Helmholtz Gemeinschaft


Comparison and evaluation of methods for liver segmentation from CT datasets

Item Type:Article
Title:Comparison and evaluation of methods for liver segmentation from CT datasets
Creators Name:Heimann, T. and van Ginneken, B. and Styner, M.A. and Arzhaeva, Y. and Aurich, V. and Bauer, C. and Beck, A. and Becker, C. and Beichel, R. and Bekes, G. and Bello, F. and Binnig, G. and Bischof, H. and Bornik, A. and Cashman, P.M.M. and Chi, Y. and Cordova, A. and Dawant, B.M. and Fidrich, M. and Furst, J.D. and Furukawa, D. and Grenacher, L. and Hornegger, J. and Kainmüller, D. and Kitney, R.I. and Kobatake, H. and Lamecker, H. and Lange, T. and Lee, J. and Lennon, B. and Li, R. and Li, S. and Meinzer, H.P. and Nemeth, G. and Raicu, D.S. and Rau, A.M. and van Rikxoort, E.M. and Rousson, M. and Rusko, L. and Saddi, K.A. and Schmidt, G. and Seghers, D. and Shimizu, A. and Slagmolen, P. and Sorantin, E. and Soza, G. and Susomboon, R. and Waite, J.M. and Wimmer, A. and Wolf, I.
Abstract: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.
Keywords:Evaluation, Liver, Segmentation
Source:IEEE Transactions on Medical Imaging
Publisher:Institute of Electrical and Electronics Engineers
Page Range:1251-1265
Date:August 2009
Official Publication:https://doi.org/10.1109/TMI.2009.2013851
PubMed:View item in PubMed

Repository Staff Only: item control page

Open Access
MDC Library