A personalized DVH prediction model for HDR brachytherapy in cervical cancer treatment
PurposeAlthough the knowledge-based dose-volume histogram (DVH) prediction has been largely researched and applied in External Beam Radiation Therapy, it is still less investigated in the domain of brachytherapy. The purpose of this study is to develop a reliable DVH prediction method for high-dose-...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.967436/full |
| _version_ | 1818494776920506368 |
|---|---|
| author | Zhen Li Kehui Chen Zhenyu Yang Qingyuan Zhu Xiaojing Yang Zhaobin Li Jie Fu |
| author_facet | Zhen Li Kehui Chen Zhenyu Yang Qingyuan Zhu Xiaojing Yang Zhaobin Li Jie Fu |
| author_sort | Zhen Li |
| collection | DOAJ |
| description | PurposeAlthough the knowledge-based dose-volume histogram (DVH) prediction has been largely researched and applied in External Beam Radiation Therapy, it is still less investigated in the domain of brachytherapy. The purpose of this study is to develop a reliable DVH prediction method for high-dose-rate brachytherapy plans.MethodA DVH prediction workflow combining kernel density estimation (KDE), k-nearest neighbor (kNN), and principal component analysis (PCA) was proposed. PCA and kNN were first employed together to select similar patients based on principal component directions. 79 cervical cancer patients with different applicators inserted was included in this study. The KDE model was built based on the relationship between distance-to-target (DTH) and the dose in selected cases, which can be subsequently used to estimate the dose probability distribution in the validation set. Model performance of bladder and rectum was quantified by |ΔD2cc|, |ΔD1cc|, |ΔD0.1cc|, |ΔDmax|, and |ΔDmean| in the form of mean and standard deviation. The model performance between KDE only and the combination of kNN, PCA, and KDE was compared.Result20, 30 patients were selected for rectum and bladder based on KNN and PCA, respectively. The absolute residual between the actual plans and the predicted plans were 0.38 ± 0.29, 0.4 ± 0.32, 0.43 ± 0.36, 0.97 ± 0.66, and 0.13 ± 0.99 for |ΔD2cc|, |ΔD1cc|, |ΔD0.1cc|, |ΔDmax|, and |ΔDmean| in the bladder, respectively. For rectum, the corresponding results were 0.34 ± 0.27, 0.38 ± 0.33, 0.63 ± 0.57, 1.41 ± 0.99 and 0.23 ± 0.17, respectively. The combination of kNN, PCA, and KDE showed a significantly better prediction performance than KDE only, with an improvement of 30.3% for the bladder and 33.3% for the rectum.ConclusionIn this study, a knowledge-based machine learning model was proposed and verified to accurately predict the DVH for new patients. This model is proved to be effective in our testing group in the workflow of HDR brachytherapy. |
| first_indexed | 2024-12-10T18:11:03Z |
| format | Article |
| id | doaj.art-b447df7b6d2941cba5f754f8436602fa |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-12-10T18:11:03Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-b447df7b6d2941cba5f754f8436602fa2022-12-22T01:38:26ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2022-08-011210.3389/fonc.2022.967436967436A personalized DVH prediction model for HDR brachytherapy in cervical cancer treatmentZhen Li0Kehui Chen1Zhenyu Yang2Qingyuan Zhu3Xiaojing Yang4Zhaobin Li5Jie Fu6Shanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, ChinaShuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, Shanghai, ChinaDuke University, Durham, NC, United StatesShanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, ChinaShanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, ChinaShanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, ChinaShanghai Jiao Tong University Affiliated Sixth People's Hospital, Shanghai, ChinaPurposeAlthough the knowledge-based dose-volume histogram (DVH) prediction has been largely researched and applied in External Beam Radiation Therapy, it is still less investigated in the domain of brachytherapy. The purpose of this study is to develop a reliable DVH prediction method for high-dose-rate brachytherapy plans.MethodA DVH prediction workflow combining kernel density estimation (KDE), k-nearest neighbor (kNN), and principal component analysis (PCA) was proposed. PCA and kNN were first employed together to select similar patients based on principal component directions. 79 cervical cancer patients with different applicators inserted was included in this study. The KDE model was built based on the relationship between distance-to-target (DTH) and the dose in selected cases, which can be subsequently used to estimate the dose probability distribution in the validation set. Model performance of bladder and rectum was quantified by |ΔD2cc|, |ΔD1cc|, |ΔD0.1cc|, |ΔDmax|, and |ΔDmean| in the form of mean and standard deviation. The model performance between KDE only and the combination of kNN, PCA, and KDE was compared.Result20, 30 patients were selected for rectum and bladder based on KNN and PCA, respectively. The absolute residual between the actual plans and the predicted plans were 0.38 ± 0.29, 0.4 ± 0.32, 0.43 ± 0.36, 0.97 ± 0.66, and 0.13 ± 0.99 for |ΔD2cc|, |ΔD1cc|, |ΔD0.1cc|, |ΔDmax|, and |ΔDmean| in the bladder, respectively. For rectum, the corresponding results were 0.34 ± 0.27, 0.38 ± 0.33, 0.63 ± 0.57, 1.41 ± 0.99 and 0.23 ± 0.17, respectively. The combination of kNN, PCA, and KDE showed a significantly better prediction performance than KDE only, with an improvement of 30.3% for the bladder and 33.3% for the rectum.ConclusionIn this study, a knowledge-based machine learning model was proposed and verified to accurately predict the DVH for new patients. This model is proved to be effective in our testing group in the workflow of HDR brachytherapy.https://www.frontiersin.org/articles/10.3389/fonc.2022.967436/fullmachine learningbrachytherapycervical cancerdose predictionradiation oncology |
| spellingShingle | Zhen Li Kehui Chen Zhenyu Yang Qingyuan Zhu Xiaojing Yang Zhaobin Li Jie Fu A personalized DVH prediction model for HDR brachytherapy in cervical cancer treatment Frontiers in Oncology machine learning brachytherapy cervical cancer dose prediction radiation oncology |
| title | A personalized DVH prediction model for HDR brachytherapy in cervical cancer treatment |
| title_full | A personalized DVH prediction model for HDR brachytherapy in cervical cancer treatment |
| title_fullStr | A personalized DVH prediction model for HDR brachytherapy in cervical cancer treatment |
| title_full_unstemmed | A personalized DVH prediction model for HDR brachytherapy in cervical cancer treatment |
| title_short | A personalized DVH prediction model for HDR brachytherapy in cervical cancer treatment |
| title_sort | personalized dvh prediction model for hdr brachytherapy in cervical cancer treatment |
| topic | machine learning brachytherapy cervical cancer dose prediction radiation oncology |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.967436/full |
| work_keys_str_mv | AT zhenli apersonalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT kehuichen apersonalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT zhenyuyang apersonalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT qingyuanzhu apersonalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT xiaojingyang apersonalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT zhaobinli apersonalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT jiefu apersonalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT zhenli personalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT kehuichen personalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT zhenyuyang personalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT qingyuanzhu personalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT xiaojingyang personalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT zhaobinli personalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment AT jiefu personalizeddvhpredictionmodelforhdrbrachytherapyincervicalcancertreatment |