Cargando…

Real-world analysis of manual editing of deep learning contouring in the thorax region

BACKGROUND AND PURPOSE: User-adjustments after deep-learning (DL) contouring in radiotherapy were evaluated to get insight in real-world editing during clinical practice. This study assessed the amount, type and spatial regions of editing of auto-contouring for organs-at-risk (OARs) in routine clini...

Descripción completa

Detalles Bibliográficos
Autores principales: Vaassen, Femke, Boukerroui, Djamal, Looney, Padraig, Canters, Richard, Verhoeven, Karolien, Peeters, Stephanie, Lubken, Indra, Mannens, Jolein, Gooding, Mark J., van Elmpt, Wouter
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9115320/
https://www.ncbi.nlm.nih.gov/pubmed/35602549
http://dx.doi.org/10.1016/j.phro.2022.04.008
_version_ 1784709920338214912
author Vaassen, Femke
Boukerroui, Djamal
Looney, Padraig
Canters, Richard
Verhoeven, Karolien
Peeters, Stephanie
Lubken, Indra
Mannens, Jolein
Gooding, Mark J.
van Elmpt, Wouter
author_facet Vaassen, Femke
Boukerroui, Djamal
Looney, Padraig
Canters, Richard
Verhoeven, Karolien
Peeters, Stephanie
Lubken, Indra
Mannens, Jolein
Gooding, Mark J.
van Elmpt, Wouter
author_sort Vaassen, Femke
collection PubMed
description BACKGROUND AND PURPOSE: User-adjustments after deep-learning (DL) contouring in radiotherapy were evaluated to get insight in real-world editing during clinical practice. This study assessed the amount, type and spatial regions of editing of auto-contouring for organs-at-risk (OARs) in routine clinical workflow for patients in the thorax region. MATERIALS AND METHODS: A total of 350 lung cancer and 362 breast cancer patients, contoured between March 2020 and March 2021 using a commercial DL-contouring method followed by manual adjustments were retrospectively analyzed. Subsampling was performed for some OARs, using an inter-slice gap of 1–3 slices. Commonly-used whole-organ contouring assessment measures were calculated, and all cases were registered to a common reference shape per OAR to identify regions of manual adjustment. Results were expressed as the median, 10th-90th percentile of adjustment and visualized using 3D renderings. RESULTS: Per OAR, the median amount of editing was below 1 mm. However, large adjustments were found in some locations for most OARs. In general, enlarging of the auto-contours was needed. Subsampling DL-contours showed less adjustments were made in the interpolated slices compared to simulated no-subsampling for these OARs. CONCLUSION: The real-world performance of automatic DL-contouring software was evaluated and proven useful in clinical practice. Specific regions-of-adjustment were identified per OAR in the thorax region, and separate models were found to be necessary for specific clinical indications different from training data. This analysis showed the need to perform routine clinical analysis especially when procedures or acquisition protocols change to have the best configuration of the workflow.
format Online
Article
Text
id pubmed-9115320
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-91153202022-05-19 Real-world analysis of manual editing of deep learning contouring in the thorax region Vaassen, Femke Boukerroui, Djamal Looney, Padraig Canters, Richard Verhoeven, Karolien Peeters, Stephanie Lubken, Indra Mannens, Jolein Gooding, Mark J. van Elmpt, Wouter Phys Imaging Radiat Oncol Original Research Article BACKGROUND AND PURPOSE: User-adjustments after deep-learning (DL) contouring in radiotherapy were evaluated to get insight in real-world editing during clinical practice. This study assessed the amount, type and spatial regions of editing of auto-contouring for organs-at-risk (OARs) in routine clinical workflow for patients in the thorax region. MATERIALS AND METHODS: A total of 350 lung cancer and 362 breast cancer patients, contoured between March 2020 and March 2021 using a commercial DL-contouring method followed by manual adjustments were retrospectively analyzed. Subsampling was performed for some OARs, using an inter-slice gap of 1–3 slices. Commonly-used whole-organ contouring assessment measures were calculated, and all cases were registered to a common reference shape per OAR to identify regions of manual adjustment. Results were expressed as the median, 10th-90th percentile of adjustment and visualized using 3D renderings. RESULTS: Per OAR, the median amount of editing was below 1 mm. However, large adjustments were found in some locations for most OARs. In general, enlarging of the auto-contours was needed. Subsampling DL-contours showed less adjustments were made in the interpolated slices compared to simulated no-subsampling for these OARs. CONCLUSION: The real-world performance of automatic DL-contouring software was evaluated and proven useful in clinical practice. Specific regions-of-adjustment were identified per OAR in the thorax region, and separate models were found to be necessary for specific clinical indications different from training data. This analysis showed the need to perform routine clinical analysis especially when procedures or acquisition protocols change to have the best configuration of the workflow. Elsevier 2022-05-14 /pmc/articles/PMC9115320/ /pubmed/35602549 http://dx.doi.org/10.1016/j.phro.2022.04.008 Text en © 2022 The Authors https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Original Research Article
Vaassen, Femke
Boukerroui, Djamal
Looney, Padraig
Canters, Richard
Verhoeven, Karolien
Peeters, Stephanie
Lubken, Indra
Mannens, Jolein
Gooding, Mark J.
van Elmpt, Wouter
Real-world analysis of manual editing of deep learning contouring in the thorax region
title Real-world analysis of manual editing of deep learning contouring in the thorax region
title_full Real-world analysis of manual editing of deep learning contouring in the thorax region
title_fullStr Real-world analysis of manual editing of deep learning contouring in the thorax region
title_full_unstemmed Real-world analysis of manual editing of deep learning contouring in the thorax region
title_short Real-world analysis of manual editing of deep learning contouring in the thorax region
title_sort real-world analysis of manual editing of deep learning contouring in the thorax region
topic Original Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9115320/
https://www.ncbi.nlm.nih.gov/pubmed/35602549
http://dx.doi.org/10.1016/j.phro.2022.04.008
work_keys_str_mv AT vaassenfemke realworldanalysisofmanualeditingofdeeplearningcontouringinthethoraxregion
AT boukerrouidjamal realworldanalysisofmanualeditingofdeeplearningcontouringinthethoraxregion
AT looneypadraig realworldanalysisofmanualeditingofdeeplearningcontouringinthethoraxregion
AT cantersrichard realworldanalysisofmanualeditingofdeeplearningcontouringinthethoraxregion
AT verhoevenkarolien realworldanalysisofmanualeditingofdeeplearningcontouringinthethoraxregion
AT peetersstephanie realworldanalysisofmanualeditingofdeeplearningcontouringinthethoraxregion
AT lubkenindra realworldanalysisofmanualeditingofdeeplearningcontouringinthethoraxregion
AT mannensjolein realworldanalysisofmanualeditingofdeeplearningcontouringinthethoraxregion
AT goodingmarkj realworldanalysisofmanualeditingofdeeplearningcontouringinthethoraxregion
AT vanelmptwouter realworldanalysisofmanualeditingofdeeplearningcontouringinthethoraxregion