Application of kernel density estimation in predicting bone marrow dose of radiation therapy for gynecological tumors
Cong Xiufeng1, Chen Jun1, Zhang Jingchao1, Zhang Xiaoting1, Lu Zaiming2
1Department of Oncology, Shengjing Hospital of China Medical University, Shenyang 110004, China; 2Department of Radiology, Shengjing Hospital of China Medical University, Shenyang 110004, China
Abstract：Objective To predict the dose of lumbosacral spine (LS) and pelvic bone marrow (PBM) based on kernel density estimation (KDE) in patients with gynecological tumors. Methods Fifteen patients with gynecological tumors receiving radiotherapy plans with dose limitation for LS and PBM in our hospital were selected as training data for machine learning. Another 10 cases were selected as the data for model validation. The minimum directional distance between the dose point in the organs and the edge of the planned target volume for the LS and PBM was calculated. Model training was performed by KDE. The accuracy of the model prediction was evaluated by the root mean square error. The model was utilized to predict the actual planned doses of the LS and PBM, and a linear fitting was performed on the predicted dose volume histogram (DVH) and actual results. The prediction effect was assessed by the goodness of fit R2. Results In terms of the DVH parameters required by the planner, the prediction doses from the model were similar to those of the verification plans:the difference of PBM V40Gy was 2.0%, the difference of the mean dose was 1.6Gy, and the difference of LS V10Gy was -0.4%. In the unrequired DVH parameters, except for the PBM V10Gy, the predicted values of the model were significantly high. The difference between the DVH predicted by the model and the actual plan was small, and the R2of the LS and PBM were 0.988 and 0.995, respectively. Conclusions The model based on KDE method can accurately predict the doses of the LS and PBM. This model can also be used as a method to ensure the quality of the plan, and improve the consistency and quality of the plan.
Cong Xiufeng,Chen Jun,Zhang Jingchao et al. Application of kernel density estimation in predicting bone marrow dose of radiation therapy for gynecological tumors[J]. Chinese Journal of Radiation Oncology, 2021, 30(3): 262-265.
[1] Nicholas S,Chen L,Choflet A,et al.Pelvic radiation and normal tissue toxicity[J].Semin Radiat Oncol,2017,27(4):358-369.DOI:10.1016/j.semradonc.2017.04.010. [2] Mell LK,Sirák I,Wei L,et al.Bone marrow-sparing intensity modulated radiation therapy with concurrent cisplatin for stage Ⅰ b-IVA cervical cancer:an international multicenter phase Ⅱ clinical trial (INTERTECC-2)[J].Int J Radiat Oncol Biol Phys,2017,97(3):536-545.DOI:10.1016/j.ijrobp.2016.11.027. [3] Jodda A,Urbański B,Piotrowski T,et al.Relations between doses cumulated in bone marrow and dose delivery techniques during radiation therapy of cervical and endometrial cancer[J].Phys Med,2017,36(1):54-59.DOI:10.1016/j.ejmp.2017.03.006. [4] Folkert MR,Shih KK,Abu-Rustum NR,et al.Postoperative pelvic intensity-modulated radiotherapy and concurrent chemotherapy in intermediate-and high-risk cervical cancer[J].Gynecol Oncol,2013,128(2):288-293.DOI:10.1016/j.ygyno.2012.11.012. [5] Wan J,Liu K,Li K,et al.Can dosimetric parameters predict acute hematologic toxicity in rectal cancer patients treated with intensity-modulated pelvic radiotherapy?[J].Radiat Oncol,2015,10:162.DOI:10.1186/s13014-015-0454-0. [6] Bortfeld T.IMRT:a review and preview[J].Phys Med Biol,2006,51(13):R363-R379.DOI:10.1088/0031-9155/51/13/R21. [7] Chang A,Hung A,Cheung F,et al.Comparison of planning quality and efficiency between conventional and knowledge-based algorithms in nasopharyngeal cancer patients using intensity modulated radiation therapy[J].Int J Radiat Oncol Biol Phys,2016,95(3):981-990.DOI:10.1016/j.ijrobp.2016.02.017. [8] Berry SL,Ma R,Boczkowski A,et al.Evaluating inter-campus plan consistency using a knowledge based planning model[J].Radiother Oncol,2016,120(2):349-355.DOI:10.1016/j.radonc.2016.06.010. [9] Lin JC,Tsai JT,Chang CC,et al.Comparing treatment plan in all locations of esophageal cancer:volumetric modulated arc therapy versus intensity-modulated radiotherapy[J].Medicine (Baltimore),2015,94(17):e750.DOI:10.1097/MD.0000000000000750 [10] Ma M,Kovalchuk N,Buyyounouski MK,et al.Dosimetric features-driven machine learning model for DVH prediction in VMAT treatment planning[J].Med Phys,2019,46(2):857-867.DOI:10.1002/mp.13334. [11] Fan J,Wang J,Zhang Z,et al.Iterative dataset optimization in automated planning:implementation for breast and rectal cancer radiotherapy[J].Med Phys,2017,44(6):2515-2531.DOI:10.1002/mp.12232. [12] Xu H,Lu J,Wang J,et al.Implement a knowledge-based automated dose volume histogram prediction module in Pinnacle3 treatment planning system for plan quality assurance and guidance[J].J Appl Clin Med Phys,2019,20(8):134-140.DOI:10.1002/acm2.12689. [13] Zhang J,Ge Y,Sheng Y,et al.Modeling of multiple planning target volumes for head and neck treatments in knowledge-based treatment planning[J].Med Phys,2019,46(9):3812-3822.DOI:10.1002/mp.13679. [14] Mayo CS,Phillips M,McNutt TR,et al.Treatment data and technical process challenges for practical big data efforts in radiation oncology[J].Med Phys,2018,45(10):e793-e810.DOI:10.1002/mp.13114. [15] Skarpman-Munter J,Sjölund J.Dose-volume histogram prediction using density estimation[J].Phys Med Biol,2015,60(17):6923-6936.DOI:10.1088/0031-9155/60/17/6923. [16] Alpuche AJ,Cordero MM,Sasaki D,et al.Creation of knowledge-based planning models intended for large scale distribution:minimizing the effect of outlier plans[J].J Appl Clin Med Phys,2018,19(3):215-226.DOI:10.1002/acm2.12322.
2021, Vol. 30 
