TY - JOUR ID - 17352 TI - Developing A Method for Inter-Seed Effect Correction in 125I Interstitial Brachytherapy Using Artificial Neural Network JO - Iranian Journal of Medical Physics JA - IJMP LA - en SN - AU - Bayati, Kheibar AU - Sina, Sedigheh AU - Faghihi, Reza AU - Moharram zadeh, Vahed AU - Papie, Maryam AD - Nuclear engineering department, school of mechanical engineering, Shiraz University, Shiraz, Iran. AD - Nuclear Engineering Department, School of Mechanical Engineering, Shiraz University, Shiraz, Iran. Radiation Research Center, Shiraz University, Shiraz, Iran AD - Nuclear engineering department, school of mechanical engineering, Shiraz University, Shiraz, Iran AD - Nuclear Engineering Department, School of Mechanical Engineering, Shiraz University, Shiraz, Iran Y1 - 2022 PY - 2022 VL - 19 IS - 1 SP - 14 EP - 21 KW - Dosimetry KW - Monte Carlo Method Interstitial Brachytherapy DO - 10.22038/ijmp.2021.50066.1814 N2 - 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. UR - https://ijmp.mums.ac.ir/article_17352.html L1 - https://ijmp.mums.ac.ir/article_17352_c48ba768c02881606f286bce76194c79.pdf ER -