TY - JOUR
T1 - Standardized evaluation methodology and reference database for evaluating IVUS image segmentation
AU - Balocco, Simone
AU - Gatta, Carlo
AU - Ciompi, Francesco
AU - Wahle, Andreas
AU - Radeva, Petia
AU - Carlier, Stephane
AU - Unal, Gozde
AU - Sanidas, Elias
AU - Mauri, Josepa
AU - Carillo, Xavier
AU - Kovarnik, Tomas
AU - Wang, Ching Wei
AU - Chen, Hsiang Chou
AU - Exarchos, Themis P.
AU - Fotiadis, Dimitrios I.
AU - Destrempes, François
AU - Cloutier, Guy
AU - Pujol, Oriol
AU - Alberti, Marina
AU - Mendizabal-Ruiz, E. Gerardo
AU - Rivera, Mariano
AU - Aksoy, Timur
AU - Downe, Richard W.
AU - Kakadiaris, Ioannis A.
N1 - Funding Information:
Ioannis A. Kakadiaris is Hugh Roy and Lillie Cranz Cullen University Professor of Computer Science, Electrical & Computer Engineering, and Biomedical Engineering at UH. His research interests include computer vision, pattern recognition, biomedical image analysis, and biometrics. Dr. Kakadiaris is the recipient of a number of awards, including the NSF Early Career Development Award, Schlumberger Technical Foundation Award, UH Computer Science Research Excellence Award, UH Enron Teaching Excellence Award, and the James Muller Vulnerable Plaque Young Investigator Prize. His research has been featured on The Discovery Channel, National Public Radio, KPRC NBC News, KTRH ABC News, and KHOU CBS News.
Funding Information:
T. P. E. and D. I. F. are partially funded by ARTREAT , FP7-224297. G.C. and F.D. are partially funded by MDEIE, Canada ; Boston Scientific, Fremont, CA, USA ; NSERC (grant # 138570 ). B.S., F.C. and M.A. are partially funded by TIN2009-14404-C02; TIN2012-38187-C03-01; Boston Scientific, USA and SGR00696. C. G. is supported by MICINN (Ramon y Cajal Grant) . The work of C. W. W. and H. C. C. is partially funded by NSC , 101-2628-E-011-006-MY3 . A.W. and R.W.D.: National Institutes of Health, U.S.A. (R01EB004640, R01HL063373). T.K.: Czech Ministry of Health, Czech Republic (IGA NR9214-3). E. G. M. was supported by CONACYT. I. A. K. was partially supported by NSF Grant DMS-0915242 and the UH Hugh Roy and Lillie Cranz Cullen Endowment Fund.
PY - 2014/3
Y1 - 2014/3
N2 - This paper describes an evaluation framework that allows a standardized and quantitative comparison of IVUS lumen and media segmentation algorithms. This framework has been introduced at the MICCAI 2011 Computing and Visualization for (Intra)Vascular Imaging (CVII) workshop, comparing the results of eight teams that participated.We describe the available data-base comprising of multi-center, multi-vendor and multi-frequency IVUS datasets, their acquisition, the creation of the reference standard and the evaluation measures. The approaches address segmentation of the lumen, the media, or both borders; semi- or fully-automatic operation; and 2-D vs. 3-D methodology. Three performance measures for quantitative analysis have been proposed. The results of the evaluation indicate that segmentation of the vessel lumen and media is possible with an accuracy that is comparable to manual annotation when semi-automatic methods are used, as well as encouraging results can be obtained also in case of fully-automatic segmentation. The analysis performed in this paper also highlights the challenges in IVUS segmentation that remains to be solved.
AB - This paper describes an evaluation framework that allows a standardized and quantitative comparison of IVUS lumen and media segmentation algorithms. This framework has been introduced at the MICCAI 2011 Computing and Visualization for (Intra)Vascular Imaging (CVII) workshop, comparing the results of eight teams that participated.We describe the available data-base comprising of multi-center, multi-vendor and multi-frequency IVUS datasets, their acquisition, the creation of the reference standard and the evaluation measures. The approaches address segmentation of the lumen, the media, or both borders; semi- or fully-automatic operation; and 2-D vs. 3-D methodology. Three performance measures for quantitative analysis have been proposed. The results of the evaluation indicate that segmentation of the vessel lumen and media is possible with an accuracy that is comparable to manual annotation when semi-automatic methods are used, as well as encouraging results can be obtained also in case of fully-automatic segmentation. The analysis performed in this paper also highlights the challenges in IVUS segmentation that remains to be solved.
KW - Algorithm comparison
KW - Evaluation framework
KW - IVUS (intravascular ultrasound)
KW - Image segmentation
UR - http://www.scopus.com/inward/record.url?scp=84895070065&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84895070065&partnerID=8YFLogxK
U2 - 10.1016/j.compmedimag.2013.07.001
DO - 10.1016/j.compmedimag.2013.07.001
M3 - Article
C2 - 24012215
AN - SCOPUS:84895070065
VL - 38
SP - 70
EP - 90
JO - Computerized Medical Imaging and Graphics
JF - Computerized Medical Imaging and Graphics
SN - 0895-6111
IS - 2
ER -