Clinical implementation of deep learning robust IMPT planning in oropharyngeal cancer patients: A blinded clinical study
•Deep learning planning automates robust proton therapy planning for oropharyngeal cancer.•Plan quality was evaluated in blinded retrospective and prospective studies.•Deep learning plans were preferred over or comparable to manual plans in 92% of the patients. This study aimed to evaluate the plan...
Gespeichert in:
Veröffentlicht in: | Radiotherapy and oncology 2024-11, Vol.200, p.110522, Article 110522 |
---|---|
Hauptverfasser: | , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | 110522 |
container_title | Radiotherapy and oncology |
container_volume | 200 |
creator | van Bruggen, Ilse G. van Dijk, Marije Brinkman-Akker, Minke J. Löfman, Fredrik Langendijk, Johannes A. Both, Stefan Korevaar, E.W. |
description | •Deep learning planning automates robust proton therapy planning for oropharyngeal cancer.•Plan quality was evaluated in blinded retrospective and prospective studies.•Deep learning plans were preferred over or comparable to manual plans in 92% of the patients.
This study aimed to evaluate the plan quality of our deep learning-based automated treatment planning method for robustly optimized intensity-modulated proton therapy (IMPT) plans in patients with oropharyngeal carcinoma (OPC). The assessment was conducted through a retrospective and prospective study, blindly comparing manual plans with deep learning plans.
A set of 95 OPC patients was split into training (n = 60), configuration (n = 10), test retrospective study (n = 10), and test prospective study (n = 15). Our deep learning optimization (DLO) method combines IMPT dose prediction using a deep learning model with a robust mimicking optimization algorithm. Dosimetrists manually adjusted the DLO plan for individual patients. In both studies, manual plans and manually adjusted deep learning (mDLO) plans were blindly assessed by a radiation oncologist, a dosimetrist, and a physicist, through visual inspection, clinical goal evaluation, and comparison of normal tissue complication probability values. mDLO plans were completed within an average time of 2.5 h. In comparison, the manual planning process typically took around 2 days.
In the retrospective study, in 10/10 (100%) patients, the mDLO plans were preferred, while in the prospective study, 9 out of 15 (60%) mDLO plans were preferred. In 4 out of the remaining 6 cases, the manual and mDLO plans were considered comparable in quality. Differences between manual and mDLO plans were limited.
This study showed a high preference for mDLO plans over manual IMPT plans, with 92% of cases considering mDLO plans comparable or superior in quality for OPC patients. |
doi_str_mv | 10.1016/j.radonc.2024.110522 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3101796241</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S016781402403500X</els_id><sourcerecordid>3101796241</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2022-9f62d030eb93495f6abe3dc244cf871a5a6c61a1ba6b665b51e2c4736c1e43603</originalsourceid><addsrcrecordid>eNp9kE1P3DAURS1UxExp_0FVedlNpv6Kk3RRaTQqZaRBsIC15dgv1KPETu0ElX-PIcCyK0vWeffqHoS-ULKhhMrvx03UNnizYYSJDaWkZOwErWldNQWp6-oDWmesKmoqyAp9TOlICGGEV2doxRsmeC35Gv3b9c47o3vshrGHAfykJxc8Dh22ACPuQUfv_D2OoZ3ThPdXN7d47LV_-XQZjGH8o-Ojv4ecYrQ3EPGYQ3JU-oG3uM0NFiw2b01pmu3jJ3Ta6T7B59f3HN1d_LrdXRaH69_73fZQmLyLFU0nmSWcQNtw0ZSd1C1wa5gQpqsrqkstjaSatlq2UpZtSYEZUXFpKAguCT9H35bcMYa_M6RJDS4Z6PMCCHNSPMusGskEzahYUBNDShE6NUY35GmKEvXsXB3V4lw9O1eL83z29bVhbgew70dvkjPwcwEg73xwEFUy2Y4B6yKYSdng_t_wBLQBlVk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3101796241</pqid></control><display><type>article</type><title>Clinical implementation of deep learning robust IMPT planning in oropharyngeal cancer patients: A blinded clinical study</title><source>ScienceDirect Freedom Collection (Elsevier)</source><creator>van Bruggen, Ilse G. ; van Dijk, Marije ; Brinkman-Akker, Minke J. ; Löfman, Fredrik ; Langendijk, Johannes A. ; Both, Stefan ; Korevaar, E.W.</creator><creatorcontrib>van Bruggen, Ilse G. ; van Dijk, Marije ; Brinkman-Akker, Minke J. ; Löfman, Fredrik ; Langendijk, Johannes A. ; Both, Stefan ; Korevaar, E.W.</creatorcontrib><description>•Deep learning planning automates robust proton therapy planning for oropharyngeal cancer.•Plan quality was evaluated in blinded retrospective and prospective studies.•Deep learning plans were preferred over or comparable to manual plans in 92% of the patients.
This study aimed to evaluate the plan quality of our deep learning-based automated treatment planning method for robustly optimized intensity-modulated proton therapy (IMPT) plans in patients with oropharyngeal carcinoma (OPC). The assessment was conducted through a retrospective and prospective study, blindly comparing manual plans with deep learning plans.
A set of 95 OPC patients was split into training (n = 60), configuration (n = 10), test retrospective study (n = 10), and test prospective study (n = 15). Our deep learning optimization (DLO) method combines IMPT dose prediction using a deep learning model with a robust mimicking optimization algorithm. Dosimetrists manually adjusted the DLO plan for individual patients. In both studies, manual plans and manually adjusted deep learning (mDLO) plans were blindly assessed by a radiation oncologist, a dosimetrist, and a physicist, through visual inspection, clinical goal evaluation, and comparison of normal tissue complication probability values. mDLO plans were completed within an average time of 2.5 h. In comparison, the manual planning process typically took around 2 days.
In the retrospective study, in 10/10 (100%) patients, the mDLO plans were preferred, while in the prospective study, 9 out of 15 (60%) mDLO plans were preferred. In 4 out of the remaining 6 cases, the manual and mDLO plans were considered comparable in quality. Differences between manual and mDLO plans were limited.
This study showed a high preference for mDLO plans over manual IMPT plans, with 92% of cases considering mDLO plans comparable or superior in quality for OPC patients.</description><identifier>ISSN: 0167-8140</identifier><identifier>ISSN: 1879-0887</identifier><identifier>EISSN: 1879-0887</identifier><identifier>DOI: 10.1016/j.radonc.2024.110522</identifier><identifier>PMID: 39243863</identifier><language>eng</language><publisher>Ireland: Elsevier B.V</publisher><subject>Automated treatment planning ; Deep learning ; Head and neck cancer ; IMPT ; Robust evaluation ; Robust optimization</subject><ispartof>Radiotherapy and oncology, 2024-11, Vol.200, p.110522, Article 110522</ispartof><rights>2024 The Author(s)</rights><rights>Copyright © 2024. Published by Elsevier B.V.</rights><rights>Copyright © 2024 The Author(s). Published by Elsevier B.V. All rights reserved.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c2022-9f62d030eb93495f6abe3dc244cf871a5a6c61a1ba6b665b51e2c4736c1e43603</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.radonc.2024.110522$$EHTML$$P50$$Gelsevier$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/39243863$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>van Bruggen, Ilse G.</creatorcontrib><creatorcontrib>van Dijk, Marije</creatorcontrib><creatorcontrib>Brinkman-Akker, Minke J.</creatorcontrib><creatorcontrib>Löfman, Fredrik</creatorcontrib><creatorcontrib>Langendijk, Johannes A.</creatorcontrib><creatorcontrib>Both, Stefan</creatorcontrib><creatorcontrib>Korevaar, E.W.</creatorcontrib><title>Clinical implementation of deep learning robust IMPT planning in oropharyngeal cancer patients: A blinded clinical study</title><title>Radiotherapy and oncology</title><addtitle>Radiother Oncol</addtitle><description>•Deep learning planning automates robust proton therapy planning for oropharyngeal cancer.•Plan quality was evaluated in blinded retrospective and prospective studies.•Deep learning plans were preferred over or comparable to manual plans in 92% of the patients.
This study aimed to evaluate the plan quality of our deep learning-based automated treatment planning method for robustly optimized intensity-modulated proton therapy (IMPT) plans in patients with oropharyngeal carcinoma (OPC). The assessment was conducted through a retrospective and prospective study, blindly comparing manual plans with deep learning plans.
A set of 95 OPC patients was split into training (n = 60), configuration (n = 10), test retrospective study (n = 10), and test prospective study (n = 15). Our deep learning optimization (DLO) method combines IMPT dose prediction using a deep learning model with a robust mimicking optimization algorithm. Dosimetrists manually adjusted the DLO plan for individual patients. In both studies, manual plans and manually adjusted deep learning (mDLO) plans were blindly assessed by a radiation oncologist, a dosimetrist, and a physicist, through visual inspection, clinical goal evaluation, and comparison of normal tissue complication probability values. mDLO plans were completed within an average time of 2.5 h. In comparison, the manual planning process typically took around 2 days.
In the retrospective study, in 10/10 (100%) patients, the mDLO plans were preferred, while in the prospective study, 9 out of 15 (60%) mDLO plans were preferred. In 4 out of the remaining 6 cases, the manual and mDLO plans were considered comparable in quality. Differences between manual and mDLO plans were limited.
This study showed a high preference for mDLO plans over manual IMPT plans, with 92% of cases considering mDLO plans comparable or superior in quality for OPC patients.</description><subject>Automated treatment planning</subject><subject>Deep learning</subject><subject>Head and neck cancer</subject><subject>IMPT</subject><subject>Robust evaluation</subject><subject>Robust optimization</subject><issn>0167-8140</issn><issn>1879-0887</issn><issn>1879-0887</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kE1P3DAURS1UxExp_0FVedlNpv6Kk3RRaTQqZaRBsIC15dgv1KPETu0ElX-PIcCyK0vWeffqHoS-ULKhhMrvx03UNnizYYSJDaWkZOwErWldNQWp6-oDWmesKmoqyAp9TOlICGGEV2doxRsmeC35Gv3b9c47o3vshrGHAfykJxc8Dh22ACPuQUfv_D2OoZ3ThPdXN7d47LV_-XQZjGH8o-Ojv4ecYrQ3EPGYQ3JU-oG3uM0NFiw2b01pmu3jJ3Ta6T7B59f3HN1d_LrdXRaH69_73fZQmLyLFU0nmSWcQNtw0ZSd1C1wa5gQpqsrqkstjaSatlq2UpZtSYEZUXFpKAguCT9H35bcMYa_M6RJDS4Z6PMCCHNSPMusGskEzahYUBNDShE6NUY35GmKEvXsXB3V4lw9O1eL83z29bVhbgew70dvkjPwcwEg73xwEFUy2Y4B6yKYSdng_t_wBLQBlVk</recordid><startdate>20241101</startdate><enddate>20241101</enddate><creator>van Bruggen, Ilse G.</creator><creator>van Dijk, Marije</creator><creator>Brinkman-Akker, Minke J.</creator><creator>Löfman, Fredrik</creator><creator>Langendijk, Johannes A.</creator><creator>Both, Stefan</creator><creator>Korevaar, E.W.</creator><general>Elsevier B.V</general><scope>6I.</scope><scope>AAFTH</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>20241101</creationdate><title>Clinical implementation of deep learning robust IMPT planning in oropharyngeal cancer patients: A blinded clinical study</title><author>van Bruggen, Ilse G. ; van Dijk, Marije ; Brinkman-Akker, Minke J. ; Löfman, Fredrik ; Langendijk, Johannes A. ; Both, Stefan ; Korevaar, E.W.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2022-9f62d030eb93495f6abe3dc244cf871a5a6c61a1ba6b665b51e2c4736c1e43603</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Automated treatment planning</topic><topic>Deep learning</topic><topic>Head and neck cancer</topic><topic>IMPT</topic><topic>Robust evaluation</topic><topic>Robust optimization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>van Bruggen, Ilse G.</creatorcontrib><creatorcontrib>van Dijk, Marije</creatorcontrib><creatorcontrib>Brinkman-Akker, Minke J.</creatorcontrib><creatorcontrib>Löfman, Fredrik</creatorcontrib><creatorcontrib>Langendijk, Johannes A.</creatorcontrib><creatorcontrib>Both, Stefan</creatorcontrib><creatorcontrib>Korevaar, E.W.</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Radiotherapy and oncology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>van Bruggen, Ilse G.</au><au>van Dijk, Marije</au><au>Brinkman-Akker, Minke J.</au><au>Löfman, Fredrik</au><au>Langendijk, Johannes A.</au><au>Both, Stefan</au><au>Korevaar, E.W.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Clinical implementation of deep learning robust IMPT planning in oropharyngeal cancer patients: A blinded clinical study</atitle><jtitle>Radiotherapy and oncology</jtitle><addtitle>Radiother Oncol</addtitle><date>2024-11-01</date><risdate>2024</risdate><volume>200</volume><spage>110522</spage><pages>110522-</pages><artnum>110522</artnum><issn>0167-8140</issn><issn>1879-0887</issn><eissn>1879-0887</eissn><abstract>•Deep learning planning automates robust proton therapy planning for oropharyngeal cancer.•Plan quality was evaluated in blinded retrospective and prospective studies.•Deep learning plans were preferred over or comparable to manual plans in 92% of the patients.
This study aimed to evaluate the plan quality of our deep learning-based automated treatment planning method for robustly optimized intensity-modulated proton therapy (IMPT) plans in patients with oropharyngeal carcinoma (OPC). The assessment was conducted through a retrospective and prospective study, blindly comparing manual plans with deep learning plans.
A set of 95 OPC patients was split into training (n = 60), configuration (n = 10), test retrospective study (n = 10), and test prospective study (n = 15). Our deep learning optimization (DLO) method combines IMPT dose prediction using a deep learning model with a robust mimicking optimization algorithm. Dosimetrists manually adjusted the DLO plan for individual patients. In both studies, manual plans and manually adjusted deep learning (mDLO) plans were blindly assessed by a radiation oncologist, a dosimetrist, and a physicist, through visual inspection, clinical goal evaluation, and comparison of normal tissue complication probability values. mDLO plans were completed within an average time of 2.5 h. In comparison, the manual planning process typically took around 2 days.
In the retrospective study, in 10/10 (100%) patients, the mDLO plans were preferred, while in the prospective study, 9 out of 15 (60%) mDLO plans were preferred. In 4 out of the remaining 6 cases, the manual and mDLO plans were considered comparable in quality. Differences between manual and mDLO plans were limited.
This study showed a high preference for mDLO plans over manual IMPT plans, with 92% of cases considering mDLO plans comparable or superior in quality for OPC patients.</abstract><cop>Ireland</cop><pub>Elsevier B.V</pub><pmid>39243863</pmid><doi>10.1016/j.radonc.2024.110522</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0167-8140 |
ispartof | Radiotherapy and oncology, 2024-11, Vol.200, p.110522, Article 110522 |
issn | 0167-8140 1879-0887 1879-0887 |
language | eng |
recordid | cdi_proquest_miscellaneous_3101796241 |
source | ScienceDirect Freedom Collection (Elsevier) |
subjects | Automated treatment planning Deep learning Head and neck cancer IMPT Robust evaluation Robust optimization |
title | Clinical implementation of deep learning robust IMPT planning in oropharyngeal cancer patients: A blinded clinical study |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T08%3A43%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Clinical%20implementation%20of%20deep%20learning%20robust%20IMPT%20planning%20in%20oropharyngeal%20cancer%20patients:%20A%20blinded%20clinical%20study&rft.jtitle=Radiotherapy%20and%20oncology&rft.au=van%20Bruggen,%20Ilse%20G.&rft.date=2024-11-01&rft.volume=200&rft.spage=110522&rft.pages=110522-&rft.artnum=110522&rft.issn=0167-8140&rft.eissn=1879-0887&rft_id=info:doi/10.1016/j.radonc.2024.110522&rft_dat=%3Cproquest_cross%3E3101796241%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3101796241&rft_id=info:pmid/39243863&rft_els_id=S016781402403500X&rfr_iscdi=true |