TY - JOUR T1 - Comparison and evaluation of methods for liver segmentation from CT datasets JF - IEEE TRANSACTIONS ON MEDICAL IMAGING Y1 - 2009 A1 - Tobias Heimann A1 - Brahm Van Ginneken A1 - Martin A Styner A1 - Yulia Arzhaeva A1 - Volker Aurich A1 - Christian Bauer A1 - Andreas Beck A1 - Christoph Becker A1 - Reinhardt Beichel A1 - György Bekes A1 - Fernando Bello A1 - Gerd Binnig A1 - Horst Bischof A1 - Alexander Bornik A1 - Peter MM Cashman A1 - Ying Chi A1 - Andres Córdova A1 - Benoit M Dawant A1 - Márta Fidrich A1 - Jacob D Furst A1 - Daisuke Furukawa A1 - Lars Grenacher A1 - Joachim Hornegger A1 - Dagmar Kainmüller A1 - Richard I Kitney A1 - Hidefumi Kobatake A1 - Hans Lamecker A1 - Thomas Lange A1 - Jeongjin Lee A1 - Brian Lennon A1 - Rui Li A1 - Senhu Li A1 - Hans-Peter Meinzer A1 - Gábor Németh A1 - Daniela S Raicu A1 - Anne-Mareike Rau A1 - Eva M Van Rikxoort A1 - Mikael Rousson A1 - László Ruskó A1 - Kinda A Saddi A1 - Günter Schmidt A1 - Dieter Seghers A1 - Akinobi Shimizu A1 - Pieter Slagmolen A1 - Erich Sorantin A1 - Grzegorz Soza A1 - Ruchaneewan Susomboon A1 - Jonathan M Waite A1 - Andreas Wimmer A1 - Ivo Wolf AB -

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.

CY - 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 VL - 28 SN - 0278-0062 IS - 8 N1 - ScopusID: 68249121543doi: 10.1109/TMI.2009.2013851 JO - IEEE T MED IMAGING ER -