Automatic Planning of Whole Breast Radiation Therapy Using Machine Learning Models
Purpose: To develop an automatic treatment planning system for whole breast radiation therapy (WBRT) based on two intensity-modulated tangential fields, enabling near-real-time planning.Methods and Materials: A total of 40 WBRT plans from a single institution were included in this study under IRB ap...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2019-08-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fonc.2019.00750/full |
| _version_ | 1811240386424733696 |
|---|---|
| author | Yang Sheng Yang Sheng Taoran Li Taoran Li Sua Yoo Sua Yoo Fang-Fang Yin Fang-Fang Yin Rachel Blitzblau Janet K. Horton Yaorong Ge Q. Jackie Wu Q. Jackie Wu |
| author_facet | Yang Sheng Yang Sheng Taoran Li Taoran Li Sua Yoo Sua Yoo Fang-Fang Yin Fang-Fang Yin Rachel Blitzblau Janet K. Horton Yaorong Ge Q. Jackie Wu Q. Jackie Wu |
| author_sort | Yang Sheng |
| collection | DOAJ |
| description | Purpose: To develop an automatic treatment planning system for whole breast radiation therapy (WBRT) based on two intensity-modulated tangential fields, enabling near-real-time planning.Methods and Materials: A total of 40 WBRT plans from a single institution were included in this study under IRB approval. Twenty WBRT plans, 10 with single energy (SE, 6MV) and 10 with mixed energy (ME, 6/15MV), were randomly selected as training dataset to develop the methodology for automatic planning. The rest 10 SE cases and 10 ME cases served as validation. The auto-planning process consists of three steps. First, an energy prediction model was developed to automate energy selection. This model establishes an anatomy-energy relationship based on principle component analysis (PCA) of the gray level histograms from training cases' digitally reconstructed radiographs (DRRs). Second, a random forest (RF) model generates an initial fluence map using the selected energies. Third, the balance of overall dose contribution throughout the breast tissue is realized by automatically selecting anchor points and applying centrality correction. The proposed method was tested on the validation dataset. Non-parametric equivalence test was performed for plan quality metrics using one-sided Wilcoxon Signed-Rank test.Results: For validation, the auto-planning system suggested same energy choices as clinical-plans in 19 out of 20 cases. The mean (standard deviation, SD) of percent target volume covered by 100% prescription dose was 82.5% (4.2%) for auto-plans, and 79.3% (4.8%) for clinical-plans (p > 0.999). Mean (SD) volume receiving 105% Rx were 95.2 cc (90.7 cc) for auto-plans and 83.9 cc (87.2 cc) for clinical-plans (p = 0.108). Optimization time for auto-plan was <20 s while clinical manual planning takes between 30 min and 4 h.Conclusions: We developed an automatic treatment planning system that generates WBRT plans with optimal energy selection, clinically comparable plan quality, and significant reduction in planning time, allowing for near-real-time planning. |
| first_indexed | 2024-04-12T13:19:15Z |
| format | Article |
| id | doaj.art-24a4d9caaf38450c9afaf9ce57894d36 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-12T13:19:15Z |
| publishDate | 2019-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-24a4d9caaf38450c9afaf9ce57894d362022-12-22T03:31:32ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2019-08-01910.3389/fonc.2019.00750469525Automatic Planning of Whole Breast Radiation Therapy Using Machine Learning ModelsYang Sheng0Yang Sheng1Taoran Li2Taoran Li3Sua Yoo4Sua Yoo5Fang-Fang Yin6Fang-Fang Yin7Rachel Blitzblau8Janet K. Horton9Yaorong Ge10Q. Jackie Wu11Q. Jackie Wu12Department of Radiation Oncology, Duke University Medical Center, Durham, NC, United StatesMedical Physics Graduate Program, Duke University Medical Center, Durham, NC, United StatesMedical Physics Graduate Program, Duke University Medical Center, Durham, NC, United StatesDepartment of Radiation Oncology, University of Pennsylvania, Philadelphia, PA, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, NC, United StatesMedical Physics Graduate Program, Duke University Medical Center, Durham, NC, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, NC, United StatesMedical Physics Graduate Program, Duke University Medical Center, Durham, NC, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, NC, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, NC, United StatesDepartment of Software and Information Systems, University of North Carolina, Charlotte, NC, United StatesDepartment of Radiation Oncology, Duke University Medical Center, Durham, NC, United StatesMedical Physics Graduate Program, Duke University Medical Center, Durham, NC, United StatesPurpose: To develop an automatic treatment planning system for whole breast radiation therapy (WBRT) based on two intensity-modulated tangential fields, enabling near-real-time planning.Methods and Materials: A total of 40 WBRT plans from a single institution were included in this study under IRB approval. Twenty WBRT plans, 10 with single energy (SE, 6MV) and 10 with mixed energy (ME, 6/15MV), were randomly selected as training dataset to develop the methodology for automatic planning. The rest 10 SE cases and 10 ME cases served as validation. The auto-planning process consists of three steps. First, an energy prediction model was developed to automate energy selection. This model establishes an anatomy-energy relationship based on principle component analysis (PCA) of the gray level histograms from training cases' digitally reconstructed radiographs (DRRs). Second, a random forest (RF) model generates an initial fluence map using the selected energies. Third, the balance of overall dose contribution throughout the breast tissue is realized by automatically selecting anchor points and applying centrality correction. The proposed method was tested on the validation dataset. Non-parametric equivalence test was performed for plan quality metrics using one-sided Wilcoxon Signed-Rank test.Results: For validation, the auto-planning system suggested same energy choices as clinical-plans in 19 out of 20 cases. The mean (standard deviation, SD) of percent target volume covered by 100% prescription dose was 82.5% (4.2%) for auto-plans, and 79.3% (4.8%) for clinical-plans (p > 0.999). Mean (SD) volume receiving 105% Rx were 95.2 cc (90.7 cc) for auto-plans and 83.9 cc (87.2 cc) for clinical-plans (p = 0.108). Optimization time for auto-plan was <20 s while clinical manual planning takes between 30 min and 4 h.Conclusions: We developed an automatic treatment planning system that generates WBRT plans with optimal energy selection, clinically comparable plan quality, and significant reduction in planning time, allowing for near-real-time planning.https://www.frontiersin.org/article/10.3389/fonc.2019.00750/fullwhole breast radiation therapybreast cancermachine learningauto planningrandom forestelectronic compensation |
| spellingShingle | Yang Sheng Yang Sheng Taoran Li Taoran Li Sua Yoo Sua Yoo Fang-Fang Yin Fang-Fang Yin Rachel Blitzblau Janet K. Horton Yaorong Ge Q. Jackie Wu Q. Jackie Wu Automatic Planning of Whole Breast Radiation Therapy Using Machine Learning Models Frontiers in Oncology whole breast radiation therapy breast cancer machine learning auto planning random forest electronic compensation |
| title | Automatic Planning of Whole Breast Radiation Therapy Using Machine Learning Models |
| title_full | Automatic Planning of Whole Breast Radiation Therapy Using Machine Learning Models |
| title_fullStr | Automatic Planning of Whole Breast Radiation Therapy Using Machine Learning Models |
| title_full_unstemmed | Automatic Planning of Whole Breast Radiation Therapy Using Machine Learning Models |
| title_short | Automatic Planning of Whole Breast Radiation Therapy Using Machine Learning Models |
| title_sort | automatic planning of whole breast radiation therapy using machine learning models |
| topic | whole breast radiation therapy breast cancer machine learning auto planning random forest electronic compensation |
| url | https://www.frontiersin.org/article/10.3389/fonc.2019.00750/full |
| work_keys_str_mv | AT yangsheng automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT yangsheng automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT taoranli automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT taoranli automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT suayoo automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT suayoo automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT fangfangyin automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT fangfangyin automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT rachelblitzblau automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT janetkhorton automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT yaorongge automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT qjackiewu automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels AT qjackiewu automaticplanningofwholebreastradiationtherapyusingmachinelearningmodels |