skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Toward IMRT 2D dose modeling using artificial neural networks: A feasibility study

Abstract

Purpose: To investigate the feasibility of artificial neural networks (ANN) to reconstruct dose maps for intensity modulated radiation treatment (IMRT) fields compared with those of the treatment planning system (TPS). Methods: An artificial feed forward neural network and the back-propagation learning algorithm have been used to replicate dose calculations of IMRT fields obtained from PINNACLE{sup 3} v9.0. The ANN was trained with fluence and dose maps of IMRT fields for 6 MV x-rays, which were obtained from the amorphous silicon (a-Si) electronic portal imaging device of Novalis TX. Those fluence distributions were imported to the TPS and the dose maps were calculated on the horizontal midpoint plane of a water equivalent homogeneous cylindrical virtual phantom. Each exported 2D dose distribution from the TPS was classified into two clusters of high and low dose regions, respectively, based on the K-means algorithm and the Euclidian metric in the fluence-dose domain. The data of each cluster were divided into two sets for the training and validation phase of the ANN, respectively. After the completion of the ANN training phase, 2D dose maps were reconstructed by the ANN and isodose distributions were created. The dose maps reconstructed by ANN were evaluated and compared withmore » the TPS, where the mean absolute deviation of the dose and the {gamma}-index were used. Results: A good agreement between the doses calculated from the TPS and the trained ANN was achieved. In particular, an average relative dosimetric difference of 4.6% and an average {gamma}-index passing rate of 93% were obtained for low dose regions, and a dosimetric difference of 2.3% and an average {gamma}-index passing rate of 97% for high dose region. Conclusions: An artificial neural network has been developed to convert fluence maps to corresponding dose maps. The feasibility and potential of an artificial neural network to replicate complex convolution kernels in the TPS for IMRT dose calculations have been demonstrated.« less

Authors:
; ; ; ;  [1]
  1. Radiation Oncology Department, University of Texas, Health Science Center San Antonio, Texas 78229 and Radiation Oncology Department, Stanford University School of Medicine, Stanford, California 94305 (United States)
Publication Date:
OSTI Identifier:
22100609
Resource Type:
Journal Article
Journal Name:
Medical Physics
Additional Journal Information:
Journal Volume: 38; Journal Issue: 10; Other Information: (c) 2011 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA); Journal ID: ISSN 0094-2405
Country of Publication:
United States
Language:
English
Subject:
61 RADIATION PROTECTION AND DOSIMETRY; 62 RADIOLOGY AND NUCLEAR MEDICINE; ALGORITHMS; DISTRIBUTION; DOSIMETRY; EQUIPMENT; FEASIBILITY STUDIES; KERNELS; METRICS; NEURAL NETWORKS; PHANTOMS; PLANNING; RADIATION DOSE DISTRIBUTIONS; RADIATION DOSES; RADIOTHERAPY; SIMULATION; TRAINING; X RADIATION

Citation Formats

Kalantzis, Georgios, Vasquez-Quino, Luis A., Zalman, Travis, Pratx, Guillem, Lei, Yu, Radiation Oncology Department, University of Texas, Health Science Center San Antonio, Texas 78229, Radiation Oncology Department, Stanford University School of Medicine, Stanford, California 94305, and Radiation Oncology Department, University of Texas, Health Science Center San Antonio, Texas 78229. Toward IMRT 2D dose modeling using artificial neural networks: A feasibility study. United States: N. p., 2011. Web. doi:10.1118/1.3639998.
Kalantzis, Georgios, Vasquez-Quino, Luis A., Zalman, Travis, Pratx, Guillem, Lei, Yu, Radiation Oncology Department, University of Texas, Health Science Center San Antonio, Texas 78229, Radiation Oncology Department, Stanford University School of Medicine, Stanford, California 94305, & Radiation Oncology Department, University of Texas, Health Science Center San Antonio, Texas 78229. Toward IMRT 2D dose modeling using artificial neural networks: A feasibility study. United States. https://doi.org/10.1118/1.3639998
Kalantzis, Georgios, Vasquez-Quino, Luis A., Zalman, Travis, Pratx, Guillem, Lei, Yu, Radiation Oncology Department, University of Texas, Health Science Center San Antonio, Texas 78229, Radiation Oncology Department, Stanford University School of Medicine, Stanford, California 94305, and Radiation Oncology Department, University of Texas, Health Science Center San Antonio, Texas 78229. 2011. "Toward IMRT 2D dose modeling using artificial neural networks: A feasibility study". United States. https://doi.org/10.1118/1.3639998.
@article{osti_22100609,
title = {Toward IMRT 2D dose modeling using artificial neural networks: A feasibility study},
author = {Kalantzis, Georgios and Vasquez-Quino, Luis A. and Zalman, Travis and Pratx, Guillem and Lei, Yu and Radiation Oncology Department, University of Texas, Health Science Center San Antonio, Texas 78229 and Radiation Oncology Department, Stanford University School of Medicine, Stanford, California 94305 and Radiation Oncology Department, University of Texas, Health Science Center San Antonio, Texas 78229},
abstractNote = {Purpose: To investigate the feasibility of artificial neural networks (ANN) to reconstruct dose maps for intensity modulated radiation treatment (IMRT) fields compared with those of the treatment planning system (TPS). Methods: An artificial feed forward neural network and the back-propagation learning algorithm have been used to replicate dose calculations of IMRT fields obtained from PINNACLE{sup 3} v9.0. The ANN was trained with fluence and dose maps of IMRT fields for 6 MV x-rays, which were obtained from the amorphous silicon (a-Si) electronic portal imaging device of Novalis TX. Those fluence distributions were imported to the TPS and the dose maps were calculated on the horizontal midpoint plane of a water equivalent homogeneous cylindrical virtual phantom. Each exported 2D dose distribution from the TPS was classified into two clusters of high and low dose regions, respectively, based on the K-means algorithm and the Euclidian metric in the fluence-dose domain. The data of each cluster were divided into two sets for the training and validation phase of the ANN, respectively. After the completion of the ANN training phase, 2D dose maps were reconstructed by the ANN and isodose distributions were created. The dose maps reconstructed by ANN were evaluated and compared with the TPS, where the mean absolute deviation of the dose and the {gamma}-index were used. Results: A good agreement between the doses calculated from the TPS and the trained ANN was achieved. In particular, an average relative dosimetric difference of 4.6% and an average {gamma}-index passing rate of 93% were obtained for low dose regions, and a dosimetric difference of 2.3% and an average {gamma}-index passing rate of 97% for high dose region. Conclusions: An artificial neural network has been developed to convert fluence maps to corresponding dose maps. The feasibility and potential of an artificial neural network to replicate complex convolution kernels in the TPS for IMRT dose calculations have been demonstrated.},
doi = {10.1118/1.3639998},
url = {https://www.osti.gov/biblio/22100609}, journal = {Medical Physics},
issn = {0094-2405},
number = 10,
volume = 38,
place = {United States},
year = {Sat Oct 15 00:00:00 EDT 2011},
month = {Sat Oct 15 00:00:00 EDT 2011}
}