Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms

被引:261
作者
Schaap, Michiel [1 ]
Metz, Coert T. [1 ]
van Walsum, Theo [1 ]
van der Giessen, Alina G. [2 ]
Weustink, Annick C. [3 ]
Mollet, Nico R. [3 ]
Bauer, Christian [4 ]
Bogunovic, Hrvoje [5 ,6 ,7 ]
Castro, Carlos [16 ,17 ]
Deng, Xiang [8 ]
Dikici, Engin [9 ]
O'Donnell, Thomas
Frenay, Michel [10 ]
Friman, Ola [11 ]
Hernandez Hoyos, Marcela [12 ]
Kitslaar, Pieter H. [10 ,13 ]
Krissian, Karl [14 ]
Kuehnel, Caroline [11 ]
Luengo-Oroz, Miguel A. [16 ,17 ]
Orkisz, Maciej [15 ]
Smedby, Orjan [18 ]
Styner, Martin [19 ]
Szymczak, Andrzej [20 ]
Tek, Hueseyin [21 ]
Wang, Chunliang [18 ]
Warfield, Simon K. [22 ]
Zambal, Sebastian [23 ]
Zhang, Yong [24 ]
Krestin, Gabriel P. [3 ]
Niessen, Wiro J. [1 ,25 ]
机构
[1] Erasmus MC, Biomed Imaging Grp Rotterdam, Dept Radiol & Med Informat, Rotterdam, Netherlands
[2] Erasmus MC, Dept Biomed Engn, Rotterdam, Netherlands
[3] Erasmus MC, Dept Radiol, Rotterdam, Netherlands
[4] Graz Univ Technol, Inst Comp Graph & Vis, A-8010 Graz, Austria
[5] Ctr Computat Imaging & Simulat Technol Biomed CIS, Barcelona, Spain
[6] Univ Pompeu Fabra, Barcelona, Spain
[7] CIBER BBN, Barcelona, Spain
[8] Siemens Corp Res, Cent Med Imaging Validat, Princeton, NJ USA
[9] Univ Florida, Coll Med, Dept Radiol, Jacksonville, FL USA
[10] Leiden Univ Med Cent, Dept Radiol, Div Image Proc, Leiden, Netherlands
[11] MeVis Res, Bremen, Germany
[12] Univ Los Andes, Grp Imagine, Grp Ingn Biomed, Bogota, Colombia
[13] Medis Med Imaging Syst bv, Leiden, Netherlands
[14] Univ Palmas Gran Canaria, Ctr Tecnol Med, Dept Signal & Com, Las Palmas Of Gc, Spain
[15] Univ Lyon 1, CNRS, INSA Lyon, INSERM,UMR 5220,CREATIS,U630, F-69622 Villeurbanne, France
[16] Univ Politecn Madrid, ETSI Telecomunicac, Biomed Image Technol Lab, Madrid, Spain
[17] Biomed Res Cent Bioengn Biomat & Nanomed CIBER BB, Zaragoza, Spain
[18] Linkoping Univ, Dept Radiol & Cent Med Image Sci & Visualizat, Linkoping, Sweden
[19] Univ N Carolina, Dept Comp Sci & Psychiat, Chapel Hill, NC USA
[20] Colorado Sch Mines, Dept Math & Comp Sci, Golden, CO 80401 USA
[21] Siemens Corp Res, Imaging & Visualizat Dept, Princeton, NJ USA
[22] Childrens Hosp Boston, Dept Radiol, Boston, MA USA
[23] VRVis Res Cent Virtual Real & Visualizat, Vienna, Austria
[24] Methodist Hosp Res Inst, Houston, TX USA
[25] Delft Univ Technol, Fac Sci Appl, Delft, Netherlands
关键词
Standardized evaluation; Centerline extraction; Tracking; Coronaries; Computed tomography; COMPUTED-TOMOGRAPHY; VESSEL SEGMENTATION; RADIATION-EXPOSURE; ANGIOGRAPHY; TREE; RECONSTRUCTION; ACCURACY; TRACKING; IMAGES;
D O I
10.1016/j.media.2009.06.003
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Efficiently obtaining a reliable coronary artery centerline from computed tomography angiography data is relevant in clinical practice. Whereas numerous methods have been presented for this purpose, up to now no standardized evaluation methodology has been published to reliably evaluate and compare the performance of the existing or newly developed coronary artery centerline extraction algorithms. This paper describes a standardized evaluation methodology and reference database for the quantitative evaluation of coronary artery centerline extraction algorithms. The contribution of this work is fourfold: (1) a method is described to create a consensus centerline with multiple observers, (2) well-defined measures are presented for the evaluation of coronary artery centerline extraction algorithms, (3) a database containing 32 cardiac CTA datasets with corresponding reference standard is described and made available. and (4) 13 coronary artery centerline extraction algorithms, implemented by different research groups, are quantitatively evaluated and compared. The presented evaluation framework is made available to the medical imaging community for benchmarking existing or newly developed coronary centerline extraction algorithms. (C) 2009 Elsevier B.V. All rights reserved.
引用
收藏
页码:701 / 714
页数:14
相关论文
共 74 条
[31]  
Larralde A, 2003, LECT NOTES COMPUT SC, V2674, P39
[32]  
Lavi G, 2004, IEEE NUCL SCI CONF R, P3308
[33]   Accuracy of 64-slice computed tomography to classify and quantify plaque volumes in the proximal coronary system - A comparative study using intravascular ultrasound [J].
Leber, AW ;
Becker, A ;
Knez, A ;
von Ziegler, F ;
Sirol, M ;
Nikolaou, K ;
Ohnesorge, B ;
Fayad, ZA ;
Becker, CR ;
Reiser, M ;
Steinbeck, G ;
Boekstegers, P .
JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2006, 47 (03) :672-677
[34]   Medial-based Bayesian tracking for vascular segmentation: Application to coronary arteries in 3D CT angiography [J].
Lesage, David ;
Angelini, Elsa D. ;
Bloch, Isabelle ;
Funka-Lea, Gareth .
2008 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO, VOLS 1-4, 2008, :268-+
[35]   Accuracy of MSCT coronary angiography with 64-slice technology:: first experience [J].
Leschka, S ;
Alkadhi, H ;
Plass, A ;
Desbiolles, L ;
Grünenfelder, J ;
Marincek, B ;
Wildermuth, S .
EUROPEAN HEART JOURNAL, 2005, 26 (15) :1482-1487
[36]   Vessels as 4-d curves: global minimal 4-d paths to extract 3-d tubular surfaces and centerlines [J].
Li, Hua ;
Yezzi, Anthony .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2007, 26 (09) :1213-1223
[37]   Simultaneous segmentation and tree reconstruction of the coronary arteries in MSCT images [J].
Lorenz, C ;
Renisch, S ;
Schlathölter, T ;
Bülow, T .
MEDICAL IMAGING 2003: PHYSIOLOGY AND FUNCTION: METHODS, SYSTEMS, AND APPLICATIONS, 2003, 5031 :167-177
[38]   A comprehensive shape model of the heart [J].
Lorenz, Cristian ;
von Berg, Jens .
MEDICAL IMAGE ANALYSIS, 2006, 10 (04) :657-670
[39]  
Luengo-Oroz MA, 2007, LECT NOTES COMPUT SC, V4466, P424
[40]   Towards quantitative analysis of coronary CTA [J].
Marquering, HA ;
Dijkstra, J ;
de Koning, PJH ;
Stoel, BC ;
Reiber, JHC .
INTERNATIONAL JOURNAL OF CARDIOVASCULAR IMAGING, 2005, 21 (01) :73-84