A GENERAL AND BALANCED REGION-BASED METRIC FOR EVALUATING MEDICAL IMAGE SEGMENTATION ALGORITHMS

被引：0

作者：

Cappabianco, Fabio A. M. ^{[1
]}

Ribeiro, Pedro F. O. ^{[1
]}

de Miranda, Paulo A. V. ^{[2
]}

Udupa, Jayaram K. ^{[3
]}

机构：

[1] Univ Fed Sao Paulo, ICT, GIBIS, Sao J Campos, SP, Brazil

[2] Univ Sao Paulo, IME, Sao Paulo, SP, Brazil

[3] Univ Penn, Dept Radiol, Philadelphia, PA 19104 USA

来源：

2019 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2019年

基金：

巴西圣保罗研究基金会;

关键词：

Dice coefficient; Jaccard coefficient; image segmentation; image evaluation;

D O I：

10.1109/icip.2019.8803083

中图分类号：

TB8 [摄影技术];

学科分类号：

0804 ;

摘要：

Evaluating medical imaging segmentation is a very complex problem. Several papers proposed methodologies and different metrics pursuing more reliable and unbiased procedures. In this paper, we propose a novel accuracy metric which is more balanced than the well known Dice and Jaccard coefficients. We also prove mathematically that the proposed metric generalizes Dice, Jaccard and the previously proposed Balanced Dice and Balanced Jaccard coefficients. Our experiments show that significant changes in brain tissue segmentation evaluation results are noticed as we applied our new metric.

引用

页码：1525 / 1529

页数：5

共 17 条

[1] The impact of skull-stripping and radio-frequency bins correction on grey-matter segmentation for voxel-based morphometry [J].

Acosta-Cabronero, Julio ;

Williams, Guy B. ;

Pereira, Joao M. S. ;

Pengas, George ;

Nestor, Peter J. .

NEUROIMAGE, 2008, 39 (04) :1654-1665

[2] Adaptive Markov modeling for mutual-information-based, unsupervised MRI brain-tissue classification [J].

Awate, Suyash P. ;

Tasdizen, Tolga ;

Foster, Norman ;

Whitaker, Ross T. .

MEDICAL IMAGE ANALYSIS, 2006, 10 (05) :726-739

[3]

Cappabianco F. A. M., 2012, 2012 XXV SIBGRAPI - Conference on Graphics, Patterns and Images (SIBGRAPI 2012), P1, DOI 10.1109/SIBGRAPI.2012.10

[4]

Cappabianco FAM, 2017, IEEE IMAGE PROC, P3894, DOI 10.1109/ICIP.2017.8297012

[5] Brain tissue MR-image segmentation via optimum-path forest clustering [J].

Cappabianco, Fabio A. M. ;

Falcao, Alexandre X. ;

Yasuda, Clarissa L. ;

Udupa, Jayaram K. .

COMPUTER VISION AND IMAGE UNDERSTANDING, 2012, 116 (10) :1047-1059

[6] MEASURES OF THE AMOUNT OF ECOLOGIC ASSOCIATION BETWEEN SPECIES [J].

DICE, LR .

ECOLOGY, 1945, 26 (03) :297-302

[7] Quantitative evaluation of automated skull-stripping methods applied to contemporary and legacy images: Effects of diagnosis, bias correction, and slice location [J].

Fennema-Notestine, C ;

Ozyurt, IB ;

Clark, CP ;

Morris, S ;

Bischoff-Grethe, A ;

Bondi, MW ;

Jernigan, TL ;

Fischl, B ;

Segonne, F ;

Shattuck, DW ;

Leahy, RM ;

Rex, DE ;

Toga, AW ;

Zou, KH ;

Birn, M ;

Brown, GG .

HUMAN BRAIN MAPPING, 2006, 27 (02) :99-113

[8] Measuring agreement in medical informatics reliability studies [J].

Hripcsak, G ;

Heitjan, DF .

JOURNAL OF BIOMEDICAL INFORMATICS, 2002, 35 (02) :99-110

[9] COMPARING IMAGES USING THE HAUSDORFF DISTANCE [J].

HUTTENLOCHER, DP ;

KLANDERMAN, GA ;

RUCKLIDGE, WJ .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1993, 15 (09) :850-863

[10]

Jaccard P., 1901, Bulletin del la Societe Vaudoise des Sciences Naturelles, V37, P547, DOI [DOI 10.5169/SEALS-266450, 10.5169/seals-266450]

← 1 2 →