A Feasibility Study for in Vivo Treatment Verification of IMRT Using Monte Carlo Dose Calculation and Deep Learning-based Modelling of EPID Detector Response

Overview

Journal Radiat Oncol

Publisher Biomed Central

Specialties Oncology
Radiology

Date 2022 Feb 11

PMID 35144641

Authors

Jun Zhang

Zhibiao Cheng

Ziting Fan

Qilin Zhang

Xile Zhang

Ruijie Yang

Junhai Wen

Affiliations

Soon will be listed here.

Abstract

Background: This paper describes the development of a predicted electronic portal imaging device (EPID) transmission image (TI) using Monte Carlo (MC) and deep learning (DL). The measured and predicted TI were compared for two-dimensional in vivo radiotherapy treatment verification.

Methods: The plan CT was pre-processed and combined with solid water and then imported into PRIMO. The MC method was used to calculate the dose distribution of the combined CT. The U-net neural network-based deep learning model was trained to predict EPID TI based on the dose distribution of solid water calculated by PRIMO. The predicted TI was compared with the measured TI for two-dimensional in vivo treatment verification.

Results: The EPID TI of 1500 IMRT fields were acquired, among which 1200, 150, and 150 fields were used as the training set, the validation set, and the test set, respectively. A comparison of the predicted and measured TI was carried out using global gamma analyses of 3%/3 mm and 2%/2 mm (5% threshold) to validate the model's accuracy. The gamma pass rates were greater than 96.7% and 92.3%, and the mean gamma values were 0.21 and 0.32, respectively.

Conclusions: Our method facilitates the modelling process more easily and increases the calculation accuracy when using the MC algorithm to simulate the EPID response, and has potential to be used for in vivo treatment verification in the clinic.

Citing Articles

A Novel Approach for Position Verification and Dose Calculation through Local MVCT Reconstruction.

Zhang J, Chen Z, Lei Y, Wen J Diagnostics (Basel). 2024; 14(5).

PMID: 38472954 PMC: 10931282. DOI: 10.3390/diagnostics14050482.

Invertible and Variable Augmented Network for Pretreatment Patient-Specific Quality Assurance Dose Prediction.

Zou Z, Gong C, Zeng L, Guan Y, Huang B, Yu X J Imaging Inform Med. 2024; 37(1):60-71.

PMID: 38343215 PMC: 10976903. DOI: 10.1007/s10278-023-00930-w.

AAPM Task Group Report 307: Use of EPIDs for Patient-Specific IMRT and VMAT QA.

Dogan N, Mijnheer B, Padgett K, Nalichowski A, Wu C, Nyflot M Med Phys. 2023; 50(8):e865-e903.

PMID: 37384416 PMC: 11230298. DOI: 10.1002/mp.16536.

Artificial intelligence assists precision medicine in cancer treatment.

Liao J, Li X, Gan Y, Han S, Rong P, Wang W Front Oncol. 2023; 12:998222.

PMID: 36686757 PMC: 9846804. DOI: 10.3389/fonc.2022.998222.

References

Siebers J, Kim J, Ko L, Keall P, Mohan R . Monte Carlo computation of dosimetric amorphous silicon electronic portal images. Med Phys. 2004; 31(7):2135-46. DOI: 10.1118/1.1764392. View

Greer P . Correction of pixel sensitivity variation and off-axis response for amorphous silicon EPID dosimetry. Med Phys. 2006; 32(12):3558-68. DOI: 10.1118/1.2128498. View

Xing Y, Nguyen D, Lu W, Yang M, Jiang S . Technical Note: A feasibility study on deep learning-based radiotherapy dose calculation. Med Phys. 2019; 47(2):753-758. PMC: 7864679. DOI: 10.1002/mp.13953. View

Rodriguez M, Sempau J, Brualla L . PRIMO: a graphical environment for the Monte Carlo simulation of Varian and Elekta linacs. Strahlenther Onkol. 2013; 189(10):881-6. DOI: 10.1007/s00066-013-0415-1. View

Fogliata A, Stravato A, Reggiori G, Tomatis S, Wurfel J, Scorsetti M . Collimator scatter factor: Monte Carlo and in-air measurements approaches. Radiat Oncol. 2018; 13(1):126. PMC: 6042423. DOI: 10.1186/s13014-018-1070-6. View

van Elmpt W, Nijsten S, Petit S, Mijnheer B, Lambin P, Dekker A . 3D in vivo dosimetry using megavoltage cone-beam CT and EPID dosimetry. Int J Radiat Oncol Biol Phys. 2009; 73(5):1580-7. DOI: 10.1016/j.ijrobp.2008.11.051. View

Van Uytven E, Van Beek T, McCowan P, Chytyk-Praznik K, Greer P, McCurdy B . Validation of a method for in vivo 3D dose reconstruction for IMRT and VMAT treatments using on-treatment EPID images and a model-based forward-calculation algorithm. Med Phys. 2015; 42(12):6945-54. DOI: 10.1118/1.4935199. View

Bacala A . Linac photon beam fine-tuning in PRIMO using the gamma-index analysis toolkit. Radiat Oncol. 2020; 15(1):8. PMC: 6945657. DOI: 10.1186/s13014-019-1455-1. View

Zhang S, Wang H, Tian S, Zhang X, Li J, Lei R . A slice classification model-facilitated 3D encoder-decoder network for segmenting organs at risk in head and neck cancer. J Radiat Res. 2020; 62(1):94-103. PMC: 7779351. DOI: 10.1093/jrr/rraa094. View

10.

Chytyk-Praznik K, VanUytven E, vanBeek T, Greer P, McCurdy B . Model-based prediction of portal dose images during patient treatment. Med Phys. 2013; 40(3):031713. DOI: 10.1118/1.4792203. View

11.

Wendling M, McDermott L, Mans A, Olaciregui-Ruiz I, Pecharroman-Gallego R, Sonke J . In aqua vivo EPID dosimetry. Med Phys. 2012; 39(1):367-77. DOI: 10.1118/1.3665709. View

12.

Zhen X, Chen J, Zhong Z, Hrycushko B, Zhou L, Jiang S . Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study. Phys Med Biol. 2017; 62(21):8246-8263. DOI: 10.1088/1361-6560/aa8d09. View

13.

Berry S, Sheu R, Polvorosa C, Wuu C . Implementation of EPID transit dosimetry based on a through-air dosimetry algorithm. Med Phys. 2012; 39(1):87-98. DOI: 10.1118/1.3665249. View

14.

Das I, Cao M, Cheng C, Misic V, Scheuring K, Schule E . A quality assurance phantom for electronic portal imaging devices. J Appl Clin Med Phys. 2011; 12(2):3350. PMC: 5718680. DOI: 10.1120/jacmp.v12i2.3350. View

15.

Paganini L, Reggiori G, Stravato A, Palumbo V, Mancosu P, Lobefalo F . MLC parameters from static fields to VMAT plans: an evaluation in a RT-dedicated MC environment (PRIMO). Radiat Oncol. 2019; 14(1):216. PMC: 6889207. DOI: 10.1186/s13014-019-1421-y. View

16.

Camilleri J, Mazurier J, Franck D, Dudouet P, Latorzeff I, Franceries X . 2D EPID dose calibration for pretreatment quality control of conformal and IMRT fields: A simple and fast convolution approach. Phys Med. 2015; 32(1):133-40. DOI: 10.1016/j.ejmp.2015.10.094. View

17.

Fuangrod T, Woodruff H, Van Uytven E, McCurdy B, Kuncic Z, OConnor D . A system for EPID-based real-time treatment delivery verification during dynamic IMRT treatment. Med Phys. 2013; 40(9):091907. DOI: 10.1118/1.4817484. View

18.

Olaciregui-Ruiz I, Rozendaal R, Mijnheer B, van Herk M, Mans A . Automatic in vivo portal dosimetry of all treatments. Phys Med Biol. 2013; 58(22):8253-64. DOI: 10.1088/0031-9155/58/22/8253. View

19.

Gustafsson H, Vial P, Kuncic Z, Baldock C, Denham J, Greer P . Direct dose to water dosimetry for pretreatment IMRT verification using a modified EPID. Med Phys. 2011; 38(11):6257-64. DOI: 10.1118/1.3656946. View

20.

Wang L, Li J, Zhang S, Zhang X, Zhang Q, Chan M . Multi-task autoencoder based classification-regression model for patient-specific VMAT QA. Phys Med Biol. 2020; 65(23):235023. PMC: 10072931. DOI: 10.1088/1361-6560/abb31c. View