Cloud-Based Evaluation of Anatomical Structure Segmentation and Landmark Detection Algorithms: VISCERAL Anatomy Benchmarks.

TitleCloud-Based Evaluation of Anatomical Structure Segmentation and Landmark Detection Algorithms: VISCERAL Anatomy Benchmarks.
Publication TypeJournal Article
Year of Publication2016
AuthorsJimenez-Del-Toro O., Muller H., Krenn M., Gruenberg K., Taha A.A., Winterstein M., Eggel I., Foncubierta-Rodriguez A., Goksel O., Jakab A., Kontokotsios G., Langs G., Menze B., Salas Fernandez T., Schaer R., Walleyo A., Weber M.-A., Dicente Cid Y., Gass T., Heinrich M.P., Jia F., Kahl F., Kechichian R., Mai D., Spanier A., Vincent G., Wang C., Wyeth D., Hanbury A.
JournalIEEE transactions on medical imaging
Volume35
Issue11
Pages2459-2475
Date Published2016 Jun 9
Publication LanguageENG
ISSN1558-254X
Abstract

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.

DOI10.1109/TMI.2016.2578680
PubMed Link

http://www.ncbi.nlm.nih.gov/pubmed/27305669?dopt=Abstract

Alternate JournalIEEE Trans Med Imaging
Created at July 25, 2016 - 6:44pm. Last modified at February 21, 2017 - 12:22pm.

Languages

Address

Office
Susanne Petersen

Tel+49 451 3101 5601
Fax+49 451 3101 5604


Ratzeburger Allee 160
23538 Lübeck
Germany