Cargando…

External validation of deep learning-based contouring of head and neck organs at risk

BACKGROUND AND PURPOSE: Head and neck (HN) radiotherapy can benefit from automatic delineation of tumor and surrounding organs because of the complex anatomy and the regular need for adaptation. The aim of this study was to assess the performance of a commercially available deep learning contouring...

Descripción completa

Detalles Bibliográficos
Autores principales: Brunenberg, Ellen J.L., Steinseifer, Isabell K., van den Bosch, Sven, Kaanders, Johannes H.A.M., Brouwer, Charlotte L., Gooding, Mark J., van Elmpt, Wouter, Monshouwer, René
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7807543/
https://www.ncbi.nlm.nih.gov/pubmed/33458320
http://dx.doi.org/10.1016/j.phro.2020.06.006
_version_ 1783636763237941248
author Brunenberg, Ellen J.L.
Steinseifer, Isabell K.
van den Bosch, Sven
Kaanders, Johannes H.A.M.
Brouwer, Charlotte L.
Gooding, Mark J.
van Elmpt, Wouter
Monshouwer, René
author_facet Brunenberg, Ellen J.L.
Steinseifer, Isabell K.
van den Bosch, Sven
Kaanders, Johannes H.A.M.
Brouwer, Charlotte L.
Gooding, Mark J.
van Elmpt, Wouter
Monshouwer, René
author_sort Brunenberg, Ellen J.L.
collection PubMed
description BACKGROUND AND PURPOSE: Head and neck (HN) radiotherapy can benefit from automatic delineation of tumor and surrounding organs because of the complex anatomy and the regular need for adaptation. The aim of this study was to assess the performance of a commercially available deep learning contouring (DLC) model on an external validation set. MATERIALS AND METHODS: The CT-based DLC model, trained at the University Medical Center Groningen (UMCG), was applied to an independent set of 58 patients from the Radboud University Medical Center (RUMC). DLC results were compared to the RUMC manual reference using the Dice similarity coefficient (DSC) and 95th percentile of Hausdorff distance (HD95). Craniocaudal spatial information was added by calculating binned measures. In addition, a qualitative evaluation compared the acceptance of manual and DLC contours in both groups of observers. RESULTS: Good correspondence was shown for the mandible (DSC 0.90; HD95 3.6 mm). Performance was reasonable for the glandular OARs, brainstem and oral cavity (DSC 0.78–0.85, HD95 3.7–7.3 mm). The other aerodigestive tract OARs showed only moderate agreement (DSC 0.53–0.65, HD95 around 9 mm). The binned measures displayed the largest deviations caudally and/or cranially. CONCLUSIONS: This study demonstrates that the DLC model can provide a reasonable starting point for delineation when applied to an independent patient cohort. The qualitative evaluation did not reveal large differences in the interpretation of contouring guidelines between RUMC and UMCG observers.
format Online
Article
Text
id pubmed-7807543
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-78075432021-01-14 External validation of deep learning-based contouring of head and neck organs at risk Brunenberg, Ellen J.L. Steinseifer, Isabell K. van den Bosch, Sven Kaanders, Johannes H.A.M. Brouwer, Charlotte L. Gooding, Mark J. van Elmpt, Wouter Monshouwer, René Phys Imaging Radiat Oncol Original Research Article BACKGROUND AND PURPOSE: Head and neck (HN) radiotherapy can benefit from automatic delineation of tumor and surrounding organs because of the complex anatomy and the regular need for adaptation. The aim of this study was to assess the performance of a commercially available deep learning contouring (DLC) model on an external validation set. MATERIALS AND METHODS: The CT-based DLC model, trained at the University Medical Center Groningen (UMCG), was applied to an independent set of 58 patients from the Radboud University Medical Center (RUMC). DLC results were compared to the RUMC manual reference using the Dice similarity coefficient (DSC) and 95th percentile of Hausdorff distance (HD95). Craniocaudal spatial information was added by calculating binned measures. In addition, a qualitative evaluation compared the acceptance of manual and DLC contours in both groups of observers. RESULTS: Good correspondence was shown for the mandible (DSC 0.90; HD95 3.6 mm). Performance was reasonable for the glandular OARs, brainstem and oral cavity (DSC 0.78–0.85, HD95 3.7–7.3 mm). The other aerodigestive tract OARs showed only moderate agreement (DSC 0.53–0.65, HD95 around 9 mm). The binned measures displayed the largest deviations caudally and/or cranially. CONCLUSIONS: This study demonstrates that the DLC model can provide a reasonable starting point for delineation when applied to an independent patient cohort. The qualitative evaluation did not reveal large differences in the interpretation of contouring guidelines between RUMC and UMCG observers. Elsevier 2020-07-10 /pmc/articles/PMC7807543/ /pubmed/33458320 http://dx.doi.org/10.1016/j.phro.2020.06.006 Text en © 2020 The Author(s) http://creativecommons.org/licenses/by/4.0/ This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Original Research Article
Brunenberg, Ellen J.L.
Steinseifer, Isabell K.
van den Bosch, Sven
Kaanders, Johannes H.A.M.
Brouwer, Charlotte L.
Gooding, Mark J.
van Elmpt, Wouter
Monshouwer, René
External validation of deep learning-based contouring of head and neck organs at risk
title External validation of deep learning-based contouring of head and neck organs at risk
title_full External validation of deep learning-based contouring of head and neck organs at risk
title_fullStr External validation of deep learning-based contouring of head and neck organs at risk
title_full_unstemmed External validation of deep learning-based contouring of head and neck organs at risk
title_short External validation of deep learning-based contouring of head and neck organs at risk
title_sort external validation of deep learning-based contouring of head and neck organs at risk
topic Original Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7807543/
https://www.ncbi.nlm.nih.gov/pubmed/33458320
http://dx.doi.org/10.1016/j.phro.2020.06.006
work_keys_str_mv AT brunenbergellenjl externalvalidationofdeeplearningbasedcontouringofheadandneckorgansatrisk
AT steinseiferisabellk externalvalidationofdeeplearningbasedcontouringofheadandneckorgansatrisk
AT vandenboschsven externalvalidationofdeeplearningbasedcontouringofheadandneckorgansatrisk
AT kaandersjohannesham externalvalidationofdeeplearningbasedcontouringofheadandneckorgansatrisk
AT brouwercharlottel externalvalidationofdeeplearningbasedcontouringofheadandneckorgansatrisk
AT goodingmarkj externalvalidationofdeeplearningbasedcontouringofheadandneckorgansatrisk
AT vanelmptwouter externalvalidationofdeeplearningbasedcontouringofheadandneckorgansatrisk
AT monshouwerrene externalvalidationofdeeplearningbasedcontouringofheadandneckorgansatrisk