Journal of Isfahan Medical School

Journal of Isfahan Medical School

Hybrid Convolutional Neural Network to Generate Optimal Intensity-Modulated Radiotherapy Treatment Planning for Brain Tumors

Document Type : Original Article(s)

Authors
Arash Ebrahimi 1
Iraj Abedi 2
Arian Banaee 3
Shayesteh Sadat Momahhed 4
1 Department of Physics, Faculty of Sciences, University of Isfahan, Isfahan, Iran
2 Department of Medical Physics, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran
3 Department of Computer Science, Shahid Beheshti University, Tehran, Iran
4 Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran
10.48305/jims.v44.i860.0623
Abstract
Background: Intensity-Modulated Radiation Therapy (IMRT) is one of the main treatments for brain tumors; however, treatment planning is complex and highly dependent on the physicist's experience. This study aimed to develop and evaluate a Hybrid Convolutional Neural Network (Hybrid CNN) model for accurate automated IMRT treatment planning prediction.
Methods: Data from 120 patients with glioblastoma treated between 2021 and 2024 were used. Contoured CT and MRI images along with Overlap Volume Histogram (OVH) values for organs-at-risk and target volumes were provided as model inputs. Three approaches were evaluated: using OVH data, contoured structures, and a combined input of both. The model was trained using 1D and 3D-CNN layers with a fully connected network, and its performance was assessed using Mean Absolute Error (MAE) and Mean Squared Error (MSE).
Results: The hybrid model outperformed individual models. The mean MAE and MSE in the test set were 2.85 Gy and 7.55 Gy, respectively. Predicted doses for organs-at-risk showed high agreement with actual values (p>0.05). Combining OVH and contoured images improved model accuracy and captured complex relationships between anatomical structures and dose–volume objectives.
Conclusion: The Hybrid CNN can perform automated IMRT treatment planning with high accuracy, improve plan quality, reduce dependence on physicist experience, and integrate with clinical treatment planning systems. This approach paves the way for safer and personalized radiotherapy in patients with brain tumors.

Highlights

Iraj Abedi: Google Scholar , PubMed

Keywords
Intensity-Modulated Radiotherapy
Hybrid Convolutional Neural Network
Automatic Treatment Planning
Brain Tumor
Overlap Volume Histogram
Subjects
1.    Takahashi S, Miyake K, Ogawa D, Anada M, Kinoshita T, Nishide T , et al. A prospective study of intensity-modulated radiation therapy using a standard radiation dose for high-grade glioma. Cancer Diagn Progn 2023; 3(4): 491-7.
2.    Feng X, Zhang L, Li Y, Pan y, Zuo g, Yang r. A new deep learning model for predicting IMRT dose distribution in lung cancer. Front Oncol 2025; 15: 1587788.
3.    Li X, Zhang Y, Zhao F, Yang F, Luo Y. Transformer-integrated hybrid convolutional neural network for dose prediction in nasopharyngeal carcinoma radiotherapy. Journal of Imaging Informatics in Medicine 2024; 38(3): 1531-51.
4.    van de Sande D, Sharabiani M, Bluemink H, Kneepkens E, Bakx N, Hagelaar E, et al. Artificial intelligence-based treatment planning of radiotherapy for locally advanced breast cancer. Phys Imaging Radiat Oncol 2021: 20: 111-6.
5.    Scaringi C, Minniti G, Paolini S. Technical advances in radiation therapy for brain tumors. Anticancer Res 2018; 38(11): 6041–7.
6.    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. J Radiat Res 2019; 60(5): 685-93.
7.    Sheng Y, Li M, Liu Z, et al. Artificial intelligence applications in intensity modulated radiation therapy. Med Phys 2021; 48(3): 1–8.
8.    Cai W, Ding S, Li Y, Zhou X, Dou W, Zhou L, et al. Automatic IMRT treatment planning through fluence prediction and plan fine-tuning for nasopharyngeal carcinoma. Radiother Oncol 2024; 19(1): 39.
9.    Li J. Artificial intelligence-based treatment planning of radiotherapy for different anatomical sites. Durham, NC: Duke University; 2023.
10. Fuller CD, Choi M, Forthuber B, Wang SJ, Rajagiriyil N, Salter BJ, et al. Standard fractionation intensity modulated radiation therapy (IMRT) of primary and recurrent glioblastoma multiforme. Radiat Onco 2007: 2: 26.
11. Wang Y, Piao Z, Gu H, Chen M, Zhang D, Zhu J. Deep learning-based prediction of radiation therapy dose distribution in head and neck cancers Technol Cancer Res Treat 2024; 23: 15330338241256594.
12. Tol JP, Dahele M, Delaney AR, Slotman BJ, Verbakel WF. Can knowledge-based DVH predictions be used for automated, individualized quality assurance of radiotherapy treatment plans? Radiat Oncol 2015; 10(1): 234.
13. Westermayer M, Sandu D, Laude C, Racadot S, Serre AA, Sarrut D, et al. Evaluation of a quasi-automatic treatment planning workflow for head-and-neck cancer in radiotherapy. Phys Imaging Radiat Oncol 2026; 39: 100983.
14. Nabors B, Portnow J, Hattangadi-Gluth J, HorbinskiC. NCCN CNS tumor guidelines update for 2023. Neuro Oncol 2023; 25(12): 2114–6.
15. International Commission on Radiation Units and Measurements (ICRU). ICRU Report 62: Prescribing, Recording, and Reporting Photon Beam Therapy. Bethesda, MD: ICRU; 1999.
16. Soomro MH, Alves VG, Nourzadeh H, Siebers JV. DeepDoseNet: A deep learning model for 3D dose prediction in radiation therapy. arXiv. 2021. Available from: https://arxiv.org/pdf/2111.00077
17. Jihong C, Penggang B, Xiuchun Z, Kaiqiang C, Wenjuan C, Yitao D, et al. Automated Intensity Modulated Radiation Therapy Treatment Planning for Cervical Cancer Based on Convolution Neural Network. Technol Cancer Res Treat 2020; 19: 1533033820957002.
18. Wang CW, Khalil MA, Puspita Firdi N. A survey on deep learning for precision oncology. Diagnostics (Basel) 2022; 12(6): 1489.
Journal of Isfahan Medical School
Volume 44, Issue 860
4th Week, June
May and June 2026
Pages 623-631

  • Receive Date 31 March 2025
  • Accept Date 19 July 2026