Standardized evaluation framework for evaluating coronary artery stenosis detection, stenosis quantification and lumen segmentation algorithms in computed tomography angiography

被引：148

作者：

Kirisli, H. A. ^{[1
,2
]}

Schaap, M. ^{[1
]}

Metz, C. T. ^{[1
]}

Dharampal, A. S. ^{[3
,4
]}

Meijboom, W. B. ^{[4
]}

Papadopoulou, S. L. ^{[3
]}

Dedic, A. ^{[4
]}

Nieman, K. ^{[3
,4
]}

de Graaf, M. A. ^{[6
,7
]}

Meijs, M. F. L. ^{[5
]}

Cramer, M. J. ^{[5
]}

Broersen, A. ^{[2
]}

Cetin, S. ^{[12
]}

Eslami, A. ^{[20
,21
]}

Florez-Valencia, L. ^{[16
]}

Lor, K. L. ^{[13
]}

Matuszewski, B. ^{[24
]}

Melki, I. ^{[14
,15
]}

Mohr, B. ^{[11
]}

Oksuz, I. ^{[18
]}

Shahzad, R. ^{[1
,9
]}

Wang, C. ^{[19
]}

Kitslaar, P. H. ^{[2
]}

Unal, G. ^{[12
]}

Katouzian, A. ^{[20
,22
]}

Orkisz, M. ^{[17
]}

Chen, C. M. ^{[13
]}

Precioso, F. ^{[23
]}

Najman, L. ^{[14
]}

Masood, S. ^{[11
]}

Unay, D. ^{[18
]}

Van Vliet, L. ^{[9
]}

Moreno, R. ^{[19
]}

Goldenberg, R. ^{[8
]}

Vucini, E. ^{[10
]}

Krestin, G. P. ^{[3
]}

Niessen, W. J. ^{[1
,9
]}

van Walsum, T. ^{[1
]}

机构：

[1] Erasmus MC, Biomed Imaging Grp Rotterdam, Dept Radiol & Med Informat, Rotterdam, Netherlands

[2] Leiden UMC, Dept Radiol, Div Image Proc, Leiden, Netherlands

[3] Erasmus MC, Dept Radiol, Rotterdam, Netherlands

[4] Erasmus MC, Dept Cardiol, Rotterdam, Netherlands

[5] UMC Utrecht, Dept Cardiol, Utrecht, Netherlands

[6] Leiden UMC, Dept Cardiol, Leiden, Netherlands

[7] Interuniv Cardiol Inst Netherlands, Utrecht, Netherlands

[8] Rcadia Med Imaging, Haifa, Israel

[9] Delft Univ Technol, Fac Sci Appl, Quantitat Imaging Grp, Delft, Netherlands

[10] VRVis Res Ctr Virtual Real & Visualizat, Vienna, Austria

[11] Toshiba Med Visualizat Syst, Edinburgh, Midlothian, Scotland

[12] Sabanci Univ, Fac Engn & Nat Sci, TR-34956 Istanbul, Turkey

[13] Natl Taiwan Univ, Inst Biomed Engn, Taipei 10764, Taiwan

[14] Univ Paris Est, Lab Informat Gaspard Monge, Equipe A3SI, Noisy Le Grand, France

[15] Gen Elect Med Syst Europe, F-78530 Buc, France

[16] Pontificia Univ Javeriana, Dept Ingn Sistemas, Grp Takina, Bogota, Colombia

[17] Univ Lyon, CREATIS, CNRS UMR 5220, INSERM U1044,INSA Lyon, Lyon, France

[18] Bahcesehir Univ, Istanbul, Turkey

[19] Linkoping Univ, Dept Med & Hlth Sci, Ctr Med Imaging Sci & Visualizat, Linkoping, Sweden

[20] Tech Univ Munich, D-80290 Munich, Germany

[21] Helmholtz Zentrum Munich, Inst Biomath & Biometry, Munich, Germany

[22] Columbia Univ, Dept Biomed Engn, New York, NY 10027 USA

[23] Univ Nice Sophia Antipolis, Lab Informat Signal & Syst I3S, Nice Sophia Antipolis, France

[24] Univ Cent Lancashire, Sch Comp Engn & Phys Sci, Preston PR1 2HE, Lancs, England

来源：

MEDICAL IMAGE ANALYSIS | 2013年 / 17卷 / 08期

关键词：

Standardized evaluation framework; Coronary arteries; Computed tomography angiography (CTA); stenoses detection; stenoses quantification; AUTOMATIC DETECTION; CT; DISEASE; PLAQUE;

D O I：

10.1016/j.media.2013.05.007

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Though conventional coronary angiography (CCA) has been the standard of reference for diagnosing coronary artery disease in the past decades, computed tomography angiography (CIA) has rapidly emerged, and is nowadays widely used in clinical practice. Here, we introduce a standardized evaluation framework to reliably evaluate and compare the performance of the algorithms devised to detect and quantify the coronary artery stenoses, and to segment the coronary artery lumen in CIA data. The objective of this evaluation framework is to demonstrate the feasibility of dedicated algorithms to: (I) (semi-)automatically detect and quantify stenosis on CIA, in comparison with quantitative coronary angiography (QCA) and CIA consensus reading, and (2) (semi-)automatically segment the coronary lumen on CIA, in comparison with expert's manual annotation. A database consisting of 48 multicenter multivendor cardiac CIA datasets with corresponding reference standards are described and made available. The algorithms from 11 research groups were quantitatively evaluated and compared. The results show that (1) some of the current stenosis detection/quantification algorithms may be used for triage or as a second-reader in clinical practice, and that (2) automatic lumen segmentation is possible with a precision similar to that obtained by experts. The framework is open for new submissions through the website, at http://coronary.bigr.nl/stenoses/. (C) 2013 Elsevier B.V. All rights reserved.

引用

页码：859 / 876

页数：18

共 55 条

[1] Can CT detect the vulnerable coronary plaque?
Achenbach, Stephan
[J]. INTERNATIONAL JOURNAL OF CARDIOVASCULAR IMAGING, 2008, 24 (03) : 311 - 312
[2] MULTICENTER EVALUATION OF DUAL SOURCE CT CORONARY ANGIOGRAPHY IN PATIENTS WITH INTERMEDIATE LIKELIHOOD OF CORONARY ARTERY STENOSES (MEDIC): ACCURACY FOR THE DETECTION OF INDIVIDUALS WITH SIGNIFICANT CORONARY ARTERY STENOSES
Achenbach, Stephan
Schuhbaeck, Annika
Marwan, Mohamed
Bathina, Ravi
Ovrehus, Kristian
Anders, Katharina
Hoffmann, Udo
Abbara, Suhny
Aulbach, Peter
Ropers, Dieter
Pflederer, Tobias
Becker, Christoph
Berman, Daniel
Hausleiter, Joerg
[J]. JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2012, 59 (13) : E1337 - E1337
[3] [Anonymous], 2012, P MICCAI WORKSH 3D C
[4] Automated computer-aided stenosis detection at coronary CT angiography: initial experience
Arnoldi, Elisabeth
Gebregziabher, Mulugeta
Schoepf, U. Joseph
Goldenberg, Roman
Ramos-Duran, Luis
Zwerner, Peter L.
Nikolaou, Konstantin
Reiser, Maximilian F.
Costello, Philip
Thilo, Christian
[J]. EUROPEAN RADIOLOGY, 2010, 20 (05) : 1160 - 1167
[5] Austen W G, 1975, Circulation, V51, P5
[6] Automated quantification of coronary plaque with computed tomography: comparison with intravascular ultrasound using a dedicated registration algorithm for fusion-based quantification
Boogers, Mark J.
Broersen, Alexander
van Velzen, Joella E.
de Graaf, Fleur R.
El-Naggar, Heba M.
Kitslaar, Pieter H.
Dijkstra, Jouke
Delgado, Victoria
Boersma, Eric
de Roos, Albert
Schuijf, Joanne D.
Schalij, Martin J.
Reiber, Johan H. C.
Bax, Jeroen J.
Jukema, J. Wouter
[J]. EUROPEAN HEART JOURNAL, 2012, 33 (08) : 1007 - 1016
[7] Automated Quantification of Stenosis Severity on 64-Slice CT A Comparison With Quantitative Coronary Angiography
Boogers, Mark J.
Schuijf, Joanne D.
Kitslaar, Pieter H.
van Werkhoven, Jacob M.
de Graaf, Fleur R.
Boersma, Eric
van Velzen, Joella E.
Dijkstra, Jouke
Adame, Isabel M.
Kroft, Lucia J.
de Roos, Albert
Schreur, Joop H. M.
Heijenbrok, Mark W.
Jukema, J. Wouter
Reiber, Johan H. C.
Bax, Jeroen J.
[J]. JACC-CARDIOVASCULAR IMAGING, 2010, 3 (07) : 699 - 709
[8] Assessment of coronary artery disease by cardiac computed tomography - A scientific statement from the American Heart Association committee on cardiovascular imaging and intervention, council on cardiovascular radiology and intervention, and Committee on Cardiac Imaging, Council on Clinical Cardiology
Budoff, Matthew J.
Achenbach, Stephan
Blumenthal, Roger S.
Carr, J. Jeffrey
Goldin, Jonathan G.
Greenland, Philip
Guerci, Alan D.
Lima, Joao A. C.
Rader, Daniel J.
Rubin, Geoffrey D.
Shaw, Leslee J.
Wiegers, Susan E.
[J]. CIRCULATION, 2006, 114 (16) : 1761 - 1791
[9] Cetin S., 2012, P MICCAI WORKSH 3D C
[10] Vessel Tractography Using an Intensity Based Tensor Model With Branch Detection
Cetin, Suheyla
Demir, Ali
Yezzi, Anthony
Degertekin, Muzaffer
Unal, Gozde
[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2013, 32 (02) : 348 - 363

← 1 2 3 4 5 6 →