03870nas a2200733 4500008004100000020001400041245008100055210006900136260027000205300001600475490000700491520149600498100002001994700002402014700002202038700002002060700001902080700002102099700001802120700002202138700002302160700001902183700002002202700001702222700001902239700002202258700002302280700001402303700002102317700002202338700002002360700002002380700002202400700002002422700002302442700002402465700002302489700002302512700001902535700001802554700001802572700001802590700001202608700001402620700002402634700002002658700002202678700002202700700002502722700002002747700002102767700002002788700002102808700002002829700002102849700002202870700002002892700001902912700002702931700002302958700002002981700001403001856012103015 2009 eng d a0278-006200aComparison and evaluation of methods for liver segmentation from CT datasets0 aComparison and evaluation of methods for liver segmentation from aPrice, K., Anything you can do, I can do better (no you can't) (1986) Comput. Vis. Graph. Image Process, 36 (2-3), pp. 387-391;S. G. Armato, G. McLennan, M. F. McNitt-Gray, C. R. Meyer, D. Yankelevitz, D. R. Aberle, C. I. Henschke, E. A. Hoffman, E. A. KacAug 2009 a1251 - 12650 v283 a
This paper presents a comparison study between 10 automatic and six interactive methods for liver segmentation from contrast-enhanced CT images. It is based on results from the "MICCAI 2007 Grand Challenge" workshop, where 16 teams evaluated their algorithms on a common database. A collection of 20 clinical images with reference segmentations was provided to train and tune algorithms in advance. Participants were also allowed to use additional proprietary training data for that purpose. All teams then had to apply their methods to 10 test datasets and submit the obtained results. Employed algorithms include statistical shape models, atlas registration, level-sets, graph-cuts and rule-based systems. All results were compared to reference segmentations five error measures that highlight different aspects of segmentation accuracy. All measures were combined according to a specific scoring system relating the obtained values to human expert variability. In general, interactive methods reached higher average scores than automatic approaches and featured a better consistency of segmentation quality. However, the best automatic methods (mainly based on statistical shape models with some additional free deformation) could compete well on the majority of test images. The study provides an insight in performance of different segmentation approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques. © 2009 IEEE.
1 aHeimann, Tobias1 aVan Ginneken, Brahm1 aStyner, Martin, A1 aArzhaeva, Yulia1 aAurich, Volker1 aBauer, Christian1 aBeck, Andreas1 aBecker, Christoph1 aBeichel, Reinhardt1 aBekes, György1 aBello, Fernando1 aBinnig, Gerd1 aBischof, Horst1 aBornik, Alexander1 aCashman, Peter, MM1 aChi, Ying1 aCórdova, Andres1 aDawant, Benoit, M1 aFidrich, Márta1 aFurst, Jacob, D1 aFurukawa, Daisuke1 aGrenacher, Lars1 aHornegger, Joachim1 aKainmüller, Dagmar1 aKitney, Richard, I1 aKobatake, Hidefumi1 aLamecker, Hans1 aLange, Thomas1 aLee, Jeongjin1 aLennon, Brian1 aLi, Rui1 aLi, Senhu1 aMeinzer, Hans-Peter1 aNémeth, Gábor1 aRaicu, Daniela, S1 aRau, Anne-Mareike1 aVan Rikxoort, Eva, M1 aRousson, Mikael1 aRuskó, László1 aSaddi, Kinda, A1 aSchmidt, Günter1 aSeghers, Dieter1 aShimizu, Akinobi1 aSlagmolen, Pieter1 aSorantin, Erich1 aSoza, Grzegorz1 aSusomboon, Ruchaneewan1 aWaite, Jonathan, M1 aWimmer, Andreas1 aWolf, Ivo uhttps://www.inf.u-szeged.hu/publication/comparison-and-evaluation-of-methods-for-liver-segmentation-from-ct-datasets