Cargando…
The 2014 liver ultrasound tracking benchmark
The Challenge on Liver Ultrasound Tracking (CLUST) was held in conjunction with the MICCAI 2014 conference to enable direct comparison of tracking methods for this application. This paper reports the outcome of this challenge, including setup, methods, results and experiences. The database included...
Autores principales: | , , , , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
IOP Publishing
2015
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5454593/ https://www.ncbi.nlm.nih.gov/pubmed/26134417 http://dx.doi.org/10.1088/0031-9155/60/14/5571 |
_version_ | 1783240854583902208 |
---|---|
author | De Luca, V Benz, T Kondo, S König, L Lübke, D Rothlübbers, S Somphone, O Allaire, S Lediju Bell, M A Chung, D Y F Cifor, A Grozea, C Günther, M Jenne, J Kipshagen, T Kowarschik, M Navab, N Rühaak, J Schwaab, J Tanner, C |
author_facet | De Luca, V Benz, T Kondo, S König, L Lübke, D Rothlübbers, S Somphone, O Allaire, S Lediju Bell, M A Chung, D Y F Cifor, A Grozea, C Günther, M Jenne, J Kipshagen, T Kowarschik, M Navab, N Rühaak, J Schwaab, J Tanner, C |
author_sort | De Luca, V |
collection | PubMed |
description | The Challenge on Liver Ultrasound Tracking (CLUST) was held in conjunction with the MICCAI 2014 conference to enable direct comparison of tracking methods for this application. This paper reports the outcome of this challenge, including setup, methods, results and experiences. The database included 54 2D and 3D sequences of the liver of healthy volunteers and tumor patients under free breathing. Participants had to provide the tracking results of 90% of the data (test set) for pre-defined point-landmarks (healthy volunteers) or for tumor segmentations (patient data). In this paper we compare the best six methods which participated in the challenge. Quantitative evaluation was performed by the organizers with respect to manual annotations. Results of all methods showed a mean tracking error ranging between 1.4 mm and 2.1 mm for 2D points, and between 2.6 mm and 4.6 mm for 3D points. Fusing all automatic results by considering the median tracking results, improved the mean error to 1.2 mm (2D) and 2.5 mm (3D). For all methods, the performance is still not comparable to human inter-rater variability, with a mean tracking error of 0.5–0.6 mm (2D) and 1.2–1.8 mm (3D). The segmentation task was fulfilled only by one participant, resulting in a Dice coefficient ranging from 76.7% to 92.3%. The CLUST database continues to be available and the online leader-board will be updated as an ongoing challenge. |
format | Online Article Text |
id | pubmed-5454593 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2015 |
publisher | IOP Publishing |
record_format | MEDLINE/PubMed |
spelling | pubmed-54545932017-06-30 The 2014 liver ultrasound tracking benchmark De Luca, V Benz, T Kondo, S König, L Lübke, D Rothlübbers, S Somphone, O Allaire, S Lediju Bell, M A Chung, D Y F Cifor, A Grozea, C Günther, M Jenne, J Kipshagen, T Kowarschik, M Navab, N Rühaak, J Schwaab, J Tanner, C Phys Med Biol Paper The Challenge on Liver Ultrasound Tracking (CLUST) was held in conjunction with the MICCAI 2014 conference to enable direct comparison of tracking methods for this application. This paper reports the outcome of this challenge, including setup, methods, results and experiences. The database included 54 2D and 3D sequences of the liver of healthy volunteers and tumor patients under free breathing. Participants had to provide the tracking results of 90% of the data (test set) for pre-defined point-landmarks (healthy volunteers) or for tumor segmentations (patient data). In this paper we compare the best six methods which participated in the challenge. Quantitative evaluation was performed by the organizers with respect to manual annotations. Results of all methods showed a mean tracking error ranging between 1.4 mm and 2.1 mm for 2D points, and between 2.6 mm and 4.6 mm for 3D points. Fusing all automatic results by considering the median tracking results, improved the mean error to 1.2 mm (2D) and 2.5 mm (3D). For all methods, the performance is still not comparable to human inter-rater variability, with a mean tracking error of 0.5–0.6 mm (2D) and 1.2–1.8 mm (3D). The segmentation task was fulfilled only by one participant, resulting in a Dice coefficient ranging from 76.7% to 92.3%. The CLUST database continues to be available and the online leader-board will be updated as an ongoing challenge. IOP Publishing 2015-07-21 2015-07-02 /pmc/articles/PMC5454593/ /pubmed/26134417 http://dx.doi.org/10.1088/0031-9155/60/14/5571 Text en © 2015 Institute of Physics and Engineering in Medicine http://creativecommons.org/licenses/by/3.0/ Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence (http://creativecommons.org/licenses/by/3.0/) . Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI. |
spellingShingle | Paper De Luca, V Benz, T Kondo, S König, L Lübke, D Rothlübbers, S Somphone, O Allaire, S Lediju Bell, M A Chung, D Y F Cifor, A Grozea, C Günther, M Jenne, J Kipshagen, T Kowarschik, M Navab, N Rühaak, J Schwaab, J Tanner, C The 2014 liver ultrasound tracking benchmark |
title | The 2014 liver ultrasound tracking benchmark |
title_full | The 2014 liver ultrasound tracking benchmark |
title_fullStr | The 2014 liver ultrasound tracking benchmark |
title_full_unstemmed | The 2014 liver ultrasound tracking benchmark |
title_short | The 2014 liver ultrasound tracking benchmark |
title_sort | 2014 liver ultrasound tracking benchmark |
topic | Paper |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5454593/ https://www.ncbi.nlm.nih.gov/pubmed/26134417 http://dx.doi.org/10.1088/0031-9155/60/14/5571 |
work_keys_str_mv | AT delucav the2014liverultrasoundtrackingbenchmark AT benzt the2014liverultrasoundtrackingbenchmark AT kondos the2014liverultrasoundtrackingbenchmark AT konigl the2014liverultrasoundtrackingbenchmark AT lubked the2014liverultrasoundtrackingbenchmark AT rothlubberss the2014liverultrasoundtrackingbenchmark AT somphoneo the2014liverultrasoundtrackingbenchmark AT allaires the2014liverultrasoundtrackingbenchmark AT ledijubellma the2014liverultrasoundtrackingbenchmark AT chungdyf the2014liverultrasoundtrackingbenchmark AT cifora the2014liverultrasoundtrackingbenchmark AT grozeac the2014liverultrasoundtrackingbenchmark AT guntherm the2014liverultrasoundtrackingbenchmark AT jennej the2014liverultrasoundtrackingbenchmark AT kipshagent the2014liverultrasoundtrackingbenchmark AT kowarschikm the2014liverultrasoundtrackingbenchmark AT navabn the2014liverultrasoundtrackingbenchmark AT ruhaakj the2014liverultrasoundtrackingbenchmark AT schwaabj the2014liverultrasoundtrackingbenchmark AT tannerc the2014liverultrasoundtrackingbenchmark AT delucav 2014liverultrasoundtrackingbenchmark AT benzt 2014liverultrasoundtrackingbenchmark AT kondos 2014liverultrasoundtrackingbenchmark AT konigl 2014liverultrasoundtrackingbenchmark AT lubked 2014liverultrasoundtrackingbenchmark AT rothlubberss 2014liverultrasoundtrackingbenchmark AT somphoneo 2014liverultrasoundtrackingbenchmark AT allaires 2014liverultrasoundtrackingbenchmark AT ledijubellma 2014liverultrasoundtrackingbenchmark AT chungdyf 2014liverultrasoundtrackingbenchmark AT cifora 2014liverultrasoundtrackingbenchmark AT grozeac 2014liverultrasoundtrackingbenchmark AT guntherm 2014liverultrasoundtrackingbenchmark AT jennej 2014liverultrasoundtrackingbenchmark AT kipshagent 2014liverultrasoundtrackingbenchmark AT kowarschikm 2014liverultrasoundtrackingbenchmark AT navabn 2014liverultrasoundtrackingbenchmark AT ruhaakj 2014liverultrasoundtrackingbenchmark AT schwaabj 2014liverultrasoundtrackingbenchmark AT tannerc 2014liverultrasoundtrackingbenchmark |