Evaluation of three predictive models of knowledge-based treatment strategies for radiotherapy
Wu Aiqian1, Li Yongbao2, Qi Mengke1, Jia Qiyuan1, Guo Futong1, Lu Xingyu1, Liu Yuliang1, Zhou Linghong1, Song Ting1, Chen Chaomin1
1School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; 2Department of Radiation Oncology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
Abstract：Objective To compare the accuracy and generalized robustness of three predictive models of knowledge-based treatment strategies for radiotherapy for optimized model selection. Methods The clinical radiotherapy plans of 45 prostate cancer (PC) cases and 25 nasopharyngeal cancer (NPC) cases were collected, and analyzed using three models (Z,L and S model),proposed by Zhu et al, Appenzoller et al and Shiraishi et al, respectively, to predict the dose-volume histogram (DVH) of bladder and rectum on PC cases and that of left and right parotid on NPC cases. The prediction error was measured by the difference of area under the predicted DVH and the clinical DVH curves (|V(pre_DVH)-V(clin_DVH)|),where a smaller prediction error implies a greater prediction accuracy. The accuracies of these three models were compared on the single organ at risk (OAR), and the generalized robustness of models was evaluated and compared by calculating the standard deviation of the prediction accuracy on different OAR. Results For bladder and rectum, the prediction error of L model (0.114 and 0.163,respectively) was significantly higher than those values of Z and S models (≤0.071,P<0.05);for left parotid gland, the predicted error of S model (0.033) did not present significant difference from those values of Z and L models (≤0.025,P>0.05);for right parotid gland, S model (0.033) demonstrated significantly higher prediction error than those of Z and L models (≤0.028,P<0.05). Regarding different OAR,S model showed a lower standard deviation of prediction accuracy when comparing to Z and L models (0.016,0.018 and 0.060,respectively). Conclusions In the prediction of DVH in bladder and rectum of PC,Z and S models were more accurate than L model. In contrast, Z and L models demonstrated higher accuracy than S model in the prediction of left and right parotid glands of NPC. In respect to different OAR, the generalized robustness of S model was superior than the other two models.
Wu Aiqian,Li Yongbao,Qi Mengke et al. Evaluation of three predictive models of knowledge-based treatment strategies for radiotherapy[J]. Chinese Journal of Radiation Oncology, 2020, 29(5): 363-373.
[1] Younge KC, Marsh RB, Owen D, et al. Improving quality and consistency in NRG oncology radiation therapy oncology group 0631 for spine radiosurgery via knowledge-based planning[J]. Int J Radiat Oncol Biol Phys, 2018, 100(4):1067-1074. DOI:10.1016/j.ijrobp.2017.12.276.
[2] Faught AM, Olsen L, Schubert L, et al. Functional-guided radiotherapy using knowledge-based planning[J]. Radiother Oncol, 2018, 129(3):494-498. DOI:10.1016/j.radonc.2018.03.025.
[3] 贾启源,郭芙彤,吴艾茜,等. 基于危及器官预测剂量分布与gEUD混合目标的调强放疗计划优化[J]. 中华放射医学与防护杂志, 2019, 39(6):422-427. DOI:10.3760/cma.j.issn.0254-5098.2019.06.004.
Jia QY, Guo FT, Wu AQ, et al. OAR predicted dose distribution and gEUD based treatment planning optimization for IMRT[J]. Chin J Radiat Oncol, 2019, 39(6):422-427. DOI:10.3760/cma.j.issn.0254-5098.2019.06.004.
[4] 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.
[5] Shiraishi S, Moore KL. Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy[J]. Med Phys, 2016, 43(1):378-387. DOI:10.1118/1.4938583.
[6] Wu B, Ricchetti F, Sanguineti G, et al. Patient geometry-driven information retrieval for IMRT treatment plan quality control[J]. Med Phys, 2009, 36(12):5497-5505. DOI:10.1118/1.3253464.
[7] Appenzoller LM, Michalski JM, Thorstad WL, et al. Predicting dose-volume histograms for organs-at-risk in IMRT planning[J]. Med Phys, 2012, 39(12):7446-7461. DOI:10.1118/1.4761864.
[8] Zhu X, Ge Y, Li T, et al. A planning quality evaluation tool for prostate adaptive IMRT based on machine learning[J]. Med Phys, 2011, 38(2):719-726. DOI:10.1118/1.3539749.
[9] Wall PDH, Carver RL, Fontenot JD. An improved distance-to-dose correlation for predicting bladder and rectum dose-volumes in knowledge-based VMAT planning for prostate cancer[J]. Phys Med Biol, 2018, 63(1):15035. DOI:10.1088/1361-6560/aa9a30.
[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] McIntosh C, Welch M, McNiven A, et al. Fully automated treatment planning for head and neck radiotherapy using a voxel-based dose prediction and dose mimicking method[J]. Phys Med Biol, 2017, 62(15):5926. DOI:10.1088/1361-6560/aa71f8.
[12] Barragán-Montero AM, Nguyen D, Lu W, et al. Three-dimensional dose prediction for lung IMRT patients with deep neural networks:robust learning from heterogeneous beam configurations[J]. Med Phys, 2019, 46(8):3679-3691. DOI:10.1002/mp.13597.
[13] Kajikawa T, Kadoya N, Ito K, et al. A convolutional neural network approach for IMRT dose distribution prediction in prostate cancer patients[J]. J Radiat Res, 2019, 60(5):685-693. DOI:10.1093/jrr/rrz051.
[14] 孔繁图,麦燕华,亓孟科,等. 基于神经网络学习方法的放疗计划三维剂量分布预测[J]. 南方医科大学学报, 2018, 38(6):683-690. DOI:10.3969/j.issn.1673-4254.2018.06.07.
Kong FT, Mai YH, Qi MK, et al. Prediction of three-dimensional dose distribution in intensity-modulated radiation therapy based on neural network learning[J]. J South Med Univ, 2018, 38(06):683-690. DOI:10.3969/j.issn.1673-4254.2018.06.07.
[15] Ma M, Kovalchuk N, Buyyounouski MK, et al. Incorporating dosimetric features into the prediction of 3D VMAT dose distributions using deep convolutional neural network[J]. Phys Med Biol, 2019, 64(12):125017. DOI:10.1088/1361-6560/ab2146.
2020, Vol. 29 
