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

被引:13
|
作者
Kalantzis, Georgios [1 ,2 ]
Vasquez-Quino, Luis A. [1 ]
Zalman, Travis [1 ]
Pratx, Guillem [2 ]
Lei, Yu [1 ]
机构
[1] Univ Texas Hlth Sci Ctr San Antonio, Dept Radiat Oncol, San Antonio, TX 78229 USA
[2] Stanford Univ, Dept Radiat Oncol, Sch Med, Stanford, CA 94305 USA
关键词
artificial neural network; IMRT; dose modeling; back-propagation; EPID; QUALITY-ASSURANCE; DOSIMETRIC VERIFICATION; QUANTITATIVE-EVALUATION; FILM;
D O I
10.1118/1.3639998
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
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(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. (C) 2011 American Association of Physicists in Medicine. [DOI: 10.1118/1.3639998]
引用
收藏
页码:5807 / 5817
页数:11
相关论文
共 50 条
  • [21] Feasibility of using a 2D array detector to verify composite IMRT delivery for helical tomotherapy and linac
    Shueng, P.
    Choug, N.
    Lee, H.
    Tien, H.
    Kung, W.
    Wu, L.
    INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS, 2008, 72 (01): : S675 - S675
  • [22] Feasibility Study for the virtual Training and Testing of Artificial Neural Networks
    Kehrer, Martin
    Hisung, Matthias
    Reuss, Hans-Christian
    AUTOREG 2017: AUTOMATISIERTES FAHREN UND VERNETZTE MOBILITAT, 2017, 2292 : 491 - 500
  • [23] Study on sensor modeling using Chebyshev functional link artificial neural networks
    Jun, L
    Yu, D
    ISTM/2005: 6th International Symposium on Test and Measurement, Vols 1-9, Conference Proceedings, 2005, : 2017 - 2020
  • [24] Cutting force modeling using artificial neural networks
    J Mater Process Technol, (344-349):
  • [25] Wastewater Pollutants Modeling Using Artificial Neural Networks
    Al Saleh, Hadeel Ali
    JOURNAL OF ECOLOGICAL ENGINEERING, 2021, 22 (07): : 35 - 45
  • [26] Cutting force modeling using artificial neural networks
    Szecsi, T
    JOURNAL OF MATERIALS PROCESSING TECHNOLOGY, 1999, 93 : 344 - 349
  • [27] Modeling Prosopagnosia Using Dynamic Artificial Neural Networks
    Vandermeulen, Robyn
    Morissette, Laurence
    Chartier, Sylvain
    2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2011, : 2074 - 2079
  • [28] Modeling of fuel consumption using artificial neural networks
    WITASZEK K.
    Diagnostyka, 2020, 21 (04): : 103 - 113
  • [29] River flow modeling using artificial neural networks
    Kisi, Ö
    JOURNAL OF HYDROLOGIC ENGINEERING, 2004, 9 (01) : 60 - 63
  • [30] Modeling the hydrocracking process using artificial neural networks
    Elkamel, A
    Al-Ajmi, A
    Fahim, M
    PETROLEUM SCIENCE AND TECHNOLOGY, 1999, 17 (9-10) : 931 - 954