Overview of the VISCERAL Challenge at ISBI 2015

Müller, Henning (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Göksel, Orcun (ETH Zürich, Switzerland) ; Foncubierta Rodríguez, Antonio (ETH Zürich, Switzerland) ; Jiménez del Toro, Oscar Alfonso (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Langs, Georg (Medical University of Vienna, Austria) ; Weber, Marc André (University of Heidelberg, Germany) ; Menze, Bjoern (Technical University of Munich, Germany) ; Eggel, Ivan (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Gruenberg, Katharina (University of Heidelberg, Germany) ; Winterstein, Marianne (University of Heidelberg, Germany) ; Holzer, Markus (Medical University of Vienna, Austria) ; Krenn, Markus (Medical University of Vienna, Austria) ; Kontokotsios, Georgios (Vienna University of Technology, Austria) ; Metallidis, Sokratis (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Schaer, Roger (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Taha, Abdel Aziz (Vienna University of Technology, Austria) ; Jakab, András (Medical University of Vienna, Austria) ; Fernández, Tomas Salas (AQuAS, Spain) ; Hanbury, Allan (Vienna University of Technology, Austria)

This is an overview paper describing the data and evaluation scheme of the VISCERAL Segmentation Challenge at ISBI 2015. The challenge was organized on a cloud-based virtual- machine environment, where each participant could develop and submit their algorithms. The dataset contains up to 20 anatomical structures annotated in a training and a test set consisting of CT and MR images with and without contrast enhancement. The test-set is not accessible to participants, and the organizers run the virtual-machines with submitted segmentation methods on the test data. The results of the evaluation are then presented to the participant, who can opt to make it public on the challenge leaderboard displaying 20 segmentation quality metrics per-organ and permodality. Dice coefficient and mean-surface distance are presented herein as representative quality metrics. As a continuous evaluation platform, our segmentation challenge leaderboard will be open beyond the duration of the VISCERAL project.


Conference Type:
full paper
Faculty:
Economie et Services
School:
HEG-VS
Institute:
Institut Informatique de gestion
Subject(s):
Informatique
Autres
Publisher:
New York, USA, 16 April 2015
Date:
New York, USA
16 April 2015
2015
Pagination:
6 p.
Published in
Proceedings of the Visual Concept Extraction Challenge in Radiology Anatomy3 Organ Segmentation Challenge co-located with IEEE International Symposium on Biomedical Imaging (VISCERAL@ISBI) 2015
Numeration (vol. no.):
1390
Appears in Collection:



 Record created 2015-11-20, last modified 2018-12-20

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)