%0 Journal Article %J IEEE TRANSACTIONS ON MEDICAL IMAGING %D 2009 %T Comparison and evaluation of methods for liver segmentation from CT datasets %A Tobias Heimann %A Brahm Van Ginneken %A Martin A Styner %A Yulia Arzhaeva %A Volker Aurich %A Christian Bauer %A Andreas Beck %A Christoph Becker %A Reinhardt Beichel %A György Bekes %A Fernando Bello %A Gerd Binnig %A Horst Bischof %A Alexander Bornik %A Peter MM Cashman %A Ying Chi %A Andres Córdova %A Benoit M Dawant %A Márta Fidrich %A Jacob D Furst %A Daisuke Furukawa %A Lars Grenacher %A Joachim Hornegger %A Dagmar Kainmüller %A Richard I Kitney %A Hidefumi Kobatake %A Hans Lamecker %A Thomas Lange %A Jeongjin Lee %A Brian Lennon %A Rui Li %A Senhu Li %A Hans-Peter Meinzer %A Gábor Németh %A Daniela S Raicu %A Anne-Mareike Rau %A Eva M Van Rikxoort %A Mikael Rousson %A László Ruskó %A Kinda A Saddi %A Günter Schmidt %A Dieter Seghers %A Akinobi Shimizu %A Pieter Slagmolen %A Erich Sorantin %A Grzegorz Soza %A Ruchaneewan Susomboon %A Jonathan M Waite %A Andreas Wimmer %A Ivo Wolf %X

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.

%B IEEE TRANSACTIONS ON MEDICAL IMAGING %C Price, 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. Ka %V 28 %P 1251 - 1265 %8 Aug 2009 %@ 0278-0062 %G eng %N 8 %9 Journal article %! IEEE T MED IMAGING %R 10.1109/TMI.2009.2013851