A Study on Predictive Modeling of I-131 Radioactivity Based on Machine Learning
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
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.
Abstract
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.
참고문헌 (24)
- Kopisch A, "Exposure to technologists from preparing and administering therapeutic 131I : How frequently should we bioassay?", J Nucl Med Technol, 39, pp.60~62 (2011)
- 장동근, "몬테칼로 모사를 이용한 방사성옥소 I-131의 차폐체에 대한 효용성 연구", 방사선기술과학, 37(2), pp.143~150 (2014), 대한방사선과학회
- Geoffrey MC, "Intelligent Imaging : Artificial Intelligence Augmented Nuclear Medicine", J Nucl Med Technol, 47, pp.217~222 (2019)
- Tang A, "Canadian association of radiologists white paper on artificial intelligence in radiology", Can Assoc Radial J, 69, pp.120~135 (2018)
- Lundervold AS, "An overview of deep learning in medical imaging focusing on MRI", Z Med Phys, 29, pp.102~127 (2019)
- Tukey JW, "Exploratory data analysis", Pearson, 2, pp.131~160 (1977)
- Berrar D, "Encyclopedia of Bioinformatics and Computational Biology, 1", pp.542~545 (2018)
- Nam YW, "Water leak detection based on convolutional neural network using actual leak sounds and the hold-out method", Water Supply, 21(7), pp.3477~3485 (2021)
- Lynch CM, "Prediction of lung cancer patient survival via supervised machine learning classification techniques", International Journal of Medical Informatics, 108, pp.1~8 (2017)
- Muhammad LJ, "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, 10(11), pp.197~208 (2017)
- Muhammad LJ, "Supervised machine learning models for prediction of COVID-19infection using epidemiology dataset", SN Computer Science, 2(1), pp.11~ (2021)
- Muhammad LJ, "Multi query optimization algorithm using semantic and heuristic approaches", Int J Database Theory Appl, 6(9), pp.219~226 (2016)
- Hastie T, "The Elements of Statistical learning:Data mining, inference, and prediction, Springer Series in Statistics", pp.587~604 (2009), Springer
- "A brief introduction to XGBoost" (2020)[URL]
- Chen T, "XGBoost: A scalable tree boosting system", pp.785~794 (2016), ACM
- Belgiu M, "Random forest in remote sensing : A review of applications and future directions", ISPRS Journal of Photogrammetry and Remote Sensing, 114, pp.24~31 (2016)
- Speiser JL, "A comparison of random forest variable selection methods for classification prediction modeling", Expert Syst Appl, 134, pp.93~101 (2019)
- Han S, "Double random forest", Mach Learn, pp.1569~1586 (2020)
- Qi Y., "Random forest for bioinformatics", Computer Science, pp.307~323 (2012)
- Han S, "Improving random forest predictions in small datasets from two-phase sampling designs", BMC Med Inform Decis Mak, 322(21) (2021)
- -capsule prior to radioiodine therapy with significant reduction of the radiation exposure to the medical staff, "J Appl Clin Med Phys", 2016, 59~72
- Breiman L, "Random forests", Machine Learning, 45, pp.5~32 (2001)
- Levine G, "Discrepancies in dose calibrator assays for various forms of therapeutic Iodine-131", J Nucl Med Technol, 12(2), pp.84~86 (1984)
- 강석진, "방사성요오드(I-131) 격리병실 치료 관리를 위한 환자의 체외방사선량률과 상주 보호자의 피폭선량평가", 방사선기술과학, 45(4), pp.347~353 (2022), 대한방사선과학회