Format

Send to

Choose Destination
See comment in PubMed Commons below
Med Image Anal. 2014 Oct;18(7):1217-32. doi: 10.1016/j.media.2014.07.003. Epub 2014 Jul 23.

Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: the VESSEL12 study.

Author information

1
Center for Applied Medical Research, University of Navarra, Spain. Electronic address: rina.rudyanto@gmail.com.
2
Diagnostic Image Analysis Group, Radboud University Nijmegen Medical Centre, The Netherlands.
3
Institut SudParis Telecom, France.
4
Arizona State University, USA.
5
Bahcesehir University, Turkey.
6
Brigham and Womens Hospital, Boston, USA.
7
CREATIS, Université de Lyon, France.
8
Universidad de los Andes, Bogota, Colombia.
9
Fraunhofer MEVIS, Germany.
10
Universitat Politècnica de València, Spain.
11
Division of Image Processing (LKEB), Leiden University Medical Center, The Netherlands.
12
Hunan University, China.
13
Institute of Applied Computer Science, Lodz University of Technology, Poland.
14
Norwegian University of Science and Technology, Norway.
15
Shahed University, Iran.
16
University of Alberta, Canada.
17
Universidad Politécnica de Madrid, Spain; CIBER-BBN, Spain.
18
Graz University of Technology, Institute for Computer Vision and Graphics, Austria.
19
Ludwig Boltzmann Institute for Clinical Forensic Imaging, Graz, Austria.
20
Ludwig Boltzmann Institute for Lung Vascular Research, Graz, Austria.
21
Pulmonary Department, Clínica Universidad de Navarra, University of Navarra, Spain.
22
Department of Radiology, University Medical Center, Utrecht, The Netherlands.
23
Center for Applied Medical Research, University of Navarra, Spain.

Abstract

The VESSEL12 (VESsel SEgmentation in the Lung) challenge objectively compares the performance of different algorithms to identify vessels in thoracic computed tomography (CT) scans. Vessel segmentation is fundamental in computer aided processing of data generated by 3D imaging modalities. As manual vessel segmentation is prohibitively time consuming, any real world application requires some form of automation. Several approaches exist for automated vessel segmentation, but judging their relative merits is difficult due to a lack of standardized evaluation. We present an annotated reference dataset containing 20 CT scans and propose nine categories to perform a comprehensive evaluation of vessel segmentation algorithms from both academia and industry. Twenty algorithms participated in the VESSEL12 challenge, held at International Symposium on Biomedical Imaging (ISBI) 2012. All results have been published at the VESSEL12 website http://vessel12.grand-challenge.org. The challenge remains ongoing and open to new participants. Our three contributions are: (1) an annotated reference dataset available online for evaluation of new algorithms; (2) a quantitative scoring system for objective comparison of algorithms; and (3) performance analysis of the strengths and weaknesses of the various vessel segmentation methods in the presence of various lung diseases.

KEYWORDS:

Algorithm comparison; Challenge; Lung vessels; Segmentation; Thoracic computed tomography

PMID:
25113321
PMCID:
PMC5153359
DOI:
10.1016/j.media.2014.07.003
[Indexed for MEDLINE]
Free PMC Article
PubMed Commons home

PubMed Commons

0 comments

    Supplemental Content

    Full text links

    Icon for Elsevier Science Icon for PubMed Central
    Loading ...
    Support Center