Estimating average glandular dose in routine mammography screening using neural network

Authors

Abstract

Given the extensive use of common mammography tests for screening and diagnosis of breast cancer, there are concerns over the increased dose absorbed by the patient due to the sensitivity of the breast tissue. Thus, knowing the Mean Glandular Dose (MGD) before radiation to the patient through its estimation can be helpful. For this reason, the MultiLayer Perceptron (MLP) neural network model was trained with Levenberg-Marquardt (LM) backpropagation training algorithm and the Entrance Surface Air Kerma (ESAK) was estimated. After running the program, it was found that 35 neurons is the most optimal value, offering a regression coefficient of 95.7%, where the Mean Squared Error (MSE) for all data was 0.437 mGy, accounting for 4.8% of the range of output changes, representing a prediction with 95.2% accuracy in the present research. In comparison with the Monte-Carlo simulation method, it enjoys a desirable accuracy.

Keywords

References

[1] The National Cancer Institutes (NCI) (2018). https://www.cancer.gov/ (accessed August 21, 2018). [2] L. Tabár , B. Vitak, TH-H. Chen, AM-F. Yen, A. Cohen, T. Tot, et al. Swedish Two-County Trial: Impact of Mammographic Screening on Breast Cancer Mortality during 3 Decades. Radiology .260 (2011) 658–663. [3] New Zealand National Screening Unit Website (2018). https://www.health.govt.nz/nz-health-statistics (accessed August 21, 2018). [4] DR. Dance, CL. Skinner, GA. Carlsson. Breast dosimetry. Appl Radiat Isot .50 (1999) 185–203. [5] DR. Dance. Monte Carlo calculation of conversion factors for the estimation of mean glandular breast dose. Phys Med Biol .35 (1990) 1211–1219. [6] WT. Sobol, X. Wu. Parametrization of mammography normalized average glandular dose tables. Med Phys. 24 (1997) 547–554. [7] K. Nigapruke, P. Puwanich, N. Phaisangitisakul, W. Youngdee. Monte Carlo simulation of average glandular dose and an investigation of influencing factors. J Radiat Res. 51 (2010) 441–448. [8] KO. Ko, SH. Park, JK. Lee. Assessment of patient close in mammography using Monte Carlo simulation. Nucl Sci Technol. 41 (2004) 214–218. [9] A. Mohammadi, R. Faghihi, S. Mehdizadeh, K. Hadad. Total absorbed dose of critical organs in mammography, assessment and comparison of ... Biomed Tech. 50 (2005) 393–394. [10] D. Čceke, S. Kunosic, M. Kopric, L. Lincender. Using Neural Network Algorithms in Prediction of Mean Glandular Dose Based on the Measurable Parameters in Mammography. Acta Inform Medica. 17 (2009) 194–197. [11] P. Mohammadyari, R. Faghihi, MA. Mosleh-Shirazi, M. Lotfi, MR. Hematiyan,C. Koontz, et al. Calculation of dose distribution in compressible breast tissues using finite element modeling, Monte Carlo simulation and thermoluminescence dosimeters. Phys Med Biol. 60 (2015) 9185–9202. [12] R. Highnam. Patient-Specific Radiation Dose Estimation in Breast Cancer Screening Keeping Patients Safe and Informed (2018). https://www.volparasolutions.com/assets/Uploads/VolparaDose-White-Paper.pdf (accessed August 21, 2018). [13] E. Ariga, S. Ito, S. Deji, T. Saze T. Determination of half value layers of X-ray equipment using computed radiography imaging plates. Phys Medica. 28 (2012) 71–75. [14] SS. Haykin. Neural networks : a comprehensive foundation. Prentice Hall. (1998). [15] A. Asgharzadeh, MR. Deevband, M. Ashtiyani. Neutron spectrum unfolding using radial basis function neural networks. Appl Radiat Isot. 129 (2017) 35–41. [16] JA. Anderson. An introduction to neural networks. MIT Press. (1995). [17] MT. Hagan, MB. Menhaj. Training feedforward networks with the Marquardt algorithm. IEEE Trans Neural Networks. 5 (1994) 989–993. [18] MT. Hagan, HB. Demuth, MH. Beale, O.De Jesús. Neural network design. (2014). [19] MS. Iyer, RR. Rhinehart. A method to determine the required number of neural-network training repetitions. IEEE Trans Neural Networks. 10 (1999) 427–432. [20] K. Fukumizu, S. Amari. Local minima and plateaus in multilayer neural networks. Ninth Int Conf Artif Neural Networks 1999 ICANN 99 Conf Publ No .470. 2 (1999) 597–602. [21] L. Hamm, BW. Brorsen, MT. Hagan. Comparison of Stochastic Global Optimization Methods to Estimate Neural Network Weights. Neural Process Lett. 26 (2007) 145–158.

Files

Share

How to cite

Statistics