Developing A Method for Inter-Seed Effect Correction in 125I Interstitial Brachytherapy Using Artificial Neural Network

Document Type : Original Paper


1 Nuclear engineering department, school of mechanical engineering, Shiraz University, Shiraz, Iran.

2 Nuclear Engineering Department, School of Mechanical Engineering, Shiraz University, Shiraz, Iran. Radiation Research Center, Shiraz University, Shiraz, Iran

3 Nuclear engineering department, school of mechanical engineering, Shiraz University, Shiraz, Iran

4 Nuclear Engineering Department, School of Mechanical Engineering, Shiraz University, Shiraz, Iran


Introduction: Treatment planning systems use TG-43 dose calculation protocol for brachytherapy sources. Dose calculations based on TG-43 formalism do not correct the perturbations due to the presence of tissue inhomogeneity, applicators, and inter-seed effects. Inter-seed attenuation has an important effect on dosimetry in permanent implant brachytherapy. The aim of this study is to evaluate the inter-seed attenuation effect for I-125 permanent implants. Then, software was developed to find the real dose distribution for different combinations of sources.
Material and Methods: In the first step, a hypothetical generic source model was designed based on the configurations of different commercial source types. MCNP5 Monte Carlo code was utilized to simulate the single active generic source at the center of the phantom, and an inactive placed at various positions inside the phantom. An algorithm was introduced using artificial neural network models that can estimate the dose distribution in presence of inactive sources.
Results: The Monte Carlo calculation results showed that the dose distribution is affected by the inter-seed attenuation effect. Comparison of the artificial neural network results with the Monte Carlo simulation results show that the artificial neural networks can predict the inter-seed attenuation with acceptable accuracy. Comparison of the MC calculations, and the ANN output does not show statistically significant differences between the results (P value>0.95).
Conclusion: Inter-seed effect is dependent on the distance between the seeds. Decreasing distances would cause more effect. According to the results, it seems that the artificial neural network can be used as a tool for correction of inter-seed attenuation effect in treatment planning systems.


Main Subjects

  1. Ghiassi-Nejad M, Jafarizadeh M, Ahmadian-Pour MR, Ghahramani AR. Dosimetric characteristics of 192Ir sources used in interstitial brachytherapy. Applied Radiation and Isotopes. 2001 Aug 1;55(2):189-95.
  2. Khan FM, Gibbons JP. Khan's the physics of radiation therapy. Lippincott Williams & Wilkins. 2014.
  3. Podgorsak EB. Radiation oncology physics: a handbook for teachers and students. British journal of cancer. 2008;98(5):71-99.
  4. Orton CG. Time-dose factors (TDFs) in brachytherapy. The British journal of radiology. 1974 Sep;47(561):603-7.
  5. Rivard MJ, Coursey BM, DeWerd LA, Hanson WF, Saiful Huq M, Ibbott GS, and et al.. Update of AAPM Task Group No. 43 Report: A revised AAPM protocol for brachytherapy dose calculations. Medical physics. 2004 Mar;31(3):633-74.
  6. Sina S, Faghihi R, Meigooni AS, Mehdizadeh S, Zehtabian M, Mosleh-Shirazi MA. Simulation of the shielding effects of an applicator on the AAPM TG-43 parameters of CS-137 Selectron LDR brachytherapy sources. International Journal of Radiation Research. 2009 Dec 1;7(3):135.
  7. Sina S, Faghihi R, Soleymani Meigooni A. A Comparison of the Dosimetric Parameters of Cs-137 Brachytherapy Source in Different Tissues with Water Using Monte Carlo Simulation. Iranian Journal of Medical Physics. 2012;9(1):65-74.
  8. Meigooni AS, Meli JA, Nath R. Interseed effects on dose for 125I brachytherapy implants. Medical physics. 1992 Mar;19(2):385-90.
  9. Mason J, Al-Qaisieh B, Bownes P, Henry A, Thwaites D. Investigation of interseed attenuation and tissue composition effects in 125I seed implant prostate brachytherapy. Brachytherapy. 2014 Nov 1;13(6):603-10.
  10. Safigholi H, Shah A, Meigooni AS. A Novel Algorithm Accounting for Inter-Seed Attenuation Effect in Brachytherapy Treatment Planning Systems by Monte Carlo and Artificial Neural Networks. Brachytherapy. 2014 Mar 1;13:S27-8.
  11. Sina S, Faghihi R, Meigooni A. Extracting Material Information from the CT Numbers by Artificial Neural Networks for Use in the Monte Carlo Simulations of Different Tissue Types in Brachytherapy. Journal of Biomedical Physics and Engineering, 2013; 3(1): 3-8.
  12. NV Dehkordi A., Sina S. Khodadadi F. A Comparison of Deep Learning and Pharmacokinetic Model Selection Methods in Segmentation of High-Grade Glioma. Frontiers in biomedical technologies. 2021; 8(1 ): 50-60.
  13. Shen C, Gonzalez Y, Klages P, Qin N, Jung H, Chen L, et al. Intelligent inverse treatment planning via deep reinforcement learning, a proof of-principle study in high dose-rate brachytherapy for cervical cancer. Phys. Med. Biol. 2019; 64(11):
  14. Mao X, Pineau J, Keyes R, and. Enger S. A. RapidBrachyDL: rapid radiation dose calculations in brachytherapy via deep learning. Int. J. Radiat. Oncol. Biol. Phys. 2020; 108(3): 802–
  15. Yusufaly TI, Kallis K, Simon A, Mayadev J, Yashar CM, Einck JP, et al. A knowledge-based organ dose prediction tool for brachytherapy treatment planning of patients with cervical cancer. Brachytherapy. 2020; 19(5): 624–
  16. Menhaj M. B. Fundamentals of neural networks. Tehran: Amirkabir university; 12th edition, spring 2018.