대한방사선기술학회지:방사선기술과학 (Journal of radiological science and technology)

  • 제46권2호
  • /
  • Pages.131-139
  • /
  • 2023
  • /
  • 2288-3509(pISSN)
  • /
  • 2384-1168(eISSN)
대한방사선과학회 (Korean Society of Radiological Science)
권호 표지
DOI QR코드

DOI QR Code

머신러닝 기반 고용량 I-131의 용량 예측 모델에 관한 연구

A Study on Predictive Modeling of I-131 Radioactivity Based on Machine Learning

  • Yeon-Wook You (Department of Nuclear Medicine and Research Institute, National Cancer Center) ;
  • Chung-Wun Lee (Department of Nuclear Medicine and Research Institute, National Cancer Center) ;
  • Jung-Soo Kim (Department of Radiological Science, Dongnam Health University)
  • 투고 : 2023.01.26
  • 심사 : 2023.03.06
  • 발행 : 2023.04.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

High-dose I-131 used for the treatment of thyroid cancer causes localized exposure among radiology technologists handling it. There is a delay between the calibration date and when the dose of I-131 is administered to a patient. Therefore, it is necessary to directly measure the radioactivity of the administered dose using a dose calibrator. In this study, we attempted to apply machine learning modeling to measured external dose rates from shielded I-131 in order to predict their radioactivity. External dose rates were measured at 1 m, 0.3 m, and 0.1 m distances from a shielded container with the I-131, with a total of 868 sets of measurements taken. For the modeling process, we utilized the hold-out method to partition the data with a 7:3 ratio (609 for the training set:259 for the test set). For the machine learning algorithms, we chose linear regression, decision tree, random forest and XGBoost. To evaluate the models, we calculated root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) to evaluate accuracy and R2 to evaluate explanatory power. Evaluation results are as follows. Linear regression (RMSE 268.15, MSE 71901.87, MAE 231.68, R2 0.92), decision tree (RMSE 108.89, MSE 11856.92, MAE 19.24, R2 0.99), random forest (RMSE 8.89, MSE 79.10, MAE 6.55, R2 0.99), XGBoost (RMSE 10.21, MSE 104.22, MAE 7.68, R2 0.99). The random forest model achieved the highest predictive ability. Improving the model's performance in the future is expected to contribute to lowering exposure among radiology technologists.

키워드

참고문헌

  1. Kopisch A, Martin CB, Grantham V. Exposure to technologists from preparing and administering therapeutic 131I: How frequently should we bioassay? J Nucl Med Technol. 2011;39:60-2. https://doi.org/10.2967/jnmt.110.077297
  2. Jang DG, Yang SO, Kim JG, Lee SH, Choi HS, Bae CW. A study on the shielding of iodine 131 using monte carlo simulation. Journal of Radiological Science and Technology. 2014;37(2):143-50.
  3. Geoffrey MC. Intelligent Imaging: Artificial Intelligence Augmented Nuclear Medicine. J Nucl Med Technol. 2019;47:217-22. https://doi.org/10.2967/jnmt.119.232462
  4. Tang A, Tam R, Cadrin-ChLnevert A, Guest W, Chong J, Barfett J, et al. Canadian association of radiologists white paper on artificial intelligence in radiology. Can Assoc Radial J. 2018;69:120-35. https://doi.org/10.1016/j.carj.2018.02.002
  5. Lundervold AS, Lundervold A. An overview of deep learning in medical imaging focusing on MRI. Z Med Phys. 2019;29:102-27.
  6. Tukey JW. Exploratory data analysis. Pearson. 1977;2:131-60.
  7. Berrar D. Cross-validation. Encyclopedia of Bioinformatics and Computational Biology. 2018;1:542-5.
  8. Nam YW, Arai Y, Kunizane T, Koizumi A. Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method. Water Supply. 2021;21(7):3477-85. https://doi.org/10.2166/ws.2021.109
  9. Lynch CM, Abdollahi B, Fuqua JD, De Carlo AR, Bartholomai JA, Balgemann RN, et al. Prediction of lung cancer patient survival via supervised machine learning classification techniques. International Journal of Medical Informatics. 2017;108:1-8. https://doi.org/10.1016/j.ijmedinf.2017.09.013
  10. Muhammad LJ, Salisu S, Yakubu A, Malgwi YM, Abdullahi ET, Mohammed IA, et al. Using decision tree data mining algorithm to predict causes of road traffic accidents, its prone locations and time along Kano-Wudil highway. Int J Database Theory Appl. 2017;10(11):197-208. https://doi.org/10.14257/ijdta.2017.10.1.18
  11. Muhammad LJ, Algehyne EA, Usman SS, Ahmad A, Chakraborty C, Mohammed IA. Supervised machine learning models for prediction of COVID-19 infection using epidemiology dataset. SN Computer Science. 2021;2(1):11.
  12. Muhammad LJ, Ali AG, Zakariyau YB, Mohammed IA. Multi query optimization algorithm using semantic and heuristic approaches. Int J Database Theory Appl. 2016;6(9):219-26. https://doi.org/10.14257/ijdta.2016.9.6.22
  13. Hastie T, Tibshirani R, Friedman J. Random forests. In: The Elements of Statistical learning: Data mining, inference, and prediction. 2nd ed. Springer Series in Statistics. New York: Springer; 2009:587-604.
  14. Khandelwal N. A brief introduction to XGBoost [Internet]. Towards Data Science; 2020 [cited 2020 Jul 7]. Available from: https://towardsdatascience. com/a-brief-introduction-to-XGBoost-3eaee2e 3e5d6
  15. Chen T, Guestrin C. XGBoost: A scalable tree boosting system. ACM. 2016:785-94.
  16. Belgiu M, Dragut L. Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing. 2016;114:24-31. https://doi.org/10.1016/j.isprsjprs.2016.01.011
  17. Speiser JL, Miller ME, Tooze EJ. A comparison of random forest variable selection methods for classification prediction modeling. Expert Syst Appl. 2019;134:93-101. https://doi.org/10.1016/j.eswa.2019.05.028
  18. Han S, Kim H, Lee YS. Double random forest. Mach Learn. 2020:1569-86.
  19. Qi Y. Random forest for bioinformatics. Computer Science. 2012:307-23.
  20. Han S, Williamson BD, Fong Y. Improving random forest predictions in small datasets from two-phase sampling designs. BMC Med Inform Decis Mak. 2021;322(21).
  21. LLtzen U, Zhao Y, Marx M, Imme T, Assam I, Siebert FA, et al. Effective method of measuring the radioactivity of [131I]-capsule prior to radioiodine therapy with significant reduction of the radiation exposure to the medical staff. J Appl Clin Med Phys. 2016;17(4):59-72. https://doi.org/10.1120/jacmp.v17i4.5942
  22. Breiman L. Random forests. Machine Learning. 2001;45:5-32. https://doi.org/10.1023/A:1010933404324
  23. Levine G, Malhi B, Struttman L. Discrepancies in dose calibrator assays for various forms of therapeutic Iodine-131. J Nucl Med Technol. 1984;12(2): 84-6.
  24. Kang SJ, Lee DH, Soh Y, Lee JW. Evaluation of caregivers' exposed dose and patients' external dose rate for radioactive iodine (I-131) therapy administration in isolated ward. Journal of Radiological Science and Technology. 2022;45(4):347-53. https://doi.org/10.17946/JRST.2022.45.4.347