Establishment and interpretation of the gamma pass rate prediction model based on radiomics for different intensity-modulated radiotherapy techniques in the pelvis
Background and objectives: Implementation of patient-specific quality assurance (PSQA) is a crucial aspect of precise radiotherapy. Various machine learning-based models have showed potential as virtual quality assurance tools, being capable of accurately predicting the dose verification results of...
Saved in:
Published in | Frontiers in physics Vol. 11 |
---|---|
Main Authors | , , , , , , |
Format | Journal Article |
Language | English |
Published |
Frontiers Media S.A
10.08.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Background
and objectives:
Implementation of patient-specific quality assurance (PSQA) is a crucial aspect of precise radiotherapy. Various machine learning-based models have showed potential as virtual quality assurance tools, being capable of accurately predicting the dose verification results of fixed-beam intensity-modulated radiation therapy (IMRT) or volumetric modulated arc therapy (VMAT) plans, thereby ensuring safe and efficient treatment for patients. However, there has been no research yet that simultaneously integrates different IMRT techniques to predict the gamma pass rate (GPR) and explain the model.
Methods:
Retrospective analysis of the 3D dosimetric verification results based on measurements with gamma pass rate criteria of 3%/2 mm and 10% dose threshold of 409 pelvic IMRT and VMAT plans was carried out. Radiomics features were extracted from the dose files, from which the XGBoost algorithm based on SHapley Additive exPlanations (SHAP) values was used to select the optimal feature subset as the input for the prediction model. The study employed four different machine learning algorithms, namely, random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM), to construct predictive models. Sensitivity, specificity, F1 score, and AUC value were calculated to evaluate the classification performance of these models. The SHAP values were utilized to perform a related interpretive analysis on the best performing model.
Results:
The sensitivities and specificities of the RF, AdaBoost, XGBoost, and LightGBM models were 0.96, 0.82, 0.93, and 0.89, and 0.38, 0.54, 0.62, and 0.62, respectively. The F1 scores and area under the curve (AUC) values were 0.86, 0.81, 0.88, and 0.86, and 0.81, 0.77, 0.85, and 0.83, respectively. The explanation of the model output based on SHAP values can provide a reference basis for medical physicists when adjusting the plan, thereby improving the efficiency and quality of treatment plans.
Conclusion:
It is feasible to use a machine learning method based on radiomics to establish a gamma pass rate classification prediction model for IMRT and VMAT plans in the pelvis. The XGBoost model performs better in classification than the other three tree-based ensemble models, and global explanations and single-sample explanations of the model output through SHAP values may offer reference for medical physicists to provide high-quality plans, promoting the clinical application and implementation of GPR prediction models, and providing safe and efficient personalized QA management for patients. |
---|---|
AbstractList | Backgroundand objectives: Implementation of patient-specific quality assurance (PSQA) is a crucial aspect of precise radiotherapy. Various machine learning-based models have showed potential as virtual quality assurance tools, being capable of accurately predicting the dose verification results of fixed-beam intensity-modulated radiation therapy (IMRT) or volumetric modulated arc therapy (VMAT) plans, thereby ensuring safe and efficient treatment for patients. However, there has been no research yet that simultaneously integrates different IMRT techniques to predict the gamma pass rate (GPR) and explain the model.Methods: Retrospective analysis of the 3D dosimetric verification results based on measurements with gamma pass rate criteria of 3%/2 mm and 10% dose threshold of 409 pelvic IMRT and VMAT plans was carried out. Radiomics features were extracted from the dose files, from which the XGBoost algorithm based on SHapley Additive exPlanations (SHAP) values was used to select the optimal feature subset as the input for the prediction model. The study employed four different machine learning algorithms, namely, random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM), to construct predictive models. Sensitivity, specificity, F1 score, and AUC value were calculated to evaluate the classification performance of these models. The SHAP values were utilized to perform a related interpretive analysis on the best performing model.Results: The sensitivities and specificities of the RF, AdaBoost, XGBoost, and LightGBM models were 0.96, 0.82, 0.93, and 0.89, and 0.38, 0.54, 0.62, and 0.62, respectively. The F1 scores and area under the curve (AUC) values were 0.86, 0.81, 0.88, and 0.86, and 0.81, 0.77, 0.85, and 0.83, respectively. The explanation of the model output based on SHAP values can provide a reference basis for medical physicists when adjusting the plan, thereby improving the efficiency and quality of treatment plans.Conclusion: It is feasible to use a machine learning method based on radiomics to establish a gamma pass rate classification prediction model for IMRT and VMAT plans in the pelvis. The XGBoost model performs better in classification than the other three tree-based ensemble models, and global explanations and single-sample explanations of the model output through SHAP values may offer reference for medical physicists to provide high-quality plans, promoting the clinical application and implementation of GPR prediction models, and providing safe and efficient personalized QA management for patients. Background and objectives: Implementation of patient-specific quality assurance (PSQA) is a crucial aspect of precise radiotherapy. Various machine learning-based models have showed potential as virtual quality assurance tools, being capable of accurately predicting the dose verification results of fixed-beam intensity-modulated radiation therapy (IMRT) or volumetric modulated arc therapy (VMAT) plans, thereby ensuring safe and efficient treatment for patients. However, there has been no research yet that simultaneously integrates different IMRT techniques to predict the gamma pass rate (GPR) and explain the model. Methods: Retrospective analysis of the 3D dosimetric verification results based on measurements with gamma pass rate criteria of 3%/2 mm and 10% dose threshold of 409 pelvic IMRT and VMAT plans was carried out. Radiomics features were extracted from the dose files, from which the XGBoost algorithm based on SHapley Additive exPlanations (SHAP) values was used to select the optimal feature subset as the input for the prediction model. The study employed four different machine learning algorithms, namely, random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM), to construct predictive models. Sensitivity, specificity, F1 score, and AUC value were calculated to evaluate the classification performance of these models. The SHAP values were utilized to perform a related interpretive analysis on the best performing model. Results: The sensitivities and specificities of the RF, AdaBoost, XGBoost, and LightGBM models were 0.96, 0.82, 0.93, and 0.89, and 0.38, 0.54, 0.62, and 0.62, respectively. The F1 scores and area under the curve (AUC) values were 0.86, 0.81, 0.88, and 0.86, and 0.81, 0.77, 0.85, and 0.83, respectively. The explanation of the model output based on SHAP values can provide a reference basis for medical physicists when adjusting the plan, thereby improving the efficiency and quality of treatment plans. Conclusion: It is feasible to use a machine learning method based on radiomics to establish a gamma pass rate classification prediction model for IMRT and VMAT plans in the pelvis. The XGBoost model performs better in classification than the other three tree-based ensemble models, and global explanations and single-sample explanations of the model output through SHAP values may offer reference for medical physicists to provide high-quality plans, promoting the clinical application and implementation of GPR prediction models, and providing safe and efficient personalized QA management for patients. |
Author | Tan, Jianfeng Yang, Xiaohua Pang, Jinmeng Chen, Luqiao Sun, Xiangshang Zhu, Jun Ni, Qianxi |
Author_xml | – sequence: 1 givenname: Qianxi surname: Ni fullname: Ni, Qianxi – sequence: 2 givenname: Jun surname: Zhu fullname: Zhu, Jun – sequence: 3 givenname: Luqiao surname: Chen fullname: Chen, Luqiao – sequence: 4 givenname: Jianfeng surname: Tan fullname: Tan, Jianfeng – sequence: 5 givenname: Jinmeng surname: Pang fullname: Pang, Jinmeng – sequence: 6 givenname: Xiangshang surname: Sun fullname: Sun, Xiangshang – sequence: 7 givenname: Xiaohua surname: Yang fullname: Yang, Xiaohua |
BookMark | eNpNkctO3TAQhi1EpVLKA3TnF8ipb3GcJUK0RUJiAxI7a2KPOUZJnNqm0nmevmiTc1DFai765pvF_4Wcz2lGQr5xtpPS9N_Dsj_sBBNyxwXvRNeekQshet0ooZ7PP_SfyVUpr4wxLtreCHVB_t6WCsMYy37CuVKYPY1zxbxkrFBjmmkKtO6RvsA0AV2gFJqhIl0BH92RmJLHkQ5Q0NN1zOBjmqIrNKRMfQwB8-bevHOJ9dCsB2_jKvEndtVnWA60otvP8fcblpU9Pl1w_BPLV_IpwFjw6r1ekqcft483v5r7h593N9f3jZNM18YAax0o33Ntgvat0n7QbtBBgut77YLq2sG1TPnOSac77lUnmTTBmR5NMPKS3J28PsGrXXKcIB9sgmiPi5RfLOQa3YhWr5fABQTQQQ29MmzQEJRkqkUWBlhd_ORyOZWSMfz3cWa30OwWmt1Cs--hyX8JiZJ3 |
Cites_doi | 10.3389/fnins.2021.744296 10.1002/mp.15393 10.1002/mp.16091 10.1007/s13246-014-0274-9 10.1016/s0360-3016(01)01664-9 10.1016/j.bbe.2022.06.007 10.1093/jrr/rry077 10.1016/j.imu.2020.100292 10.1118/1.4794929 10.1118/1.4953835 10.1016/j.compeleceng.2013.11.024 10.1118/1.598248 10.1118/1.3238104 10.1002/acm2.13824 10.1016/j.cmpb.2021.106584 10.1007/978-3-642-41136-6_5 10.1002/mp.12810 10.1016/j.ejmp.2021.01.071 10.1016/j.ijrobp.2019.07.049 10.1002/acm2.13375 10.1016/j.radonc.2020.07.031 10.1002/acm2.12161 10.1118/1.1591194 10.1002/acm2.13622 10.1023/A:1010933404324 10.1016/j.eswa.2017.02.017 10.1002/mp.13752 10.1016/S0140-6736(21)00233-6 10.1002/mp.13445 10.3389/frai.2020.577620 |
ContentType | Journal Article |
DBID | AAYXX CITATION DOA |
DOI | 10.3389/fphy.2023.1217275 |
DatabaseName | CrossRef Directory of Open Access Journals |
DatabaseTitle | CrossRef |
DatabaseTitleList | CrossRef |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2296-424X |
ExternalDocumentID | oai_doaj_org_article_6730a12afa6f4b9480b6af43045e0fba 10_3389_fphy_2023_1217275 |
GroupedDBID | 5VS 9T4 AAFWJ AAYXX ACGFS ACXDI ADBBV ALMA_UNASSIGNED_HOLDINGS BCNDV CITATION GROUPED_DOAJ IAO IEA IGS ISR KQ8 M~E OK1 |
ID | FETCH-LOGICAL-c306t-8a05ca4d9168f6d546db6cb6f3ac996cf475bc504d7c3c671d473038fc89e8f83 |
IEDL.DBID | DOA |
ISSN | 2296-424X |
IngestDate | Tue Dec 17 15:19:22 EST 2024 Thu Nov 21 23:51:30 EST 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c306t-8a05ca4d9168f6d546db6cb6f3ac996cf475bc504d7c3c671d473038fc89e8f83 |
OpenAccessLink | https://doaj.org/article/6730a12afa6f4b9480b6af43045e0fba |
ParticipantIDs | doaj_primary_oai_doaj_org_article_6730a12afa6f4b9480b6af43045e0fba crossref_primary_10_3389_fphy_2023_1217275 |
PublicationCentury | 2000 |
PublicationDate | 2023-08-10 |
PublicationDateYYYYMMDD | 2023-08-10 |
PublicationDate_xml | – month: 08 year: 2023 text: 2023-08-10 day: 10 |
PublicationDecade | 2020 |
PublicationTitle | Frontiers in physics |
PublicationYear | 2023 |
Publisher | Frontiers Media S.A |
Publisher_xml | – sequence: 0 name: Frontiers Media S.A |
References | Osman (B30) 2021; 22 Li (B17) 2019; 105 Lam (B12) 2019; 46 Ezzell (B4) 2009; 36 Nohara (B24) 2022; 214 Schapire (B27) 2013 Crowe (B8) 2014; 37 Marcílio (B23) 2020 Liu (B32) 2022; 42 Chan (B10) 2020; 3 Miften (B19) 2018; 45 Zhu (B15) 2023; 50 Lizar (B33) 2021; 82 Xia (B25) 2017; 78 Low (B6) 1998; 25 Chandrashekar (B22) 2014; 40 Siochi (B5) 2013; 40 Kusunoki (B7) 2022; 49 Breiman (B26) 2001; 45 Lundberg (B18) 2017 Thongsawad (B20) 2022; 23 Chen (B28) 2016 Portelance (B2) 2001; 51 Valdes (B11) 2016; 43 Wall (B16) 2020; 18 Salari (B13) 2023; 24 Chandra (B1) 2021; 398 Li (B14) 2021; 15 Kalet (B9) 2020; 47 Hirashima (B31) 2020; 153 Valdes (B34) 2017; 18 Arimura (B21) 2019; 60 Ezzell (B3) 2003; 30 Ke (B29) 2017 |
References_xml | – volume: 15 start-page: 744296 year: 2021 ident: B14 article-title: Improvement using planomics features on prediction and classification of patient-specific quality assurance using head and neck volumetric modulated arc therapy plan publication-title: Front Neurosci doi: 10.3389/fnins.2021.744296 contributor: fullname: Li – volume: 49 start-page: 727 year: 2022 ident: B7 article-title: Evaluation of prediction and classification performances in different machine learning models for patient‐specific quality assurance of head‐and‐neck VMAT plans publication-title: Med Phys doi: 10.1002/mp.15393 contributor: fullname: Kusunoki – volume: 50 start-page: 1205 year: 2023 ident: B15 article-title: Patient‐specific quality assurance prediction models based on machine learning for novel dual‐layered MLC linac publication-title: Med Phys doi: 10.1002/mp.16091 contributor: fullname: Zhu – volume: 37 start-page: 475 year: 2014 ident: B8 article-title: Treatment plan complexity metrics for predicting IMRT pre-treatment quality assurance results publication-title: Australas Phys Eng Sci Med doi: 10.1007/s13246-014-0274-9 contributor: fullname: Crowe – volume: 51 start-page: 261 year: 2001 ident: B2 article-title: Intensity-modulated radiation therapy (IMRT) reduces small bowel, rectum, and bladder doses in patients with cervical cancer receiving pelvic and para-aortic irradiation publication-title: Int J Radiat Oncol doi: 10.1016/s0360-3016(01)01664-9 contributor: fullname: Portelance – volume: 42 start-page: 856 year: 2022 ident: B32 article-title: Diagnosis of Parkinson's disease based on SHAP value feature selection publication-title: Biocybern Biomed Eng doi: 10.1016/j.bbe.2022.06.007 contributor: fullname: Liu – volume: 60 start-page: 150 year: 2019 ident: B21 article-title: Radiomics with artificial intelligence for precision medicine in radiation therapy publication-title: J Radiat Res doi: 10.1093/jrr/rry077 contributor: fullname: Arimura – volume: 18 start-page: 100292 year: 2020 ident: B16 article-title: Application and comparison of machine learning models for predicting quality assurance outcomes in radiation therapy treatment planning publication-title: Inform Med Unlocked doi: 10.1016/j.imu.2020.100292 contributor: fullname: Wall – start-page: 785 year: 2016 ident: B28 article-title: Xgboost: A scalable tree boosting system contributor: fullname: Chen – volume: 40 start-page: 070601 year: 2013 ident: B5 article-title: Patient-specific QA for IMRT should be performed using software rather than hardware methods: Point/Counterpoint publication-title: Med Phys doi: 10.1118/1.4794929 contributor: fullname: Siochi – volume: 43 start-page: 4323 year: 2016 ident: B11 article-title: A mathematical framework for virtual IMRT QA using machine learning publication-title: Med Phys doi: 10.1118/1.4953835 contributor: fullname: Valdes – volume: 40 start-page: 16 year: 2014 ident: B22 article-title: A survey on feature selection methods publication-title: Comput Electr Eng doi: 10.1016/j.compeleceng.2013.11.024 contributor: fullname: Chandrashekar – volume: 25 start-page: 656 year: 1998 ident: B6 article-title: A technique for the quantitative evaluation of dose distributions publication-title: Med Phys doi: 10.1118/1.598248 contributor: fullname: Low – volume: 36 start-page: 5359 year: 2009 ident: B4 article-title: IMRT commissioning: Multiple institution planning and dosimetry comparisons, a report from AAPM task group 119 publication-title: Med Phys doi: 10.1118/1.3238104 contributor: fullname: Ezzell – volume: 24 start-page: e13824 year: 2023 ident: B13 article-title: Using machine learning to predict gamma passing rate in volumetric-modulated arc therapy treatment plans publication-title: J Appl Clin Med Phys doi: 10.1002/acm2.13824 contributor: fullname: Salari – volume: 214 start-page: 106584 year: 2022 ident: B24 article-title: Explanation of machine learning models using shapley additive explanation and application for real data in hospital publication-title: Comput Meth Prog Bio doi: 10.1016/j.cmpb.2021.106584 contributor: fullname: Nohara – start-page: 37 volume-title: Empirical inference year: 2013 ident: B27 article-title: Explaining adaboost doi: 10.1007/978-3-642-41136-6_5 contributor: fullname: Schapire – start-page: 340 year: 2020 ident: B23 article-title: From explanations to feature selection: Assessing shap values as feature selection mechanism contributor: fullname: Marcílio – volume: 45 start-page: e53 year: 2018 ident: B19 article-title: Tolerance limits and methodologies for IMRT measurement-based verification QA: Recommendations of AAPM Task Group No. 218 publication-title: Med Phys doi: 10.1002/mp.12810 contributor: fullname: Miften – start-page: 3149 year: 2017 ident: B29 article-title: LightGBM: A highly efficient gradient boosting decision tree contributor: fullname: Ke – volume: 82 start-page: 100 year: 2021 ident: B33 article-title: Patient-specific IMRT QA verification using machine learning and gamma radiomics publication-title: Phys Med doi: 10.1016/j.ejmp.2021.01.071 contributor: fullname: Lizar – volume: 105 start-page: 893 year: 2019 ident: B17 article-title: Machine learning for patient-specific quality assurance of VMAT: Prediction and classification accuracy publication-title: Int J Radiat Oncol Biol Phys doi: 10.1016/j.ijrobp.2019.07.049 contributor: fullname: Li – volume: 22 start-page: 20 year: 2021 ident: B30 article-title: Applications of machine and deep learning to patient-specific IMRT/VMAT quality assurance publication-title: J Appl Clin Med Phys doi: 10.1002/acm2.13375 contributor: fullname: Osman – volume: 153 start-page: 250 year: 2020 ident: B31 article-title: Improvement of prediction and classification performance for gamma passing rate by using plan complexity and dosiomics features publication-title: Radiat Oncol doi: 10.1016/j.radonc.2020.07.031 contributor: fullname: Hirashima – volume: 18 start-page: 279 year: 2017 ident: B34 article-title: IMRT QA using machine learning: A multi-institutional validation publication-title: J Appl Clin Med Phys doi: 10.1002/acm2.12161 contributor: fullname: Valdes – volume: 30 start-page: 2089 year: 2003 ident: B3 article-title: Guidance document on delivery, treatment planning, and clinical implementation of IMRT: Report of the IMRT subcommittee of the AAPM radiation therapy committee publication-title: Med Phys doi: 10.1118/1.1591194 contributor: fullname: Ezzell – start-page: 4768 year: 2017 ident: B18 article-title: A unified approach to interpreting model predictions contributor: fullname: Lundberg – volume: 23 start-page: e13622 year: 2022 ident: B20 article-title: Predicting gamma evaluation results of patient‐specific head and neck volumetric‐modulated arc therapy quality assurance based on multileaf collimator patterns and fluence map features: A feasibility study publication-title: J Appl Clin Med Phys doi: 10.1002/acm2.13622 contributor: fullname: Thongsawad – volume: 45 start-page: 5 year: 2001 ident: B26 article-title: Random forests publication-title: Mach Learn doi: 10.1023/A:1010933404324 contributor: fullname: Breiman – volume: 78 start-page: 225 year: 2017 ident: B25 article-title: A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2017.02.017 contributor: fullname: Xia – volume: 46 start-page: 4666 year: 2019 ident: B12 article-title: Predicting gamma passing rates for portal dosimetry-based IMRT QA using machine learning publication-title: Med Phys doi: 10.1002/mp.13752 contributor: fullname: Lam – volume: 398 start-page: 171 year: 2021 ident: B1 article-title: Contemporary radiotherapy: Present and future publication-title: The Lancet doi: 10.1016/S0140-6736(21)00233-6 contributor: fullname: Chandra – volume: 47 start-page: e168 year: 2020 ident: B9 article-title: Radiation therapy quality assurance tasks and tools: The many roles of machine learning publication-title: Med Phys doi: 10.1002/mp.13445 contributor: fullname: Kalet – volume: 3 start-page: 577620 year: 2020 ident: B10 article-title: Integration of AI and machine learning in radiotherapy QA publication-title: Front Artif Intell doi: 10.3389/frai.2020.577620 contributor: fullname: Chan |
SSID | ssj0001259824 |
Score | 2.2872834 |
Snippet | Background
and objectives:
Implementation of patient-specific quality assurance (PSQA) is a crucial aspect of precise radiotherapy. Various machine... Backgroundand objectives: Implementation of patient-specific quality assurance (PSQA) is a crucial aspect of precise radiotherapy. Various machine... |
SourceID | doaj crossref |
SourceType | Open Website Aggregation Database |
SubjectTerms | gamma pass rate intensity-modulated radiation therapy machine learning model interpretation radiomics |
Title | Establishment and interpretation of the gamma pass rate prediction model based on radiomics for different intensity-modulated radiotherapy techniques in the pelvis |
URI | https://doaj.org/article/6730a12afa6f4b9480b6af43045e0fba |
Volume | 11 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LSwMxEA4iCF7EJ9YXOXgSYrebR7NHlZYi6MlCb0seG1mw29Kugr_HP-pMdlvakxePu8xmQ2Zgvi-ZfEPIbRA-FbrwLABTY4ILxzLgOwyVwnvcpJlxuN_x8qpGY_E8kZONVl9YE9bIAzcL11UQgqaXmmBUEDYTOrHKBIEHfEUSbAONknSDTDW7KyhMJ5pjTGBhWTfArO-xVzjqKUDSlluJaEOvPyaW4SE5aBEhfWhmckR2iuqY7MXKTLc8IT8DwG9xqwj38SgQf1puFQrSWaCA4ui7mU4NnQMYpij_QMHAl_HWAo3tbigmLE_hcWF8iZeRlxQQK121SKnjuBXWaDD4ANt6gXm0bS5pfdO14OsSbONP58XHV7k8JePh4O1pxNrOCswBRaiZNol0RnjAhjooL4XyVjmrAjcOCJALoi-tk4nwfccdeM0LcAPXwems0EHzM7JbzarinNC-N5mSHmCIA6ptje1ZGRIfFIzOM-475G61zPm8EdDIgXigT3L0SY4-yVufdMgjOmJtiNrX8QVERN5GRP5XRFz8xyCXZB8nxqL47RXZrRefxTXAj9rexEj7BUQU3Vs |
link.rule.ids | 314,780,784,864,2102,27924,27925 |
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=Establishment+and+interpretation+of+the+gamma+pass+rate+prediction+model+based+on+radiomics+for+different+intensity-modulated+radiotherapy+techniques+in+the+pelvis&rft.jtitle=Frontiers+in+physics&rft.au=Qianxi+Ni&rft.au=Qianxi+Ni&rft.au=Jun+Zhu&rft.au=Luqiao+Chen&rft.date=2023-08-10&rft.pub=Frontiers+Media+S.A&rft.eissn=2296-424X&rft.volume=11&rft_id=info:doi/10.3389%2Ffphy.2023.1217275&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_6730a12afa6f4b9480b6af43045e0fba |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2296-424X&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2296-424X&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2296-424X&client=summon |