Clinical validation of an automatic atlas-based segmentation tool for male pelvis CT images.
CT
auto-contouring
inter-observer
intra-observer
pelvis
time savings
Journal
Journal of applied clinical medical physics
ISSN: 1526-9914
Titre abrégé: J Appl Clin Med Phys
Pays: United States
ID NLM: 101089176
Informations de publication
Date de publication:
Mar 2022
Mar 2022
Historique:
revised:
01
12
2021
received:
13
05
2021
accepted:
06
12
2021
pubmed:
23
1
2022
medline:
12
3
2022
entrez:
22
1
2022
Statut:
ppublish
Résumé
This retrospective work aims to evaluate the possible impact on intra- and inter-observer variability, contouring time, and contour accuracy of introducing a pelvis computed tomography (CT) auto-segmentation tool in radiotherapy planning workflow. Tests were carried out on five structures (bladder, rectum, pelvic lymph-nodes, and femoral heads) of six previously treated subjects, enrolling five radiation oncologists (ROs) to manually re-contour and edit auto-contours generated with a male pelvis CT atlas created with the commercial software MIM MAESTRO. The ROs first delineated manual contours (M). Then they modified the auto-contours, producing automatic-modified (AM) contours. The procedure was repeated to evaluate intra-observer variability, producing M1, M2, AM1, and AM2 contour sets (each comprising 5 structures × 6 test patients × 5 ROs = 150 contours), for a total of 600 contours. Potential time savings was evaluated by comparing contouring and editing times. Structure contours were compared to a reference standard by means of Dice similarity coefficient (DSC) and mean distance to agreement (MDA), to assess intra- and inter-observer variability. To exclude any automation bias, ROs evaluated both M and AM sets as "clinically acceptable" or "to be corrected" in a blind test. Comparing AM to M sets, a significant reduction of both inter-observer variability (p < 0.001) and contouring time (-45% whole pelvis, p < 0.001) was obtained. Intra-observer variability reduction was significant only for bladder and femoral heads (p < 0.001). The statistical test showed no significant bias. Our atlas-based workflow proved to be effective for clinical practice as it can improve contour reproducibility and generate time savings. Based on these findings, institutions are encouraged to implement their auto-segmentation method.
Identifiants
pubmed: 35064746
doi: 10.1002/acm2.13507
pmc: PMC8906199
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e13507Informations de copyright
© 2022 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals, LLC on behalf of The American Association of Physicists in Medicine.
Références
IEEE Trans Med Imaging. 2004 Jul;23(7):903-21
pubmed: 15250643
Proc SPIE Int Soc Opt Eng. 2017 Feb;10133:
pubmed: 30220767
Radiat Oncol. 2013 Oct 03;8:229
pubmed: 24090107
J Appl Clin Med Phys. 2022 Mar;23(3):e13507
pubmed: 35064746
Eur Radiol. 2019 Mar;29(3):1391-1399
pubmed: 30194472
Acta Oncol. 2013 Nov;52(8):1676-81
pubmed: 23336255
J Med Imaging Radiat Oncol. 2009 Feb;53(1):100-6
pubmed: 19453535
Technol Cancer Res Treat. 2013 Jun;12(3):199-206
pubmed: 23289478
Psychometrika. 1947 Jun;12(2):153-7
pubmed: 20254758
Med Image Anal. 2017 Dec;42:60-88
pubmed: 28778026
Radiother Oncol. 2020 Apr;145:1-6
pubmed: 31869676
Radiat Oncol. 2012 Sep 18;7:160
pubmed: 22989046
Radiat Oncol. 2013 Jul 25;8:188
pubmed: 23885662
Med Image Anal. 2015 Aug;24(1):205-219
pubmed: 26201875
J Appl Clin Med Phys. 2020 Dec;21(12):219-230
pubmed: 33236827
Int J Radiat Oncol Biol Phys. 2010 Jul 1;77(3):959-66
pubmed: 20231069
Med Phys. 2019 Jan;46(1):e1-e36
pubmed: 30367497
Radiother Oncol. 2018 Feb;126(2):312-317
pubmed: 29208513
Radiat Oncol. 2020 Jul 20;15(1):176
pubmed: 32690103
Br J Radiol. 2016;89(1057):20140732
pubmed: 26539630
Acta Oncol. 2020 Aug;59(8):933-939
pubmed: 32568616
Br J Radiol. 2014 Nov;87(1043):20140299
pubmed: 25168198
Int J Radiat Oncol Biol Phys. 2009 Apr 1;73(5):1493-500
pubmed: 18804333
Int J Radiat Oncol Biol Phys. 2011 Mar 1;79(3):943-7
pubmed: 21281897
Phys Med Biol. 2018 Dec 14;63(24):245015
pubmed: 30523973