Clinical Implementation and Evaluation of Auto-Segmentation Tools for Multi-Site Contouring in Radiotherapy
Tools for auto-segmentation in radiotherapy are widely available, but guidelines for clinical implementation are missing. The goal was to develop a workflow for performance evaluation of three commercial auto-segmentation tools to select one candidate for clinical implementation. One hundred patient...
Saved in:
| Published in: | Physics and imaging in radiation oncology Vol. 28; p. 100515 |
|---|---|
| Main Authors: | , , , , , , , , , , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Netherlands
Elsevier B.V
01.10.2023
Elsevier |
| Subjects: | |
| ISSN: | 2405-6316, 2405-6316 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Tools for auto-segmentation in radiotherapy are widely available, but guidelines for clinical implementation are missing. The goal was to develop a workflow for performance evaluation of three commercial auto-segmentation tools to select one candidate for clinical implementation.
One hundred patients with six treatment sites (brain, head-and-neck, thorax, abdomen, and pelvis) were included. Three sets of AI-based contours for organs-at-risk (OAR) generated by three software tools and manually drawn expert contours were blindly rated for contouring accuracy. The dice similarity coefficient (DSC), the Hausdorff distance, and a dose/volume evaluation based on the recalculation of the original treatment plan were assessed. Statistically significant differences were tested using the Kruskal-Wallis test and the post-hoc Dunn Test with Bonferroni correction.
The mean DSC scores compared to expert contours for all OARs combined were 0.80 ± 0.10, 0.75 ± 0.10, and 0.74 ± 0.11 for the three software tools. Physicians' rating identified equivalent or superior performance of some AI-based contours in head (eye, lens, optic nerve, brain, chiasm), thorax (e.g., heart and lungs), and pelvis and abdomen (e.g., kidney, femoral head) compared to manual contours. For some OARs, the AI models provided results requiring only minor corrections. Bowel-bag and stomach were not fit for direct use. During the interdisciplinary discussion, the physicians' rating was considered the most relevant.
A comprehensive method for evaluation and clinical implementation of commercially available auto-segmentation software was developed. The in-depth analysis yielded clear instructions for clinical use within the radiotherapy department. |
|---|---|
| AbstractList | Tools for auto-segmentation in radiotherapy are widely available, but guidelines for clinical implementation are missing. The goal was to develop a workflow for performance evaluation of three commercial auto-segmentation tools to select one candidate for clinical implementation.
One hundred patients with six treatment sites (brain, head-and-neck, thorax, abdomen, and pelvis) were included. Three sets of AI-based contours for organs-at-risk (OAR) generated by three software tools and manually drawn expert contours were blindly rated for contouring accuracy. The dice similarity coefficient (DSC), the Hausdorff distance, and a dose/volume evaluation based on the recalculation of the original treatment plan were assessed. Statistically significant differences were tested using the Kruskal-Wallis test and the post-hoc Dunn Test with Bonferroni correction.
The mean DSC scores compared to expert contours for all OARs combined were 0.80 ± 0.10, 0.75 ± 0.10, and 0.74 ± 0.11 for the three software tools. Physicians' rating identified equivalent or superior performance of some AI-based contours in head (eye, lens, optic nerve, brain, chiasm), thorax (e.g., heart and lungs), and pelvis and abdomen (e.g., kidney, femoral head) compared to manual contours. For some OARs, the AI models provided results requiring only minor corrections. Bowel-bag and stomach were not fit for direct use. During the interdisciplinary discussion, the physicians' rating was considered the most relevant.
A comprehensive method for evaluation and clinical implementation of commercially available auto-segmentation software was developed. The in-depth analysis yielded clear instructions for clinical use within the radiotherapy department. Tools for auto-segmentation in radiotherapy are widely available, but guidelines for clinical implementation are missing. The goal was to develop a workflow for performance evaluation of three commercial auto-segmentation tools to select one candidate for clinical implementation.Background and purposeTools for auto-segmentation in radiotherapy are widely available, but guidelines for clinical implementation are missing. The goal was to develop a workflow for performance evaluation of three commercial auto-segmentation tools to select one candidate for clinical implementation.One hundred patients with six treatment sites (brain, head-and-neck, thorax, abdomen, and pelvis) were included. Three sets of AI-based contours for organs-at-risk (OAR) generated by three software tools and manually drawn expert contours were blindly rated for contouring accuracy. The dice similarity coefficient (DSC), the Hausdorff distance, and a dose/volume evaluation based on the recalculation of the original treatment plan were assessed. Statistically significant differences were tested using the Kruskal-Wallis test and the post-hoc Dunn Test with Bonferroni correction.Materials and MethodsOne hundred patients with six treatment sites (brain, head-and-neck, thorax, abdomen, and pelvis) were included. Three sets of AI-based contours for organs-at-risk (OAR) generated by three software tools and manually drawn expert contours were blindly rated for contouring accuracy. The dice similarity coefficient (DSC), the Hausdorff distance, and a dose/volume evaluation based on the recalculation of the original treatment plan were assessed. Statistically significant differences were tested using the Kruskal-Wallis test and the post-hoc Dunn Test with Bonferroni correction.The mean DSC scores compared to expert contours for all OARs combined were 0.80 ± 0.10, 0.75 ± 0.10, and 0.74 ± 0.11 for the three software tools. Physicians' rating identified equivalent or superior performance of some AI-based contours in head (eye, lens, optic nerve, brain, chiasm), thorax (e.g., heart and lungs), and pelvis and abdomen (e.g., kidney, femoral head) compared to manual contours. For some OARs, the AI models provided results requiring only minor corrections. Bowel-bag and stomach were not fit for direct use. During the interdisciplinary discussion, the physicians' rating was considered the most relevant.ResultsThe mean DSC scores compared to expert contours for all OARs combined were 0.80 ± 0.10, 0.75 ± 0.10, and 0.74 ± 0.11 for the three software tools. Physicians' rating identified equivalent or superior performance of some AI-based contours in head (eye, lens, optic nerve, brain, chiasm), thorax (e.g., heart and lungs), and pelvis and abdomen (e.g., kidney, femoral head) compared to manual contours. For some OARs, the AI models provided results requiring only minor corrections. Bowel-bag and stomach were not fit for direct use. During the interdisciplinary discussion, the physicians' rating was considered the most relevant.A comprehensive method for evaluation and clinical implementation of commercially available auto-segmentation software was developed. The in-depth analysis yielded clear instructions for clinical use within the radiotherapy department.ConclusionA comprehensive method for evaluation and clinical implementation of commercially available auto-segmentation software was developed. The in-depth analysis yielded clear instructions for clinical use within the radiotherapy department. Background and purpose: Tools for auto-segmentation in radiotherapy are widely available, but guidelines for clinical implementation are missing. The goal was to develop a workflow for performance evaluation of three commercial auto-segmentation tools to select one candidate for clinical implementation. Materials and Methods: One hundred patients with six treatment sites (brain, head-and-neck, thorax, abdomen, and pelvis) were included. Three sets of AI-based contours for organs-at-risk (OAR) generated by three software tools and manually drawn expert contours were blindly rated for contouring accuracy. The dice similarity coefficient (DSC), the Hausdorff distance, and a dose/volume evaluation based on the recalculation of the original treatment plan were assessed. Statistically significant differences were tested using the Kruskal-Wallis test and the post-hoc Dunn Test with Bonferroni correction. Results: The mean DSC scores compared to expert contours for all OARs combined were 0.80 ± 0.10, 0.75 ± 0.10, and 0.74 ± 0.11 for the three software tools. Physicians' rating identified equivalent or superior performance of some AI-based contours in head (eye, lens, optic nerve, brain, chiasm), thorax (e.g., heart and lungs), and pelvis and abdomen (e.g., kidney, femoral head) compared to manual contours. For some OARs, the AI models provided results requiring only minor corrections. Bowel-bag and stomach were not fit for direct use. During the interdisciplinary discussion, the physicians' rating was considered the most relevant. Conclusion: A comprehensive method for evaluation and clinical implementation of commercially available auto-segmentation software was developed. The in-depth analysis yielded clear instructions for clinical use within the radiotherapy department. |
| ArticleNumber | 100515 |
| Author | Heilmann, Martin Heilemann, Gerd Eckert, Franziska Moll, Matthias Widder, Joachim Knoth, Johannes Georg, Dietmar Simek, Inga-Malin Dick, Vincent Konrad, Stefan Buschmann, Martin Herrmann, Harald Thiele, Christopher Lechner, Wolfgang Zaharie, Alexandru Trnkova, Petra |
| Author_xml | – sequence: 1 givenname: Gerd orcidid: 0000-0002-7461-3956 surname: Heilemann fullname: Heilemann, Gerd email: gerd.heilemann@meduniwien.ac.at – sequence: 2 givenname: Martin orcidid: 0000-0001-9946-1939 surname: Buschmann fullname: Buschmann, Martin – sequence: 3 givenname: Wolfgang orcidid: 0000-0001-9211-7510 surname: Lechner fullname: Lechner, Wolfgang – sequence: 4 givenname: Vincent surname: Dick fullname: Dick, Vincent – sequence: 5 givenname: Franziska surname: Eckert fullname: Eckert, Franziska – sequence: 6 givenname: Martin surname: Heilmann fullname: Heilmann, Martin – sequence: 7 givenname: Harald surname: Herrmann fullname: Herrmann, Harald – sequence: 8 givenname: Matthias surname: Moll fullname: Moll, Matthias – sequence: 9 givenname: Johannes orcidid: 0000-0002-0704-9910 surname: Knoth fullname: Knoth, Johannes – sequence: 10 givenname: Stefan orcidid: 0000-0001-8429-3741 surname: Konrad fullname: Konrad, Stefan – sequence: 11 givenname: Inga-Malin orcidid: 0000-0002-5414-6633 surname: Simek fullname: Simek, Inga-Malin – sequence: 12 givenname: Christopher surname: Thiele fullname: Thiele, Christopher – sequence: 13 givenname: Alexandru surname: Zaharie fullname: Zaharie, Alexandru – sequence: 14 givenname: Dietmar orcidid: 0000-0002-8327-3877 surname: Georg fullname: Georg, Dietmar – sequence: 15 givenname: Joachim orcidid: 0000-0002-9972-6690 surname: Widder fullname: Widder, Joachim – sequence: 16 givenname: Petra orcidid: 0000-0002-0347-2981 surname: Trnkova fullname: Trnkova, Petra |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38111502$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9UsFu3CAQtapUTZrmB3qofOzFmwEMNr1U0SptV0pVqUnPCGPYZYPBxfZK-_ch8SZNesgFmOG9Nwzz3mdHPnidZR8RLBAgdr5d9JsYFhgwSQmgiL7JTnAJtGAEsaNn5-PsbBi2AIArTiiBd9kxqRFCFPBJdrt01lslXb7qeqc77Uc52uBz6dv8cifdNIfB5BfTGIprvf6HuQnBDbkJMf85udEW13bU-TL4MUzR-nVuff5btjaMGx1lv_-QvTXSDfrssJ9mf75d3ix_FFe_vq-WF1eFohjGgqMaQVtSXCvTaKqIgpqVXBnGKjAlRxorSZVKi0QKKqZ4WxtoWoJRSyknp9lq1m2D3Io-2k7GvQjSiodEiGsh42iV08IQgJI3JWfGlFWLZVNzXEmjGQdTKZm0vs5a_dR0ulWp9yjdC9GXN95uxDrsBIIKM0zqpPD5oBDD30kPo-jsoLRz0uswDQJzIDVD9AH66XmxpyqP40oAPANUDMMQtXmCIBD3thCp32QLcW8LMdsiker_SMrOA0wPtu516peZqtO4dlZHoQ52udX79Jv2NfIdXKjTng |
| CitedBy_id | crossref_primary_10_1016_j_zemedi_2025_02_003 crossref_primary_10_1186_s13014_024_02554_y crossref_primary_10_1038_s41598_024_81167_7 crossref_primary_10_1038_s43856_025_01048_6 crossref_primary_10_1002_mp_17782 crossref_primary_10_1088_1361_6498_ad9f71 crossref_primary_10_1007_s00120_025_02620_7 crossref_primary_10_3389_fonc_2024_1358350 crossref_primary_10_1088_1361_6560_ade5e6 crossref_primary_10_1002_acm2_14558 crossref_primary_10_3390_mti8120114 crossref_primary_10_1007_s00066_024_02277_9 crossref_primary_10_1002_acm2_70010 crossref_primary_10_1002_acm2_70067 crossref_primary_10_1007_s00066_024_02358_9 crossref_primary_10_3389_fonc_2023_1305511 |
| Cites_doi | 10.1016/j.radonc.2019.10.019 10.1200/CCI.23.00005 10.1002/mp.14845 10.1016/j.ijrobp.2010.10.019 10.1016/j.zemedi.2021.11.006 10.1016/j.radonc.2021.08.014 10.1200/JCO.2015.63.9898 10.1016/j.radonc.2021.05.003 10.1016/j.semradonc.2019.02.001 10.1002/mp.13200 10.1002/mp.16545 10.1016/j.phro.2022.04.008 10.1016/j.ijrobp.2020.11.011 10.1016/j.phro.2019.12.001 10.1016/j.phro.2022.07.004 10.1002/mp.14774 10.1016/j.radonc.2021.02.040 10.1016/j.clon.2021.12.003 10.1016/j.radonc.2022.10.029 10.1016/j.clon.2023.01.014 |
| ContentType | Journal Article |
| Copyright | 2023 The Author(s) 2023 The Author(s). 2023 The Author(s) 2023 |
| Copyright_xml | – notice: 2023 The Author(s) – notice: 2023 The Author(s). – notice: 2023 The Author(s) 2023 |
| DBID | AAYXX CITATION NPM 7X8 5PM DOA |
| DOI | 10.1016/j.phro.2023.100515 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic PubMed Central (Full Participant titles) Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 2405-6316 |
| ExternalDocumentID | oai_doaj_org_article_f30049b496ff47d2ab8927afe690f7ca PMC10726238 38111502 10_1016_j_phro_2023_100515 S2405631623001069 |
| Genre | Journal Article |
| GroupedDBID | .1- .FO 0R~ AAEDW AALRI AAXUO AAYWO ABMAC ACGFS ACVFH ADBBV ADCNI ADVLN AEUPX AFJKZ AFPUW AFRHN AFTJW AIGII AITUG AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ APXCP BCNDV EBS EJD FDB GROUPED_DOAJ M41 M~E O9- OK1 ROL RPM SSZ Z5R AAYXX CITATION AACTN NPM RIG 7X8 5PM |
| ID | FETCH-LOGICAL-c520t-91810d4528cfbe5c3c08649cf6670f491e2ca5ccca5a1c076c9d8f0bd321d5593 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 30 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001135921700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2405-6316 |
| IngestDate | Fri Oct 03 12:43:05 EDT 2025 Thu Aug 21 18:37:50 EDT 2025 Wed Oct 01 12:47:56 EDT 2025 Thu Apr 03 07:02:02 EDT 2025 Thu Nov 13 04:15:14 EST 2025 Tue Nov 18 21:08:09 EST 2025 Tue Aug 26 17:18:45 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Segmentation Radiotherapy Auto-segmentation Deep Learning |
| Language | English |
| License | This is an open access article under the CC BY license. 2023 The Author(s). This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c520t-91810d4528cfbe5c3c08649cf6670f491e2ca5ccca5a1c076c9d8f0bd321d5593 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-7461-3956 0000-0002-0704-9910 0000-0001-8429-3741 0000-0002-9972-6690 0000-0001-9946-1939 0000-0002-8327-3877 0000-0002-5414-6633 0000-0001-9211-7510 0000-0002-0347-2981 |
| OpenAccessLink | https://doaj.org/article/f30049b496ff47d2ab8927afe690f7ca |
| PMID | 38111502 |
| PQID | 2903861538 |
| PQPubID | 23479 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_f30049b496ff47d2ab8927afe690f7ca pubmedcentral_primary_oai_pubmedcentral_nih_gov_10726238 proquest_miscellaneous_2903861538 pubmed_primary_38111502 crossref_primary_10_1016_j_phro_2023_100515 crossref_citationtrail_10_1016_j_phro_2023_100515 elsevier_clinicalkey_doi_10_1016_j_phro_2023_100515 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-10-01 |
| PublicationDateYYYYMMDD | 2023-10-01 |
| PublicationDate_xml | – month: 10 year: 2023 text: 2023-10-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Netherlands |
| PublicationPlace_xml | – name: Netherlands |
| PublicationTitle | Physics and imaging in radiation oncology |
| PublicationTitleAlternate | Phys Imaging Radiat Oncol |
| PublicationYear | 2023 |
| Publisher | Elsevier B.V Elsevier |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier |
| References | Boero, Paravati, Xu, Cohen, Mell, Le (b0010) 2016; 34 Heilemann, Georg, Dobiasch, Widder, Renner (b0115) 2023 Thor, Apte, Haq, Iyer, LoCastro, Deasy (b0020) 2021; 109 Zimmermann, Faustmann, Ramsl, Georg, Heilemann (b0100) 2021; 48 Han, Hoogeman, Levendag, Hibbard, Teguh, Voet (b0025) 2008; 11 Babier, Zhang, Mahmood, Moore, Purdie, McNiven (b0105) 2021; 48 Nelms, Tomé, Robinson, Wheeler (b0005) 2012; 82 Barragan-Montero, Bibal, Dastarac, Draguet, Valdes, Nguyen (b0055) 2022 Cardenas, Yang, Anderson, Court, Brock (b0035) 2019; 29 Wong, Fong, McVicar, Smith, Giambattista, Wells (b0060) 2020; 144 Heilemann, Matthewman, Kuess, Goldner, Widder, Georg (b0040) 2022; 32 Vaassen, Boukerroui, Looney, Canters, Verhoeven, Peeters (b0075) 2022; 22 Bakx, Rijkaart, van der Sangen, Theuws, van der Toorn, Verrijssen (b0065) 2023 Costea, Zlate, Durand, Baudier, Grégoire, Sarrut (b0050) 2022; 177 Cha, Elguindi, Onochie, Gorovets, Deasy, Zelefsky (b0070) 2021; 159 Sherer, Lin, Elguindi, Duke, Tan, Cacicedo (b0015) 2021; 160 Johnston, De Rycke, Lievens, van Eijkeren, Aelterman, Vandersmissen (b0080) 2022; 23 Chung, Chang, Kim (b0085) 2023 Vrtovec, Močnik, Strojan, Pernuš, Ibragimov (b0030) 2020 Heilemann, Zimmermann, Schotola, Lechner, Peer, Widder (b0110) 2023; 50 Nikolov, Blackwell, Zverovitch, Mendes, Livne, de Fauw (b0140) 2021 Harrison, Pullen, Welsh, Oktay, Alvarez-Valle, Jena (b0045) 2022; 34 Gooding, Smith, Tariq, Aljabar, Peressutti, van der Stoep (b0095) 2018; 45 Vaassen, Hazelaar, Canters, Peeters, Petit, van Elmpt (b0130) 2021; 163 Roper, Lin, Rong (b0125) 2023 Vaassen, Hazelaar, Vaniqui, Gooding, van der Heyden, Canters (b0135) 2020; 13 Taha, Hanbury (b0090) 2015 Hindocha, Zucker, Jena, Banfill, Mackay, Price (b0120) 2023; 35 Vaassen (10.1016/j.phro.2023.100515_b0075) 2022; 22 Cha (10.1016/j.phro.2023.100515_b0070) 2021; 159 Vaassen (10.1016/j.phro.2023.100515_b0135) 2020; 13 Chung (10.1016/j.phro.2023.100515_b0085) 2023 Heilemann (10.1016/j.phro.2023.100515_b0115) 2023 Vaassen (10.1016/j.phro.2023.100515_b0130) 2021; 163 Heilemann (10.1016/j.phro.2023.100515_b0110) 2023; 50 Boero (10.1016/j.phro.2023.100515_b0010) 2016; 34 Zimmermann (10.1016/j.phro.2023.100515_b0100) 2021; 48 Taha (10.1016/j.phro.2023.100515_b0090) 2015 Gooding (10.1016/j.phro.2023.100515_b0095) 2018; 45 Roper (10.1016/j.phro.2023.100515_b0125) 2023 Harrison (10.1016/j.phro.2023.100515_b0045) 2022; 34 Sherer (10.1016/j.phro.2023.100515_b0015) 2021; 160 Han (10.1016/j.phro.2023.100515_b0025) 2008; 11 Hindocha (10.1016/j.phro.2023.100515_b0120) 2023; 35 Wong (10.1016/j.phro.2023.100515_b0060) 2020; 144 Babier (10.1016/j.phro.2023.100515_b0105) 2021; 48 Costea (10.1016/j.phro.2023.100515_b0050) 2022; 177 Thor (10.1016/j.phro.2023.100515_b0020) 2021; 109 Barragan-Montero (10.1016/j.phro.2023.100515_b0055) 2022 Vrtovec (10.1016/j.phro.2023.100515_b0030) 2020 Nikolov (10.1016/j.phro.2023.100515_b0140) 2021 Nelms (10.1016/j.phro.2023.100515_b0005) 2012; 82 Johnston (10.1016/j.phro.2023.100515_b0080) 2022; 23 Heilemann (10.1016/j.phro.2023.100515_b0040) 2022; 32 Bakx (10.1016/j.phro.2023.100515_b0065) 2023 Cardenas (10.1016/j.phro.2023.100515_b0035) 2019; 29 |
| References_xml | – volume: 34 start-page: 74 year: 2022 end-page: 88 ident: b0045 article-title: Machine Learning for Auto-Segmentation in Radiotherapy Planning publication-title: Clin Oncol – start-page: 15 year: 2015 ident: b0090 article-title: Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool publication-title: BMC Med Imaging – volume: 48 start-page: 5562 year: 2021 end-page: 5566 ident: b0100 article-title: Technical Note: Dose prediction for radiation therapy using feature-based losses and One Cycle Learning publication-title: Med Phys – volume: 48 start-page: 5549 year: 2021 end-page: 5561 ident: b0105 article-title: OpenKBP: The open-access knowledge-based planning grand challenge and dataset publication-title: Med Phys – volume: 50 start-page: 5088 year: 2023 end-page: 5094 ident: b0110 article-title: Generating deliverable DICOM RT treatment plans for prostate VMAT by predicting MLC motion sequences with an encoder-decoder network publication-title: Med Phys – volume: 144 start-page: 152 year: 2020 end-page: 158 ident: b0060 article-title: Comparing deep learning-based auto-segmentation of organs at risk and clinical target volumes to expert inter-observer variability in radiotherapy planning publication-title: Radiother Oncol – volume: 35 start-page: 219 year: 2023 end-page: 226 ident: b0120 article-title: Artificial Intelligence for Radiotherapy Auto-Contouring: Current Use, Perceptions of and Barriers to Implementation publication-title: Clin Oncol – start-page: 24 year: 2023 ident: b0125 article-title: Extensive upfront validation and testing are needed prior to the clinical implementation of AI-based auto-segmentation tools publication-title: J Appl Clin Med Phys – volume: 11 start-page: 434 year: 2008 end-page: 441 ident: b0025 article-title: Atlas-Based Auto-segmentation of Head and Neck CT Images publication-title: Med Image Comput Comput Assist Interv – volume: 34 start-page: 684 year: 2016 end-page: 690 ident: b0010 article-title: Importance of Radiation Oncologist Experience Among Patients With Head-and-Neck Cancer Treated With Intensity-Modulated Radiation Therapy publication-title: J Clin Oncol – start-page: 13 year: 2023 ident: b0085 article-title: Comprehensive clinical evaluation of deep learning-based auto-segmentation for radiotherapy in patients with cervical cancer. Front publication-title: Oncol – volume: 32 start-page: 361 year: 2022 end-page: 368 ident: b0040 article-title: Can Generative Adversarial Networks help to overcome the limited data problem in segmentation? publication-title: Z Med Phys – volume: 22 start-page: 104 year: 2022 end-page: 110 ident: b0075 article-title: Real-world analysis of manual editing of deep learning contouring in the thorax region publication-title: Phys Imaging Radiat Oncol – volume: 13 start-page: 1 year: 2020 end-page: 6 ident: b0135 article-title: Evaluation of measures for assessing time-saving of automatic organ-at-risk segmentation in radiotherapy publication-title: Phys Imaging Radiat Oncol – start-page: 67 year: 2022 ident: b0055 article-title: Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency publication-title: Phys Med Biol – volume: 109 start-page: 1619 year: 2021 end-page: 1626 ident: b0020 article-title: Using Auto-Segmentation to Reduce Contouring and Dose Inconsistency in Clinical Trials: The Simulated Impact on RTOG 0617 publication-title: Int J Radiat Oncol Biol Phys – volume: 160 start-page: 185 year: 2021 end-page: 191 ident: b0015 article-title: Metrics to evaluate the performance of auto-segmentation for radiation treatment planning: A critical review publication-title: Radiother Oncol – start-page: 26 year: 2023 ident: b0065 article-title: Clinical evaluation of a deep learning segmentation model including manual adjustments afterwards for locally advanced breast cancer. Tech Innov Patient Support publication-title: Radiat Oncol – year: 2023 ident: b0115 article-title: Increasing Quality and Efficiency of the Radiotherapy Treatment Planning Process by Constructing and Implementing a Workflow-Monitoring Application publication-title: JCO Clin Cancer Inform – start-page: 23 year: 2021 ident: b0140 article-title: Clinically applicable segmentation of head and neck anatomy for radiotherapy: Deep learning algorithm development and validation study publication-title: J Med Internet Res – volume: 29 start-page: 185 year: 2019 end-page: 197 ident: b0035 article-title: Advances in Auto-Segmentation publication-title: Semin Radiat Oncol – volume: 23 start-page: 109 year: 2022 end-page: 117 ident: b0080 article-title: Dose-volume-based evaluation of convolutional neural network-based auto-segmentation of thoracic organs at risk publication-title: Phys Imaging Radiat Oncol – volume: 177 start-page: 61 year: 2022 end-page: 70 ident: b0050 article-title: Comparison of atlas-based and deep learning methods for organs at risk delineation on head-and-neck CT images using an automated treatment planning system publication-title: Radiother Oncol – volume: 159 start-page: 1 year: 2021 end-page: 7 ident: b0070 article-title: Clinical implementation of deep learning contour autosegmentation for prostate radiotherapy publication-title: Radiother Oncol – volume: 45 start-page: 5105 year: 2018 end-page: 5115 ident: b0095 article-title: Comparative evaluation of autocontouring in clinical practice: A practical method using the Turing test publication-title: Med Phys – volume: 82 start-page: 368 year: 2012 end-page: 378 ident: b0005 article-title: Variations in the contouring of organs at risk: Test case from a patient with oropharyngeal cancer publication-title: Int J Radiat Oncol Biol Phys – volume: 163 start-page: 136 year: 2021 end-page: 142 ident: b0130 article-title: The impact of organ-at-risk contour variations on automatically generated treatment plans for NSCLC publication-title: Radiother Oncol – start-page: 47 year: 2020 ident: b0030 article-title: Auto-segmentation of organs at risk for head and neck radiotherapy planning: From atlas-based to deep learning methods publication-title: Med Phys – start-page: 13 year: 2023 ident: 10.1016/j.phro.2023.100515_b0085 article-title: Comprehensive clinical evaluation of deep learning-based auto-segmentation for radiotherapy in patients with cervical cancer. Front publication-title: Oncol – volume: 11 start-page: 434 year: 2008 ident: 10.1016/j.phro.2023.100515_b0025 article-title: Atlas-Based Auto-segmentation of Head and Neck CT Images publication-title: Med Image Comput Comput Assist Interv – start-page: 26 year: 2023 ident: 10.1016/j.phro.2023.100515_b0065 article-title: Clinical evaluation of a deep learning segmentation model including manual adjustments afterwards for locally advanced breast cancer. Tech Innov Patient Support publication-title: Radiat Oncol – volume: 144 start-page: 152 year: 2020 ident: 10.1016/j.phro.2023.100515_b0060 article-title: Comparing deep learning-based auto-segmentation of organs at risk and clinical target volumes to expert inter-observer variability in radiotherapy planning publication-title: Radiother Oncol doi: 10.1016/j.radonc.2019.10.019 – start-page: 15 year: 2015 ident: 10.1016/j.phro.2023.100515_b0090 article-title: Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool publication-title: BMC Med Imaging – year: 2023 ident: 10.1016/j.phro.2023.100515_b0115 article-title: Increasing Quality and Efficiency of the Radiotherapy Treatment Planning Process by Constructing and Implementing a Workflow-Monitoring Application publication-title: JCO Clin Cancer Inform doi: 10.1200/CCI.23.00005 – volume: 48 start-page: 5549 year: 2021 ident: 10.1016/j.phro.2023.100515_b0105 article-title: OpenKBP: The open-access knowledge-based planning grand challenge and dataset publication-title: Med Phys doi: 10.1002/mp.14845 – volume: 82 start-page: 368 year: 2012 ident: 10.1016/j.phro.2023.100515_b0005 article-title: Variations in the contouring of organs at risk: Test case from a patient with oropharyngeal cancer publication-title: Int J Radiat Oncol Biol Phys doi: 10.1016/j.ijrobp.2010.10.019 – volume: 32 start-page: 361 year: 2022 ident: 10.1016/j.phro.2023.100515_b0040 article-title: Can Generative Adversarial Networks help to overcome the limited data problem in segmentation? publication-title: Z Med Phys doi: 10.1016/j.zemedi.2021.11.006 – volume: 163 start-page: 136 year: 2021 ident: 10.1016/j.phro.2023.100515_b0130 article-title: The impact of organ-at-risk contour variations on automatically generated treatment plans for NSCLC publication-title: Radiother Oncol doi: 10.1016/j.radonc.2021.08.014 – start-page: 23 year: 2021 ident: 10.1016/j.phro.2023.100515_b0140 article-title: Clinically applicable segmentation of head and neck anatomy for radiotherapy: Deep learning algorithm development and validation study publication-title: J Med Internet Res – volume: 34 start-page: 684 year: 2016 ident: 10.1016/j.phro.2023.100515_b0010 article-title: Importance of Radiation Oncologist Experience Among Patients With Head-and-Neck Cancer Treated With Intensity-Modulated Radiation Therapy publication-title: J Clin Oncol doi: 10.1200/JCO.2015.63.9898 – start-page: 47 year: 2020 ident: 10.1016/j.phro.2023.100515_b0030 article-title: Auto-segmentation of organs at risk for head and neck radiotherapy planning: From atlas-based to deep learning methods publication-title: Med Phys – start-page: 67 year: 2022 ident: 10.1016/j.phro.2023.100515_b0055 article-title: Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency publication-title: Phys Med Biol – volume: 160 start-page: 185 year: 2021 ident: 10.1016/j.phro.2023.100515_b0015 article-title: Metrics to evaluate the performance of auto-segmentation for radiation treatment planning: A critical review publication-title: Radiother Oncol doi: 10.1016/j.radonc.2021.05.003 – volume: 29 start-page: 185 year: 2019 ident: 10.1016/j.phro.2023.100515_b0035 article-title: Advances in Auto-Segmentation publication-title: Semin Radiat Oncol doi: 10.1016/j.semradonc.2019.02.001 – volume: 45 start-page: 5105 year: 2018 ident: 10.1016/j.phro.2023.100515_b0095 article-title: Comparative evaluation of autocontouring in clinical practice: A practical method using the Turing test publication-title: Med Phys doi: 10.1002/mp.13200 – start-page: 24 year: 2023 ident: 10.1016/j.phro.2023.100515_b0125 article-title: Extensive upfront validation and testing are needed prior to the clinical implementation of AI-based auto-segmentation tools publication-title: J Appl Clin Med Phys – volume: 50 start-page: 5088 year: 2023 ident: 10.1016/j.phro.2023.100515_b0110 article-title: Generating deliverable DICOM RT treatment plans for prostate VMAT by predicting MLC motion sequences with an encoder-decoder network publication-title: Med Phys doi: 10.1002/mp.16545 – volume: 22 start-page: 104 year: 2022 ident: 10.1016/j.phro.2023.100515_b0075 article-title: Real-world analysis of manual editing of deep learning contouring in the thorax region publication-title: Phys Imaging Radiat Oncol doi: 10.1016/j.phro.2022.04.008 – volume: 109 start-page: 1619 year: 2021 ident: 10.1016/j.phro.2023.100515_b0020 article-title: Using Auto-Segmentation to Reduce Contouring and Dose Inconsistency in Clinical Trials: The Simulated Impact on RTOG 0617 publication-title: Int J Radiat Oncol Biol Phys doi: 10.1016/j.ijrobp.2020.11.011 – volume: 13 start-page: 1 year: 2020 ident: 10.1016/j.phro.2023.100515_b0135 article-title: Evaluation of measures for assessing time-saving of automatic organ-at-risk segmentation in radiotherapy publication-title: Phys Imaging Radiat Oncol doi: 10.1016/j.phro.2019.12.001 – volume: 23 start-page: 109 year: 2022 ident: 10.1016/j.phro.2023.100515_b0080 article-title: Dose-volume-based evaluation of convolutional neural network-based auto-segmentation of thoracic organs at risk publication-title: Phys Imaging Radiat Oncol doi: 10.1016/j.phro.2022.07.004 – volume: 48 start-page: 5562 year: 2021 ident: 10.1016/j.phro.2023.100515_b0100 article-title: Technical Note: Dose prediction for radiation therapy using feature-based losses and One Cycle Learning publication-title: Med Phys doi: 10.1002/mp.14774 – volume: 159 start-page: 1 year: 2021 ident: 10.1016/j.phro.2023.100515_b0070 article-title: Clinical implementation of deep learning contour autosegmentation for prostate radiotherapy publication-title: Radiother Oncol doi: 10.1016/j.radonc.2021.02.040 – volume: 34 start-page: 74 year: 2022 ident: 10.1016/j.phro.2023.100515_b0045 article-title: Machine Learning for Auto-Segmentation in Radiotherapy Planning publication-title: Clin Oncol doi: 10.1016/j.clon.2021.12.003 – volume: 177 start-page: 61 year: 2022 ident: 10.1016/j.phro.2023.100515_b0050 article-title: Comparison of atlas-based and deep learning methods for organs at risk delineation on head-and-neck CT images using an automated treatment planning system publication-title: Radiother Oncol doi: 10.1016/j.radonc.2022.10.029 – volume: 35 start-page: 219 year: 2023 ident: 10.1016/j.phro.2023.100515_b0120 article-title: Artificial Intelligence for Radiotherapy Auto-Contouring: Current Use, Perceptions of and Barriers to Implementation publication-title: Clin Oncol doi: 10.1016/j.clon.2023.01.014 |
| SSID | ssj0002793530 |
| Score | 2.3919845 |
| Snippet | Tools for auto-segmentation in radiotherapy are widely available, but guidelines for clinical implementation are missing. The goal was to develop a workflow... Background and purpose: Tools for auto-segmentation in radiotherapy are widely available, but guidelines for clinical implementation are missing. The goal was... |
| SourceID | doaj pubmedcentral proquest pubmed crossref elsevier |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 100515 |
| SubjectTerms | Auto-segmentation Deep Learning Original Radiotherapy Segmentation |
| Title | Clinical Implementation and Evaluation of Auto-Segmentation Tools for Multi-Site Contouring in Radiotherapy |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S2405631623001069 https://www.ncbi.nlm.nih.gov/pubmed/38111502 https://www.proquest.com/docview/2903861538 https://pubmed.ncbi.nlm.nih.gov/PMC10726238 https://doaj.org/article/f30049b496ff47d2ab8927afe690f7ca |
| Volume | 28 |
| WOSCitedRecordID | wos001135921700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2405-6316 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002793530 issn: 2405-6316 databaseCode: DOA dateStart: 20170101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2405-6316 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002793530 issn: 2405-6316 databaseCode: M~E dateStart: 20170101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagQohLxZsUqIzEDUU4thPbx4K24kArRAvam-X4ASlLgrq7SFz47YwdZ9kFqVy45JBMEtsztr-RZ75B6Lm1tVFWmZI3DYkXXkrPYyaXEioYSlSqRfDxrTg9lfO5erdV6ivGhI30wOPAvQyREkq1XDUhcOGoaaWiwgQPbl0QNkEjItSWM3WRjtMUqxnJWTJjQBcMTsz2oyxGBtSxDu7WTpQI-3c2pL8B559xk1sb0fFttJ8RJD4aW34HXfP9XXTzJJ-R30NfMtXnAifm3685uajHpnd4tiH3xkPAR-vVUJ75T79lzodhscQAZHHKzC3PAJHiyGA1pHRG3PX4vXFdTtv6cR99OJ6dv35T5pIKpa0pWcHSJivieE2lDa2vLbPg0nBlQ9MIEriqPLWmtqDW2lSWiMYqJwNpHaOVA-eDPUB7_dD7Rwhz04C3JaWqWkB9zoHfB6KwZgVYs1oWClRNw6tt5huPZS8Wegosu9BRJTqqRI8qKdCLzTvfRraNK6VfRa1tJCNTdroB9qOz_eh_2U-B2KRzPSWjwvIJH-qu_PWzyTw0zMd4yGJ6P6yXmirCZETRskAPR3PZNBDQUQTgtEByx5B2erD7pO8-J85v8NIpIFV58D_6_Bjdin0ZYxKfoL3V5do_RTfs91W3vDxE18VcHqb5BNeTn7Nfu0Mmaw |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Clinical+Implementation+and+Evaluation+of+Auto-Segmentation+Tools+for+Multi-Site+Contouring+in+Radiotherapy&rft.jtitle=Physics+and+imaging+in+radiation+oncology&rft.au=Heilemann%2C+Gerd&rft.au=Buschmann%2C+Martin&rft.au=Lechner%2C+Wolfgang&rft.au=Dick%2C+Vincent&rft.date=2023-10-01&rft.pub=Elsevier+B.V&rft.issn=2405-6316&rft.eissn=2405-6316&rft.volume=28&rft_id=info:doi/10.1016%2Fj.phro.2023.100515&rft.externalDocID=S2405631623001069 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2405-6316&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2405-6316&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2405-6316&client=summon |