Related Experiment Video
Updated: Apr 26, 2026
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: the VESSEL12 study
Rina D Rudyanto1, Sjoerd Kerkstra2, Eva M van Rikxoort2
1Center for Applied Medical Research, University of Navarra, Spain.
Insights
The VESSEL12 challenge offers a standardized dataset and scoring system for evaluating automated lung vessel segmentation algorithms in thoracic CT scans. This promotes objective comparison of methods for clinical applications.
Area of Science:
- Medical Imaging
- Computer-Aided Diagnosis
- Biomedical Engineering
Background:
- Automated vessel segmentation in thoracic CT scans is crucial for computer-aided processing of 3D imaging data.
- Manual segmentation is time-consuming, necessitating automated solutions for real-world applications.
- Lack of standardized evaluation hinders objective comparison of existing automated vessel segmentation algorithms.
Purpose of the Study:
- To objectively compare the performance of different algorithms for vessel segmentation in thoracic CT scans.
- To introduce a standardized evaluation framework for automated vessel segmentation methods.
- To analyze the strengths and weaknesses of various segmentation techniques, particularly in the context of lung diseases.
Main Methods:
- Development of an annotated reference dataset comprising 20 thoracic CT scans.
- Proposal of a nine-category system for comprehensive evaluation of vessel segmentation algorithms.
- Organization of the VESSEL12 challenge with participation from twenty algorithms from academia and industry.
Main Results:
- Publication of all challenge results on the VESSEL12 website.
- Establishment of an ongoing challenge platform for new participants.
- Analysis of algorithm performance across different lung disease conditions.
Conclusions:
- The VESSEL12 challenge provides a valuable resource for advancing automated vessel segmentation in medical imaging.
- The developed dataset and scoring system enable objective comparison and drive innovation in the field.
- Performance analysis offers insights into the effectiveness of different methods for clinical use.
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.
