Predicting Total Dwell Time of IPSA Plan Based on Machine Learning and Dose Calculation Models

Abstract
Figure/Table
References
Related Citation (0)

Download: PDF (261 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Objective To establish two models based on machine learning and dose calculation algorithm that can be used for the prediction of the total dwell time and rapid quality control of brachytherapy plans.Methods A total of 1042 cases of treated gynecologic oncology patients were selected, of which 512 were used as training data to establish the model and the rest were used as test data. Each treatment plan optimized by inverse planning simulated annealing with all three catheters of the Fletcher applicator. The source strength S_k, prescription dose D, source dwell time t, and tumor volume V were recorded for each case. R_V was defined as S_k·t/D. In accordance with the prescription dosage calculation formula in the planning system and machine learning method, the following equations were established: R_V=kV^2/3 and R_V=a+b·V+c·V². The R² correlation coefficient represents the accuracy of the results.Result The dose calculation algorithm-based model is R_V=1272×V^2/3, R²=0.959, whereas the machine learning-based model is R_V=258.8×V-0.359×V²+5110, R²=0.961. The treatment time prediction of the two models, each having 13 and 15 cases, respectively, has an error rate of more than 10%, and the dose calculation algorithm -based method is more accurate.Conclusion The treatment time can be quickly predicted according to the planning target volume, and the two prediction models can be used as a way of quality control.

Key words： brachytherapy simulated annealing reverse plan quality control prediction

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Xiufeng Cong
	Jun Chen
	Jingchao Zhang
	Xiaoting Zhang
	Wei Zheng

Cite this article:

Xiufeng Cong,Jun Chen,Jingchao Zhang, et al. Predicting Total Dwell Time of IPSA Plan Based on Machine Learning and Dose Calculation Models[J]. Chinese Journal of Biomedical Engineering, 2020, 29(1): 16-20.

URL:

http://manu32.magtech.com.cn/Jwk_zgswyx_en/EN/ OR http://manu32.magtech.com.cn/Jwk_zgswyx_en/EN/Y2020/V29/I1/16

[1] Han K, Milosevic M, Fyles A, et al.Trends in the utilization of brachytherapy in cervical cancer in the United States[J]. Int J Radiat Oncol Biol Phys, 2013, 87(1):111-119.
[2] Derks K, Steenhuijsen J, van den Berg H A, et al.Impact of brachytherapy technique (2D versus 3D) on outcome following radiotherapy of cervical cancer[J]. J Contemp Brachytherapy, 2018, 10(1):17-25.
[3] Ribeiro I, Janssen H, De Brabandere M, et al.Long term experience with 3D image guided brachytherapy and clinical outcome in cervical cancer patients[J]. Radiother Oncol, 2016, 120(3):447-454.
[4] Haie-Meder C, Potter R, Van Limbergen E, et al. Recommendations from Gynaecological (GYN) GEC-ESTRO Working Group (I): concepts and terms in 3D image based 3D treatment planning in cervix cancer brachytherapy with emphasis on MRI assessment of GTV and CTV[J].Radiother Oncol, 2005, 74(3):235-245.
[5] Potter R, Haie-Meder C, Van Limbergen E, et al. Recommendations from gynaecological (GYN) GEC ESTRO working group (II): concepts and terms in 3D image-based treatment planning in cervix cancer brachytherapy-3D dose volume parameters and aspects of 3D image-based anatomy, radiation physics, radiobiology[J].Radiother Oncol, 2006, 78(1):67-77.
[6] Rijkmans E C, Nout R A, Rutten I H H M, et al. Improved survival of patients with cervical cancer treated with image-guided brachytherapy compared with conventional brachytherapy[J]. Gynecologic Oncology, 2014, 135(2):231-238.
[7] Soliman A S, Owrangi A, Ravi A, et al.Metal artefacts in MRI-guided brachytherapy of cervical cancer[J].J Contemp Brachytherapy, 2016, 8(4):363-369.
[8] Trifiletti D M, Grover S, Libby B, et al. Trends in cervical cancer brachytherapy volume suggest case volume is not the primary driver of poor compliance rates with brachytherapy delivery for locally advanced cervical cancer[J]. Brachytherapy, 2017, 16(3):547-551.
[9] Panettieri V, Smith R L, Mason N J, et al. Comparison of IPSA and HIPO inverse planning optimization algorithms for prostate HDR brachytherapy[J]. J Appl Clin Med Phys, 2014, 15(6):5055.
[10] Poder J, Whitaker M. Robustness of IPSA optimized high-dose-rate prostate brachytherapy treatment plans to catheter displacements[J]. J Contemp Brachytherapy, 2016, 8(3):201-207.
[11] Choi C H, Park S Y, Park J M, et al. Comparison of the IPSA and HIPO algorithms for interstitial tongue high-dose-rate brachytherapy[J]. PLoS One, 2018, 13(10):e205229.
[12] Smith R L, Panettieri V, Lancaster C, et al. The influence of the dwell time deviation constraint (DTDC) parameter on dosimetry with IPSA optimisation for HDR prostate brachytherapy[J]. Australas Phys Eng Sci Med, 2015, 38(1):55-61.
[13] Bibault J, Giraud P, Burgun A.Big Data and machine learning in radiation oncology: State of the art and future prospects[J]. Cancer Letters, 2016, 382(1):110-117.
[14] Li H, Galperin-Aizenberg M, Pryma D, et al. Unsupervised machine learning of radiomic features for predicting treatment response and overall survival of early stage non-small cell lung cancer patients treated with stereotactic body radiation therapy[J]. Radiother Oncol, 2018, 129(2):218-226.
[15] Sun B, Lam D, Yang D, et al. A machine learning approach to the accurate prediction of monitor units for a compact proton machine[J]. Med Phys, 2018, 45(5):2243-2251.
[16] Jarrett D, Stride E, Vallis K, et al. Applications and limitations of machine learning in radiation oncology[J]. Br J Radiol, 2019, 92(1100):20190001.
[17] Pedemonte S, Pierce L, Van Leemput K. A machine learning method for fast and accurate characterization of depth-of-interaction gamma cameras[J]. Phys Med Biol, 2017, 62(21):8376-8401.
[18] Sahiner B, Pezeshk A, Hadjiiski L M, et al. Deep learning in medical imaging and radiation therapy[J]. Med Phys, 2019, 46(1):e1-e36.
[19] Peng L, Parekh V, Huang P, et al. Distinguishing True Progression From Radionecrosis After Stereotactic Radiation Therapy for Brain Metastases With Machine Learning and Radiomics[J]. Int J Radiat Oncol Biol Phys, 2018, 102(4):1236-1243.
[20] Cui S, Luo Y, Tseng H H, et al. Combining handcrafted features with latent variables in machine learning for prediction of radiation-induced lung damage[J]. Med Phys, 2019, 46(5):2497-2511.
[21] Deist T M, Dankers F, Valdes G, et al. Machine learning algorithms for outcome prediction in (chemo)radiotherapy: An empirical comparison of classifiers[J]. Med Phys, 2018, 45(7):3449-3459.
[22] El N I, Brock K, Yu Y, et al. On the Fuzziness of Machine Learning, Neural Networks, and Artificial Intelligence in Radiation Oncology[J]. Int J Radiat Oncol Biol Phys, 2018, 100(1):1-4.
[23] El N I, Ruan D, Valdes G, et al. Machine learning and modeling: Data, validation, communication challenges[J]. Med Phys, 2018, 45(10):e834-e840.
[24] Rivard M J, Butler W M, Dewerd L A, et al. Update of AAPM task group No. 43 report: A revised AAPM protocol for brachytherapy dose calculations (vol 31, pg 633, 2004)[J]. Med Phys, 2004, 31(12):3532-3533.
[25] Das R K, Bradley K A, Nelson I A, et al. Quality assurance of treatment plans for interstitial and intracavitary high-dose-rate brachytherapy[J]. Brachytherapy, 2006, 5(1):56-60.
[26] Oyekunle E O, Akinlade B I, Jimoh M A. Study of the relationships between brachytherapy plan parameters in an attempt to verify total dwell time in vaginal cylinder applications[J]. J Appl Clin Med Phys, 2018, 19(4):68-74.
[27] Carmona V, Perez-Calatayud J, Lliso F, et al. A program for the independent verification of brachytherapy planning system calculations[J]. J Contemp Brachytherapy, 2010, 2(3):129-133.
[28] Nkiwane K S, Andersen E, Champoudry J, et al. Total reference air kerma can accurately predict isodose surface volumes in cervix cancer brachytherapy. A multicenter study[J].Brachytherapy, 2017, 16(6):1184-1191.
[29] Mayo C S, Ulin K. A method for checking high dose rate treatment times for vaginal applicators[J]. J Appl Clin Med Phys, 2001, 2(4):184-190.
[30] Wadi-Ramahi S, Alnajjar W, Mahmood R, et al. Failure modes and effects analysis in image-guided high-dose-rate brachytherapy: Quality control optimization to reduce errors in treatment volume[J]. Brachytherapy, 2016, 15(5):669-678.
[31] Tian Z, Yen A, Zhou Z, et al. A machine-learning-based prediction model of fistula formation after interstitial brachytherapy for locally advanced gynecological malignancies[J]. Brachytherapy, 2019, 18(4):530-538.
[32] Nicolae A, Morton G, Chung H, et al. Evaluation of a Machine-Learning Algorithm for Treatment Planning in Prostate Low-Dose-Rate Brachytherapy[J]. Int J Radiat Oncol Biol Phys, 2017, 97(4):822-829.
[33] Roy S, Subramani V, Singh K, et al. Study of the effects of dwell time deviation constraints on inverse planning simulated annealing optimized plans of intracavitary brachytherapy of cancer cervix[J]. J Cancer Res Ther, 2019, 15(6):1370-1376.