:: Volume 21, Issue 1 (1-2023) ::
Int J Radiat Res 2023, 21(1): 53-59 Back to browse issues page
Predicting radiation therapy outcome of pituitary gland in head and neck cancer using Artificial Neural Network (ANN) and radiobiological models
S. Shahbazi , R. Ferdosi , R. Malekzadeh , R. Egdam Zamiri , A. Mesbahi
Molecular Medicine Research Center, Institute of Biomedicine, Tabriz University of Medical Sciences, Tabriz, Iran , amesbahi2010@gmail.com
Abstract:   (651 Views)
Background: Pituitary dysfunction is one of the complications associated with head and neck radiation therapy. Here, radiobiological and artificial neural network (ANN) models were used to estimate the normal tissue complication probability (NTCP) of the pituitary gland. Materials and Methods: Fifty-one adult patients with nasopharyngeal carcinoma and brain tumor were studied. Two radiobiological models of Lyman Kutcher Burman (LKB), log-logistic, and ANN were employed to calculate the NTCP of the pituitary gland for all patients. BIOPLAN and MATLAB softwares were used for all calculations. The necessary parameters for each radiobiological model were calculated using Bayesian methods. R2 (coefficient of determination) and root-mean-square error (RMSE) parameters were used for the ANN method to get the best estimate. The area under the receiver operating characteristic (ROC) curve (AUC) and Akaike information criterion (AIC) were used to compare the models. Results: The respective mean NTCPs for nasopharyngeal patients with LKB and log-logistic models were 54.53% and 50.83%. For brain tumors, these values were 62.23% for LKB and 53.55% for log-logistic. Furthermore, AIC and AUC values for LKB were 77.1 and 0.826 and for log-logistic were 71.9 and 0.902, respectively. AUC value for ANN was 0.92. Conclusions: It can be deduced that LKB and log-logistic methods make reliable estimations for NTCP of the pituitary gland after radiotherapy. Moreover, the ANN approach as a novel method for NTCP calculations performed better than the two conventional analytical models as its estimations were much closer to the clinical data.
Keywords: NTCP, radiobiological model, ANN, pituitary gland, radiotherapy.
Full-Text [PDF 884 kb]   (609 Downloads)    
Type of Study: Original Research | Subject: Radiation Biology
References
1. 1. Alterio D, Marvaso G, Ferrari A, et al. (2019) Modern radiotherapy for head and neck cancer. In Seminars in Oncology, 46(3): 233-245. [DOI:10.1053/j.seminoncol.2019.07.002] [PMID]
2. Ferlay J, Soerjomataram I, Dikshit R, et al.(2015) Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012. Int J Cancer, 136(5): E359-E86. [DOI:10.1002/ijc.29210] [PMID]
3. Niemierko A and Goitein M (1991) Calculation of normal tissue complication probability and dose-volume histogram reduction schemes for tissues with a critical element architecture. Radiat Oncol J, 20(3): 166-76. [DOI:10.1016/0167-8140(91)90093-V]
4. Warkentin B, Stavrev P, Stavreva N, et al. (2004) A TCP‐NTCP estimation module using DVHs and known radiobiological models and parameter sets. [DOI:10.1120/jacmp.26.149] [PMID] []
5. J Appl Clin Med Phys, 5(1): 50-63.
6. Niemierko A and Goitein M ( 1993) Modeling of normal tissue response to radiation: the critical volume model. Int J Radiat Oncol Biol Phys, 25(1): 135-45. [DOI:10.1016/0360-3016(93)90156-P] [PMID]
7. Mesbahi A, Rasouli N, Mohammadzadeh M, et al. ( 2019) Comparison of radiobiological models for radiation therapy plans of prostate cancer: Three-dimensional Conformal versus Intensity Modulated Radiation Therapy. J Biomed Phys Eng, 9(3): 267. [DOI:10.31661/jbpe.v9i3Jun.655]
8. Hamming-Vrieze O, Depauw N, Craft D, et al. ( 2019) Impact of setup and range uncertainties on TCP and NTCP following VMAT or IMPT of oropharyngeal cancer patients. [DOI:10.1088/1361-6560/ab1459] [PMID]
9. Phys Med Biol, 64(9): 095001.
10. Frometa-Castillo T, Pyakuryal A, Wals-Zurita A, et al. (2020) Proposals of models for new formulations of the current complication-free cure (P+) and uncomplicated tumor control probability (UTCP) concepts, and total normal tissue complication probability of late complications. Int J Radiat Biol, 96(7): 847-850. [DOI:10.1080/09553002.2020.1741722] [PMID]
11. Ghasemi Jangjoo A, Nasiri B, Jafari-Koshki T, et al. (2020) Radiobiological modeling of acute esophagitis following radiotherapy of thorax and head-neck tumors: A comparison of lyman kutcher burman with equivalent uniform dose-based models. Iranian J Med Phys, 17(4): 225-34.
12. Namdar AM, Mohammadzadeh M, Okutan M, et al. (2018) A review on the dosimetrical and radiobiological prediction of radiation-induced hypothyroidism in radiation therapy of head-and-neck cancer, breast cancer, and Hodgkin's lymphoma survivors. Pol J Med Phys Eng, 24(4): 137-48. [DOI:10.2478/pjmpe-2018-0020]
13. De Marzi L, Feuvret L, Boulé T, et al. ( 2015) Use of gEUD for predicting ear and pituitary gland damage following proton and photon radiation therapy. Br J Radiol, 88(1048): 20140413. [DOI:10.1259/bjr.20140413] [PMID] []
14. Lee T-F, Chao P-J, Wang H-Y, et al. (2012) Normal tissue complication probability model parameter estimation for xerostomia in head and neck cancer patients based on scintigraphy and quality of life assessments. BMC cancer, 12(1): 567. [DOI:10.1186/1471-2407-12-567] [PMID] []
15. Luo R, Wu VW, He B, et al. (2018) Development of a normal tissue complication probability (NTCP) model for radiation-induced hypothyroidism in nasopharyngeal carcinoma patients. BMC cancer, 18(1): 1-8. [DOI:10.1186/s12885-018-4348-z] [PMID] []
16. Boon IS, Au Yong T, Boon CS ( 2018) Assessing the role of artificial intelligence (AI) in clinical oncology: utility of machine learning in radiotherapy target volume delineation. Medicines, 5(4): 131. [DOI:10.3390/medicines5040131] [PMID] []
17. Tu JV ( 1996) Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol, 49(11): 1225-31. [DOI:10.1016/S0895-4356(96)00002-9] [PMID]
18. Hosseini-Ashrafi M, Bagherebadian H, Yahaqi E (1999) Pre-optimization of radiotherapy treatment planning: an artificial neural network classification aided technique. Phys Med Biol, 44(6): 1513. [DOI:10.1088/0031-9155/44/6/306] [PMID]
19. Isaksson M, Jalden J, Murphy MJ (2005) On using an adaptive neural network to predict lung tumor motion during respiration for radiotherapy applications. Med phys, 32(12): 3801-9. [DOI:10.1118/1.2134958] [PMID]
20. Gulliford SL, Webb S, Rowbottom CG, et al. (2004) Use of artificial neural networks to predict biological outcomes for patients receiving radical radiotherapy of the prostate. Radiat Oncol J, 71(1): 3-12. [DOI:10.1016/j.radonc.2003.03.001] [PMID]
21. Ochi T, Murase K, Fujii T, et al. (2002) Survival prediction using artificial neural networks in patients with uterine cervical cancer treated by radiation therapy alone. Int J Clin Oncol, 7(5): 0294-300. [DOI:10.1007/s101470200043] [PMID]
22. Mahdavi SR, Tavakol A, Sanei M, et al. (2019) Use of artificial neural network for pretreatment verification of intensity modulation radiation therapy fields. The British Journal of Radiology, 92(1102): 0190355. [DOI:10.1259/bjr.20190355] [PMID] []
23. Pekic S, Miljic D, Popovic V ( 2018) Hypopituitarism following cranial radiotherapy. Endotext [Internet]: MDText. com, Inc.
24. Lamba N, Bussiere MR, Niemierko A, et al. (2019) Hypopituitarism After Cranial Irradiation for Meningiomas: A Single-Institution Experience. Pract Radiat Oncol, 9(3): e266-e73. [DOI:10.1016/j.prro.2019.01.009] [PMID]
25. Gebauer J, Mehta P, Fahlbusch FB, et al. ( 2020) Hypothalamic-Pituitary Axis Dysfunction after Whole Brain Radiotherapy-A Cohort Study. Anticancer Res, 40(10): 5787-92. [DOI:10.21873/anticanres.14595] [PMID]
26. Kyriakakis N, Lynch J, Orme SM, et al. (2016) Pituitary dysfunction following cranial radiotherapy for adult‐onset nonpituitary brain tumours. Clin Endocrinol, 84(3): 372-9. [DOI:10.1111/cen.12969] [PMID]
27. Appelman-Dijkstra NM, Kokshoorn NE, Dekkers OM, et al. (2011) Pituitary dysfunction in adult patients after cranial radiotherapy: systematic review and meta-analysis. [DOI:10.1210/jc.2011-0306] [PMID] []
28. Int J Clin Endocrinol Metab, 96(8): 2330-40.
29. Merchant TE, Rose SR, Bosley C, et al. (2011) Growth hormone secretion after conformal radiation therapy in pediatric patients with localized brain tumors. J Med Oncol, 29(36): 4776. [DOI:10.1200/JCO.2011.37.9453] [PMID] []
30. Vatner RE, Niemierko A, Misra M, et al. (2018) Endocrine deficiency as a function of radiation dose to the hypothalamus and pituitary in pediatric and young adult patients with brain tumors. J Med Oncol, 36(28): 2854. [DOI:10.1200/JCO.2018.78.1492] [PMID] []
31. Mohan R, Mageras G, Baldwin B, et al. (1992) Clinically relevant optimization of 3‐D conformal treatments. Med phys, 19(4): 933-44. [DOI:10.1118/1.596781] [PMID]
32. Niemierko A (1997) Reporting and analyzing dose distributions: a concept of equivalent uniform dose. Med phys, 24(1): 103-10. [DOI:10.1118/1.598063] [PMID]
33. Niemierko A (1999) A generalized concept of equivalent uniform dose (EUD). Med Phys, 26(6): 1100.
34. Sanchez-Nieto B and Nahum A (2000) BIOPLAN: software for the biological evaluation of radiotherapy treatment plans. Med Dosim;25(2):71-6. [DOI:10.1016/S0958-3947(00)00031-5]
35. Vance A (2009) Data analysts captivated by R's power. New York Times, 6(2009).
36. Abraham TH ( 2002) (Physio) logical circuits: The intellectual origins of the McCulloch-Pitts neural networks. J Hist Behav Sci, 38(1): 3-25. [DOI:10.1002/jhbs.1094] [PMID]
37. Kucuk N, Manohara S, Hanagodimath S, et al. (2013) Modeling of gamma ray energy-absorption buildup factors for thermoluminescent dosimetric materials using multilayer perceptron neural network: A comparative study. Radiat Phys Chem, 86: 10-22. [DOI:10.1016/j.radphyschem.2013.01.021]
38. Bryce TJ, Dewhirst MW, Floyd Jr CE, et al. (1998) Artificial neural network model of survival in patients treated with irradiation with and without concurrent chemotherapy for advanced carcinoma of the head and neck. Int J Radiat Oncol Biol Phys, 41(2): 339-45. [DOI:10.1016/S0360-3016(98)00016-9]
39. Darzy KH (2009) Radiation-induced hypopituitarism after cancer therapy: who, how and when to test. Nat Clin Pract Endocrinol Metab, 5(2): 88-99. [DOI:10.1038/ncpendmet1051] [PMID]
40. Scoccianti S, Detti B, Gadda D, et al. (2015) Organs at risk in the brain and their dose-constraints in adults and in children: a radiation oncologist's guide for delineation in everyday practice. Radiat Oncol J, 114(2): 230-8. [DOI:10.1016/j.radonc.2015.01.016] [PMID]
41. Pai HH, Thornton A, Katznelson L, et al. (2001) Hypothalamic/pituitary function following high-dose conformal radiotherapy to the base of skull: demonstration of a dose-effect relationship using dose-volume histogram analysis. Int J Radiat Oncol Biol Phys, 49(4): 1079-92. [DOI:10.1016/S0360-3016(00)01387-0]
42. Emami B, Lyman J, Brown A, et al. (1991) Tolerance of normal tissue to therapeutic irradiation. Int J Radiat Oncol Biol Phys, 21(1): 109-22. [DOI:10.1016/0360-3016(91)90171-Y]
43. D'Avino V, Palma G, Liuzzi R, et al. (2015) Prediction of gastrointestinal toxicity after external beam radiotherapy for localized prostate cancer. Radiat Oncol J, 10(1): 1-9. [DOI:10.1186/s13014-015-0389-5] [PMID] []
44. Tomatis S, Rancati T, Fiorino C, et al. (2012) Late rectal bleeding after 3D-CRT for prostate cancer: development of a neural-network-based predictive model. Phys Med Biol, 57(5): 1399. [DOI:10.1088/0031-9155/57/5/1399] [PMID]
45. Pudasaini M, Leventouri T, Pella S, et al. (2021) Estimation of radiobiological indices in radiotherapy of lung cancer using an artificial neural network. Bulletin of the American Physical Society.
46. Cho DD, Wernicke AG, Nori D, et al. (2014) Predicting radiation therapy outcome for head and neck cancer patients using artificial neural network (ANN). Int J Radiat Oncol Biol Phys, 90(1): S852. [DOI:10.1016/j.ijrobp.2014.05.2442]
47. Bryce TJ, Dewhirst MW, Floyd Jr CE, et al.(1998) Artificial neural network model of survival in patients treated with irradiation with and without concurrent chemotherapy for advanced carcinoma of the head and neck. Int J Radiat Oncol Biol Phys, 41(2): 339-45. [DOI:10.1016/S0360-3016(98)00016-9]
48. Pella A, Cambria R, Riboldi M, et al. (2011) Use of machine learning methods for prediction of acute toxicity in organs at risk following prostate radiotherapy. Med phys, 38(6Part1): 2859-67. [DOI:10.1118/1.3582947] [PMID]



XML     Print



Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Volume 21, Issue 1 (1-2023) Back to browse issues page