VISCERAL@ISBI 2014 VISCERAL Organ Segmentation and Landmark Detection Challenge at IEEE International Symposium on Biomedical Imaging 2014 Beijing, China, May 1, 2014 Proceedings Orcun Goksel (Ed.) ⃝ c 2014 for the individual papers by the papers’ authors. Copying permitted only for private and academic purposes. Re-publication of material from this volume requires permission by the copyright owners. Editor’s address: Prof. Dr. Orcun Goksel Swiss Federal Institute of Technology (ETH) Zürich Computer Vision Laboratory Sternwartstrasse 7 8092 Zürich, Switzerland ogoksel@ethz.ch Preface VISCERAL (Visual Concept Extraction Challenge in Radiology) aims to organize series of benchmarks on the processing of large-scale 3D radiology images, by using an innovative cloud-based evaluation approach. While a growing number of benchmark studies compare the performance of algorithms for automated organ segmentation in images with restricted field of views, emphasis on anatom- ical segmentation and landmark localization in images with wide field-of-view (e.g. show- ing entire abdomen, trunk, or the whole body) has been limited. VISCERAL Anatomy2 benchmark series, namely Organ Segmentation and Landmark Detection Benchmarks, aim to address this need. This ISBI VISCERAL Challenge, a part of Anatomy2 series, has been organized on May 1st 2014, within the IEEE International Symposium on Biomedical Imaging (ISBI) in Beijing, China. The challenge participants have submitted segmentation and localization results two weeks before the challenge session, that were evaluated against test data by the organizers with results presented during the challenge session. Each participant presented his method in a 15 minute oral session during the challenge session. Participants also submitted short papers summarizing their specific methodologies that were used to generate their results. This volume contains two parts. The first part consist of one paper authored by the organizers of the challenge, and the second part presents a compilation of the submissions by the challenge participants. We thank the authors for their submissions and the program committee for their hard work. Orcun Goksel On behalf of VISCERAL Consortium 3 Session Chairs Orçun Göksel, Swiss Federal Institute of Technology (ETH) Zürich, Switzerland Bjoern Menze, Munich University of Technology (TUM), Germany VISCERAL Consortium Allan Hanbury, Vienna University of Technology, Austria (coordinator) Henning Müller, University of Applied Sciences Western Switzerland, Switzerland Georg Langs, Medical University of Vienna, Austria Orçun Göksel, ETH Zürich, Switzerland Marc-André Weber, University of Heidelberg, Germany Tomàs Salas Fernandez, Catalan Agency for Health Information, Assessment and Quality, Spain Contributing VISCERAL Team Members Ivan Eggel, University of Applied Sciences Western Switzerland, Switzerland Katharina Grünberg, University of Heidelberg, Germany Markus Holzer, Medical University of Vienna, Austria András Jakab, Medical University of Vienna, Austria Oscar Jiménez, University of Applied Sciences Western Switzerland, Switzerland Georgios Kontokotsios, Vienna University of Technology, Austria Markus Krenn, Medical University of Vienna, Austria Roger Schaer, University of Applied Sciences Western Switzerland, Switzerland Abdel Aziz Taha, Vienna University of Technology, Austria Marianne Winterstein, University of Heidelberg, Germany 4 Contents PART I: Organization and Evaluation VISCERAL – VISual Concept Extraction challenge in RAdioLogy: ISBI 2014 Challenge Organization Oscar Alfonso Jiménez del Toro, Orcun Goksel, Bjoern Menze, Henning Müller, Georg Langs, Marc-André Weber, Ivan Eggel, Katharina Gruenberg, Markus Holzer, András Jakab, Georgios Kontokotsios, Markus Krenn, Tomàs Salas Fernandez, Roger Schaer, Abdel Aziz Taha, Marianne Winterstein, Allan Hanbury 6 PART II: Participant Submissions Rule-Based Ventral Cavity Multi-Organ Automatic Segmentation in CT Scans Assaf B. Spanier, Leo Joskowicz 16 Automatic Liver Segmentation Using Multiple Prior Knowledge Models and Free-Form Deformation Cheng Huang, Xuhui Li, Fucang Jia 22 Automatic Multi-Organ Segmentation Using Fast Model Based Level Set Method and Hierarchical Shape Priors Chunliang Wang, Örjan Smedby 25 Hierarchical Multi-structure Segmentation Guided by Anatomical Correlations Oscar Alfonso Jiménez del Toro, Henning Müller 32 Segmentation and Landmark Localization Based on Multiple Atlases Orcun Goksel, Tobias Gass, Gabor Szekely 37 5