Lecture notes in computer science · doi:10.1007/11866565_90 · Cited by 8 · see citing works
“Echocardiography tracking [4, 5, 6, 7 , 8, 9, 10] is challenging due to severe imaging artifacts.”
BackgroundLocalization of Surgical Instruments in 3D Ultrasound Images
Christian, M., Kybic, M. J., Pascal, R. M., Petr, M., Sequeira, M., Berka, M. P., Cyril, M. A., & Vladim, M. (2007) · Cited by 7 · see citing works
A Gravitational Search Algorithm for Optimization of Modular Neural Networks in Pattern Recognition
González, B., Valdez, F., Melín, P., & Prado-Arechiga, G. (2014) · Studies in computational intelligence · doi:10.1007/978-3-319-10960-2_8 · Cited by 7 · see citing works
“Research in medical imaging is growing on the last years as it is normally a non-invasive method of diagnosis [1, 9].”
BackgroundMethodZhang, Y., Gao, Y., Jiao, J., Li, X., Li, S., & Yang, J. (2014) · Bio-Medical Materials and Engineering · doi:10.3233/bme-141108 · Cited by 6 · see citing works
“At the beginning, “deformable model” based segmentation techniques was used like level set and snake techniques [2,3].”
Fang, W., Chan, K. L., Fu, S., & Krishnan, S. M. (2008) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2008.06.007 · Cited by 6 · see citing works
Orderud, F. (2010) · Cited by 6 · see citing works
Baroni, M., & Barletta, G. (2004) · Annals of Biomedical Engineering · doi:10.1023/b:abme.0000030234.27956.cd · Cited by 6 · see citing works
Automated septum thickness measurement—A Kalman filter approach
Snare, S. R., Mjølstad, O. C., Orderud, F., Dalen, H., & Torp, H. G. (2011) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2011.02.011 · Cited by 6 · see citing works
Shape constraint function for artery tracking in ultrasound images
Paris, A., & Hafiane, A. (2021) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.101970 · Cited by 5 · see citing works
Contour Tracking with a Spatio-Temporal Intensity Moment
Demi, M. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2478438 · Cited by 5 · see citing works
“Index Terms—Contour tracking, edge detection, intensity moments, optical flow Ç”
BackgroundMotion factorization for echocardiogram classification
Wu, H., Huynh, T. T., & Souvenir, R. (2014) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2014.6867904 · Cited by 5 · see citing works
A unified framework for uncertainty propagation in automatic shape tracking
Zhou, X. S., Comaniciu, D., Xie, B., Cruceanu, R., & Gupta, A. K. (2004) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2004.1315123 · Cited by 5 · see citing works
Reconstruction, registration, and modeling of deformable object shapes
Xiao, J., & Takeo Kanade, A. (2005) · Cited by 5 · see citing works
Star algorithm: Detecting the ultrasonic endocardial boundary automatically
Yao, W., Tian, J.-M., Zhao, B., Chen, N., & Qian, G. (2004) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2004.04.011 · Cited by 5 · see citing works
Spatio-temporal motion estimation for disease discrimination in cardiac echo videos
Wang, F., Syeda-Mahmood, T. F., & Beymer, D. (2008) · Computers in cardiology · doi:10.1109/cic.2008.4748992 · Cited by 4 · see citing works
Marsousi, M., Eftekhari, A., Alirezaie, J., Кочарян, А. А., & Sharifahmadian, E. (2009) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2009.5333702 · Cited by 4 · see citing works
“For example, using active contour algorithms, with B-spline snake as a member, involves finding the epicardial boundary at first and using the fitted contour as the initialization to find the endocardial border [3, 4].”
BackgroundMethodEchocardiogram Image Recognition Using Neural Networks
González, B., Valdez, F., Melín, P., & Prado-Arechiga, G. (2014) · Studies in computational intelligence · doi:10.1007/978-3-319-05170-3_29 · Cited by 4 · see citing works
“[2] and Sugioka et al.”
Extraction of Dermo-Epidermal Surface from 3D Volumetric Images of Human Skin
Wang, J., Saitô, H., Ozawa, S., Kuwahara, T., Yamashita, T., & Takahashi, M. (2003) · International Journal of Image and Graphics · doi:10.1142/s0219467803001202 · Cited by 4 · see citing works
Fang, W. P., Chan, K. L., Fu, S., & Krishnan, S. M. (2005) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2005.1616611 · Cited by 4 · see citing works
Segmentation of 4D Echocardiography Using Stochastic Online Dictionary Learning
Huang, X., Dione, D. P., Lin, B. A., Bregasi, A., Sinusas, A. J., & Duncan, J. S. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40760-4_8 · Cited by 3 · see citing works
- Authors
- Jacob, G., Noble, J. A., Behrenbruch, C., Kelion, A. D., & Banning, A. P.
- Affiliations
- University of Oxford (GB)
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2002-03
- Volume
- 21
- Issue
- 3
- Pages
- 226-238
- ISSN
- 0278-0062 (ISSN-L)
- OpenAlex
- W2155831290
- Cited by
- 142
- References
- 53
- Citations by year
- 2024: 2 · 2023: 2 · 2022: 4 · 2021: 1 · 2020: 3 · 2019: 6 · 2018: 1 · 2017: 1 · 2016: 2 · 2015: 6 · 2014: 8 · 2013: 15 · 2012: 10
- FWCI
- 8.62
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Cardiovascular Function and Risk Factors
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Cardiac Imaging and Diagnostics
- Keywords
- shape space, regional left ventricular function, 16-segment model, myocardial wall thickening, two-dimensional echocardiography, myocardial infarction, semi-automatic segmentation
- MeSH terms
- Algorithms, Echocardiography, Elasticity, Heart, Humans, Image Enhancement, Image Interpretation, Computer-Assisted, Models, Cardiovascular, Movement, Myocardial Contraction, Myocardial Infarction, Sensitivity and Specificity, Models, Statistical, Ventricular Dysfunction, Left
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
