Optimizing the neural network training algorithm in predicting kerma in mammography

Nabipour, M.; Deevband, M.R.; Asgharzadeh Alvar, A.; Soleimani, N.

doi:10.52547/ijrr.20.3.21

[Home ] [Archive]

International Journal of Radiation Research

Main Menu

Home

IJRR Information

For Authors

For Reviewers

Subscription

News & Events

Web Mail

Search in website

Receive site information

ISSN

Hard Copy 2322-3243

Online 2345-4229

Online Submission

Now you can send your articles to IJRR office using the article submission system.

Volume 20, Issue 3 (7-2022)

Int J Radiat Res 2022, 20(3): 665-670

Back to browse issues page

Optimizing the neural network training algorithm in predicting kerma in mammography

M. Nabipour

, M.R. Deevband

, A. Asgharzadeh Alvar

, N. Soleimani

Biomedical Engineering and Medical Physics Department, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran , mdeevband@sbmu.ac.ir

Abstract: (758 Views)

Background: In regard to the enhanced use of mammography screening tests for screening breast cancer, some concerns on the enhancement of the patient's absorbed dose have increased as well. Therefore, the assessment of the patient's dose before mammography is very important, and being aware of the dose level by its estimation can be helpful before radiation. Materials and Methods: To this end, an artificial neural network (ANN) was used in this study to estimate the entrance surface air kerma (ESAK). A phantom with similar characteristics of the breast tissue was also used to collect the required data and the network was trained using some measurable parameters. To conduct the current research, multilayer perceptron (MLP) neural network architecture with training algorithms of LMBP, SCGBP, Rprop, BFGS, and GDBP, as well as radial basis function (RBF) neural network were used. Results: The results show that the neural network with BFGS training algorithm and 38 hidden layer neurons has the best performance with 7.40% root mean square error (RMSE) and coefficient of determination (R²) was obtained as 0.91. Conclusion: According to the results of this study, there is a good correlation between the estimated network output and the measured values of the ESAK. The present method will remove the limitations and costs associated with the preparation process of dosimeter instruments.

Keywords: Breast mammography screening, entrance surface air kerma estimation, MLP neural network, RBF neural network.

Full-Text [PDF 1619 kb] (396 Downloads)

Type of Study: Original Research | Subject: Radiation Biology

References

1. 1. Howlader N, Noone AM, Krapcho M (2021) SEER Cancer Statistics Review. National Cancer Institute, posted to the SEER website. Cited 2021 Apr 19. Available from: https://seer.cancer.gov/csr.

2. gco.iarc.fr [internet]. International Agency for Research on Cancer. Posted to The Global Cancer Observatory Website. 2020 [cited 2021 March 11]. Available from: https://gco.iarc.fr/today/home

3. Iranmakani S, Mortezazadeh T, Sajadian F, Ghaziani MF, Ghafari A, Khezerloo D, et al. (2020) A review of various modalities in breast imaging: technical aspects and clinical outcomes. Egypt J Radiol Nucl Med, 51: 57. [DOI:10.1186/s43055-020-00175-5]

4. Dance DR, Skinner CL, Carlsson GA (1999) Breast dosimetry. Appl Radiat Isot, 50(1): 185-203. [DOI:10.1016/S0969-8043(98)00047-5]

5. Osteras BH, Skaane P, Gullien R, Martinsen ACT (2018) Average glandular dose in paired digital mammography and digital breast tomosynthesis acquisitions in a population based screening program: Effects of measuring breast density, air kerma and beam quality. Phys Med Biol, 63(3): 035006. [DOI:10.1088/1361-6560/aaa614] [PMID]

6. Yaffe MJ and Mainprize JG (2010) Risk of radiation-induced breast cancer from mammographic screening. Radiology, 258(1): 98-105. [DOI:10.1148/radiol.10100655] [PMID]

7. Nosratieh A, Hernandez A, Shen SZ, Yaffe MJ, Seibert JA, Boone JM (2015) Mean glandular dose coefficients (DgN) for x-ray spectra used in contemporary breast imaging systems. Phys Med Biol, 60(18): 7179-90. [DOI:10.1088/0031-9155/60/18/7179] [PMID] []

8. Delis H, Spyrou G, Panayiotakis G, Tzanakos G (2005) a Monte Carlo simulation program for dose related studies in mammography. Eur J Radiol, 54(3): 371-6. [DOI:10.1016/j.ejrad.2004.07.014] [PMID]

9. Nigapruke K, Puwanich P, Phaisangittisakul N, Youngdee W (2010) Monte Carlo simulation of average glandular dose and an investigation of influencing factors. J Radiat Res, 51(4): 441-8. [DOI:10.1269/jrr.10008] [PMID]

10. Kave Z, Deevband MR, Ghorbanee M (2018) Effect of heterogeneous breast tissue on average glandular dose in mammography using simulation. Q J Sch Med Shahid Beheshti Univ Med Sci, 42(1): 34-9.

11. Suleiman ME, Brennan PC, McEntee MF (2017) Mean glandular dose in digital mammography: a dose calculation method comparison. J Med Imaging (Bellingham), 4(1): 013502. [DOI:10.1117/1.JMI.4.1.013502] [PMID] []

12. Boone JM (1999) Glandular breast dose for monoenergetic and high-energy X-ray beams. Radiology, 213: 23-37. [DOI:10.1148/radiology.213.1.r99oc3923] [PMID]

13. Stanton L, Villafana T, Day JL, Lightfoot DA (1984) Dosage evaluation in mammography. Radiology, 150(2): 577-84. [DOI:10.1148/radiology.150.2.6691119] [PMID]

14. Alvar AA, Deevband MR, Ashtiyani M (2017) Neutron spectrum unfolding using radial basis function neural networks. Appl Radiat Isot, 129: 35-41. [DOI:10.1016/j.apradiso.2017.07.048] [PMID]

15. Massera RT and Tomal A (2021) Breast glandularity and mean glandular dose assessment using a deep learning framework: Virtual patients study. Phys Medica, 83: 264-77. [DOI:10.1016/j.ejmp.2021.03.007] [PMID]

16. Dance DR, Skinner CL, Young KC, Beckett JR, Kotre CJ (2000) Additional factors for the estimation of mean glandular breast dose using the UK mammography dosimetry protocol. Phys Med Biol, 45(11): 3225-40. [DOI:10.1088/0031-9155/45/11/308] [PMID]

17. Hagan MT, Demuth HB, Beale MH, De Jesús O (2014) Neural Network Design; 2nd Edition, eBook, Frisco, Texas.

18. Yee PV and Haykin SS (2001) Regularized radial basis function networks: theory and applications. John Wiley.

19. Haykin S (1999) Neural networks: a comprehensive foundation second edition. Pearson Education.

20. Hartman EJ, Keeler JD, Kowalski JM (1990) Layered neural networks with Gaussian hidden units as universal approximations. Neural Comput MIT Press, 2(2): 210-5. [DOI:10.1162/neco.1990.2.2.210]

21. Buhmann MD (2003) Radial basis functions theory and implementations. Cambridge University Press. [DOI:10.1017/CBO9780511543241] []

22. Bayram S, Ocal Me, Laptali Oral E, Atis Cd (2016) Comparison of multi-layer perceptron (MLP) and radial basis function (RBF) for construction cost estimation: The case of Turkey. J Civ Eng Manag. Taylor & Francis, 22(4): 480-490. [DOI:10.3846/13923730.2014.897988]

23. Avriel M (2003) Nonlinear programming: analysis and methods. Dover Publications.

24. Mohammadi A, Faghihi R, Mehdizadeh S, Hadad K (2005) Total absorbed dose of critical organs in mammography, assessment and comparison of Monte-Carlo method and TLD. Biomed Tech, 50(1): 393-4.

25. Čceke D, Kunosic S, Kopric M, Lincender L (2009) Using neural network algorithms in prediction of mean glandular dose based on the measurable parameters in mammography. Acta Inform Medic, 17(4): 194-7.

Send email to the article author

Add your comments about this article

‎ 10.52547/ijrr.20.3.21

Mendeley

Zotero

RefWorks

Nabipour M, Deevband M, Asgharzadeh Alvar A, Soleimani N. Optimizing the neural network training algorithm in predicting kerma in mammography. Int J Radiat Res 2022; 20 (3) :665-670
URL: http://ijrr.com/article-1-4361-en.html

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Volume 20, Issue 3 (7-2022)

Back to browse issues page

Persian site map - English site map - Created in 0.05 seconds with 50 queries by YEKTAWEB 4645