Cloud-Based Evaluation of Anatomical Structure Segmentation and Landmark Detection Algorithms: VISCERAL Anatomy Benchmarks
Artikel i vetenskaplig tidskrift, 2016

Variations in the shape and appearance of anatomical structures in medical images are often relevant radiological signs of disease. Automatic tools can help automate parts of this manual process. A cloud-based evaluation framework is presented in this paper including results of benchmarking current state-of-the-art medical imaging algorithms for anatomical structure segmentation and landmark detection: the VISCERAL Anatomy benchmarks. The algorithms are implemented in virtual machines in the cloud where participants can only access the training data and can be run privately by the benchmark administrators to objectively compare their performance in an unseen common test set. Overall, 120 computed tomography and magnetic resonance patient volumes were manually annotated to create a standard Gold Corpus containing a total of 1295 structures and 1760 landmarks. Ten participants contributed with automatic algorithms for the organ segmentation task, and three for the landmark localization task. Different algorithms obtained the best scores in the four available imaging modalities and for subsets of anatomical structures. The annotation framework, resulting data set, evaluation setup, results and performance analysis from the three VISCERAL Anatomy benchmarks are presented in this article. Both the VISCERAL data set and Silver Corpus generated with the fusion of the participant algorithms on a larger set of non-manually-annotated medical images are available to the research community.

Evaluation framework

landmark detection

organ segmentation

Författare

Oscar Jimenez-Del-Toro

Hopitaux universitaires de Geneve

Haute Ecole Specialisee de Suisse occidentale

Henning Muller

Haute Ecole Specialisee de Suisse occidentale

Hopitaux universitaires de Geneve

Markus Krenn

Medizinische Universität Wien

Katharina Gruenberg

Universitätsklinikum Heidelberg

Abdel Aziz Taha

Technische Universität Wien

Marianne Winterstein

Universitätsklinikum Heidelberg

Ivan Eggel

Haute Ecole Specialisee de Suisse occidentale

Antonio Foncubierta-Rodriguez

Eidgenössische Technische Hochschule Zürich (ETH)

Orcun Goksel

Eidgenössische Technische Hochschule Zürich (ETH)

Andras Jakab

Medizinische Universität Wien

Georgios Kontokotsios

Technische Universität Wien

Georg Langs

Medizinische Universität Wien

Bjoern H. Menze

Eidgenössische Technische Hochschule Zürich (ETH)

Tomas Salas Fernandez

Eidgenössische Technische Hochschule Zürich (ETH)

Agency for Health Quality and Assessment of Catalonia

Roger Schaer

Haute Ecole Specialisee de Suisse occidentale

Anna Walleyo

Universitätsklinikum Heidelberg

Marc Andre Weber

Universitätsklinikum Heidelberg

Yashin Dicente Cid

Haute Ecole Specialisee de Suisse occidentale

Hopitaux universitaires de Geneve

Tobias Gass

Eidgenössische Technische Hochschule Zürich (ETH)

Mattias Heinrich

Universitaet Zu Lübeck

Fucang Jia

Chinese Academy of Sciences

Fredrik Kahl

Chalmers, Signaler och system, Signalbehandling och medicinsk teknik

Razmig Kechichian

Université de Lyon

Dominic Mai

Albert-Ludwigs-Universität Freiburg

Assaf B. Spanier

The Hebrew University Of Jerusalem

Graham Vincent

Imorphics Ltd

C. L. Wang

Kungliga Tekniska Högskolan (KTH)

Daniel Wyeth

Toshiba Medical Visualization Systems Europe

Allan Hanbury

Technische Universität Wien

IEEE Transactions on Medical Imaging

0278-0062 (ISSN)

Vol. 35 11 2459-2475 7488206

Ämneskategorier

Signalbehandling

DOI

10.1109/TMI.2016.2578680

Mer information

Senast uppdaterat

2018-09-06