Backpropagation Neural Network Implementation in Volumetric Modulated Arch Therapy of Brain Cancer Dose Prediction

Document Type : Original Paper

Authors

1 Department of Physics, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Depok, West Java, 16424, Indonesia

2 Department of Radiation Oncology, MRCCC Siloam Hospital Semanggi, Jakarta, 12930, Indonesia

10.22038/ijmp.2025.80324.2410

Abstract

Introduction: The quality of volumetric modulated arc therapy (VMAT) planning is highly subjective and varies due to differences in planner’s experience. This process is time-consuming and involves multiple iterations to achieve clinical goals. Recent advancements in artificial intelligence (AI) offers an objective approach to improve the efficiency of VMAT planning.
Material and Methods: In this study, the backpropagation neural network with 5-fold cross-validation model was employed to train the extracted Radiomics and dosiomics features from organ contours DICOM RT structure and dose distribution DICOM RT dose using 178 VMAT technique brain cancer patients. The Radiomics and dosiomics features represent the organ shapes and dose distribution quantitatively to increase the prediction accuracy. The Mean Squared Error and paired t-test was used in model evaluation. The treatment planning quality parameters, homogeneity index (HI) and conformity index (CI), was evaluated from both predicted and clinical dose.
Results: The paired t-test indicated no significant differences (p-value > 0.05) in organs at risk (OAR) and planning target volume (PTV). The p-value for the left optic nerve is the lowest among average dose (Dmean) and maximum dose (Dmax), respectively 0.1456 and 0.0662. The average HI was 0.084±0.036 (predicted) and 0.089±0.073 (clinical), and CI was 0.938±0.107 (predicted) and 0.957±0.136 (clinical).
Conclusion: The p-value for predicted parameters suggest that neural network-based dose prediction using Radiomics and dosiomics features produces results comparable to the manual treatment planning by medical physicists (overall testing dataset MSE = 0.0355).

Keywords

Main Subjects

References

  1. Podgorsak EB. Radiation Physics for Medical Physicists [Internet]. Berlin, Heidelberg: Springer Berlin Heidelberg; 2010 [cited 2021 Mar 20].
  2. Morris S, Roques T, Ahmad S, Loo S. Practical Radiotherapy Planning. Fifth Edit. CRC Press; 2024.
  3. Shirato H, Le QT, Kobashi K, Prayongrat A, Takao S, Shimizu S, Giaccia A, Xing L, Umegaki K. Selection of external beam radiotherapy approaches for precise and accurate cancer treatment. Journal of Radiation Research. 2018 Mar 1;59(suppl_1):i2-10.
  4. Zarepisheh M, Hong L, Zhou Y, Huang Q, Yang J, Jhanwar G, et al. Automated and Clinically Optimal Treatment Planning for Cancer Radiotherapy. INFORMS J Appl Anal. 2022;52(1):69–
  5. Ge Y, Wu QJ. Knowledge‐based planning for intensity‐modulated radiation therapy: a review of data‐driven approaches. Medical physics. 2019 Jun;46(6):2760-75.
  6. Tseng HH, Luo Y, Ten Haken RK, El Naqa I. The Role of Machine Learning in Knowledge-Based Response-Adapted Radiotherapy. Front Oncol. 2018 Jul 27;8:367315.
  7. Jensen PJ, Zhang J, Koontz BF, Wu QJ. A novel machine learning model for dose prediction in prostate volumetric modulated arc therapy using output initialization and optimization priorities. Frontiers in artificial intelligence. 2021 Apr 23;4:624038.
  8. Vandewinckele L, Claessens M, Dinkla A, Brouwer C, Crijns W, Verellen D, van Elmpt W. Overview of artificial intelligence-based applications in radiotherapy: Recommendations for implementation and quality assurance. Radiotherapy and Oncology. 2020 Dec 1;153:55-66.
  9. Menzel HG. The international commission on radiation units and measurements. Journal of the ICRU. 2012 Dec;12(2):1-2.
  10. Van Griethuysen JJ, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational radiomics system to decode the radiographic phenotype. Cancer research. 2017 Nov 1;77(21):e104-7.
  11. Kraus KM, Oreshko M, Schnabel JA, Bernhardt D, Combs SE, Peeken JC. Dosiomics and radiomics-based prediction of pneumonitis after radiotherapy and immune checkpoint inhibition: the relevance of fractionation. Lung Cancer. 2024 Mar 1;189:107507.
  12. Qin Y, Zhu LH, Zhao W, Wang JJ, Wang H. Review of Radiomicss- and Dosiomicss-based Predicting Models for Rectal Cancer. Front Oncol. 2022;12(August):1–
  13. Hu J, Liu B, Xie W, Zhu J, Yu X, Gu H, et al. Quantitative comparison of knowledge-based and manual intensity modulated radiation therapy planning for nasopharyngeal carcinoma. Frontiers in oncology. 2021 Jan 7;10:551763.
  14. Sinha S, Kumar A, Maheshwari G, Mohanty S, Joshi K, Shinde P, et al. Development and Validation of Single-Optimization Knowledge-Based Volumetric Modulated Arc Therapy Model Plan in Nasopharyngeal Carcinomas. Advances in radiation oncology. 2024 Jan 1;9(1):101311.
  15. Wang Y, Piao Z, Gu H, Chen M, Zhang D, Zhu J. Deep learning-based prediction of radiation therapy dose distributions in nasopharyngeal carcinomas: a preliminary study incorporating multiple features including images, structures, and dosimetry. Technology in Cancer Research & Treatment. 2024 May;23:15330338241256594.
  16. Gronberg MP, Jhingran A, Netherton TJ, Gay SS, Cardenas CE, Chung C, et al. Deep learning–based dose prediction to improve the plan quality of volumetric modulated arc therapy for gynecologic cancers. Medical physics. 2023 Nov;50(11):6639-48.
  17. Liu J, Zhang X, Cheng X, Sun L. A deep learning-based dose prediction method for evaluation of radiotherapy treatment planning. Journal of Radiation Research and Applied Sciences. 2024 Mar 1;17(1):100757.
  18. Gronberg MP, Beadle BM, Garden AS, Skinner H, Gay S, Netherton T, et al. Deep learning–based dose prediction for automated, individualized quality assurance of head and neck radiation therapy plans. Practical radiation oncology. 2023 May 1;13(3):e282-91.
  19. Kajikawa T, Kadoya N, Ito K, Takayama Y, Chiba T, Tomori S, et al. A convolutional neural network approach for IMRT dose distribution prediction in prostate cancer patients. Journal of radiation research. 2019 Sep;60(5):685-93.
  20. Li S, Deng YQ, Zhu ZL, Hua HL, Tao ZZ. A comprehensive review on radiomics and deep learning for nasopharyngeal carcinoma imaging. Diagnostics. 2021 Aug 24;11(9):1523.
  21. Puttanawarut C, Sirirutbunkajorn N, Tawong N, Jiarpinitnun C, Khachonkham S, Pattaranutaporn P, Wongsawat Y. Radiomic and dosiomic features for the prediction of radiation pneumonitis across esophageal cancer and lung cancer. Frontiers in Oncology. 2022 Feb 16;12:768152.
  22. Liu M, Yao D, Liu Z, Guo J, Chen J. An improved Adam optimization algorithm combining adaptive coefficients and composite gradients based on randomized block coordinate descent. Computational intelligence and neuroscience. 2023;2023(1):4765891.
  23. Mortazi A, Cicek V, Keles E, Bagci U. Selecting the best optimizers for deep learning–based medical image segmentation. Frontiers in Radiology. 2023 Sep 21;3:1175473.
  24. Berrar D. Cross-validation. Encycl Bioinforma Comput Biol ABC Bioinforma. 2018 Jan 1;1–3:542–
  25. Mao YP, Yin WJ, Guo R, Zhang GS, Fang JL, Chi F, et al. Dosimetric benefit to organs at risk following margin reductions in nasopharyngeal carcinoma treated with intensity‐modulated radiation therapy. Cancer Communications. 2015 Dec;34(3):1-9.
  26. Foster I, Spezi E, Wheeler P. Evaluating the use of machine learning to predict expert-driven pareto-navigated calibrations for personalised automated radiotherapy planning. Applied Sciences. 2023 Apr 3;13(7):4548.
  27. Azharuddin SK, Kumar P, Navitha S, Chauhan AK, Kumar P, Nigam J, et al. Comparison of Dosimetric Parameters and Clinical Outcomes in Inversely Planned Intensity-Modulated Radiotherapy (IMRT) and Field-in-Field Forward Planned IMRT for the Treatment of Breast Cancer. Cureus. 2022 Jul 9;14(7).

 

Iranian Journal of Medical Physics
Volume 22, Issue 2
March and April 2025
Pages 89-97

Files

History

  • Receive Date: 06 June 2024
  • Revise Date: 03 December 2024
  • Accept Date: 18 June 2025

Share

How to cite

Statistics