Heimann Tobias, van Ginneken Bram, Styner Martin A, Arzhaeva Yulia, Aurich Volker, Bauer Christian, Beck Andreas, Becker Christoph, Beichel Reinhard, Bekes György, Bello Fernando, Binnig Gerd, Bischof Horst, Bornik Alexander, Cashman Peter M M, Chi Ying, Cordova Andrés, Dawant Benoit M, Fidrich Márta, Furst Jacob D, Furukawa Daisuke, Grenacher Lars, Hornegger Joachim, Kainmüller Dagmar, Kitney Richard I, Kobatake Hidefumi, Lamecker Hans, Lange Thomas, Lee Jeongjin, Lennon Brian, Li Rui, Li Senhu, Meinzer Hans-Peter, Nemeth Gábor, Raicu Daniela S, Rau Anne-Mareike, van Rikxoort Eva M, Rousson Mikaël, Rusko László, Saddi Kinda A, Schmidt Günter, Seghers Dieter, Shimizu Akinobu, Slagmolen Pieter, Sorantin Erich, Soza Grzegorz, Susomboon Ruchaneewan, Waite Jonathan M, Wimmer Andreas, Wolf Ivo
Division of Medical and Biological Informatics, German Cancer Research Center, 69121 Heidelberg, Germany.
IEEE Trans Med Imaging. 2009 Aug;28(8):1251-65. doi: 10.1109/TMI.2009.2013851. Epub 2009 Feb 10.
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.
本文介绍了对10种自动方法和6种交互式方法进行的比较研究，这些方法用于从增强CT图像中分割肝脏。该研究基于“MICCAI 2007挑战赛”研讨会的结果，在该研讨会上，16个团队在一个公共数据库上评估了他们的算法。预先提供了一组带有参考分割的20幅临床图像，用于训练和调整算法。参与者也被允许为此目的使用额外的专有训练数据。然后，所有团队都必须将他们的方法应用于10个测试数据集并提交所得结果。所采用的算法包括统计形状模型、图谱配准、水平集、图割和基于规则的系统。所有结果都与参考分割进行了比较，采用了五种误差度量，这些度量突出了分割准确性的不同方面。所有度量都根据一个特定的评分系统进行组合，该系统将所得值与人类专家的变异性联系起来。总体而言，交互式方法的平均得分高于自动方法，并且分割质量的一致性更好。然而，最好的自动方法（主要基于带有一些额外自由变形的统计形状模型）在大多数测试图像上能够很好地竞争。该研究深入了解了不同分割方法在实际条件下的性能，并突出了当前图像分析技术的成就和局限性。
