방사선치료 시 다양한 기계학습을 이용한 선량품질관리 결과의 예측
Prediction of Delivery Quality Assurance Via Machine Learning in Helical Tomotherapy
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The objective of this study was to evaluate the accuracy and impact of leaf open time (LOT) and pitch using various machine learning models on EBT film-based delivery quality assurance (DQA) performed on 211 patients of helical tomotherapy (HT). We randomly selected passed (n=191) and failed (n=20) DQA measurements to evaluate the accuracy of the k-nearest neighbor (KNN), support vector machine (SVM), naive Bayes (NB) and logistic regression (LR) models using scale-dependent metrics such as the coefficient of determination (R2), mean squared error (MSE), and root MSE (RMSE). We evaluated the performance of the four prediction models in terms of the accuracy, precision, sensitivity, and F1-score using a confusion matrix, finding the NB and LR models to achieve optimal results. The results of this study are expected to reduce the workload of medical physicists and dosimetrists by predicting DQA results according to LOT and pitch in advance.
Abstract
The objective of this study was to evaluate the accuracy and impact of leaf open time (LOT) and pitch using various machine learning models on EBT film-based delivery quality assurance (DQA) performed on 211 patients of helical tomotherapy (HT). We randomly selected passed (n=191) and failed (n=20) DQA measurements to evaluate the accuracy of the k-nearest neighbor (KNN), support vector machine (SVM), naive Bayes (NB) and logistic regression (LR) models using scale-dependent metrics such as the coefficient of determination (R2), mean squared error (MSE), and root MSE (RMSE). We evaluated the performance of the four prediction models in terms of the accuracy, precision, sensitivity, and F1-score using a confusion matrix, finding the NB and LR models to achieve optimal results. The results of this study are expected to reduce the workload of medical physicists and dosimetrists by predicting DQA results according to LOT and pitch in advance.
참고문헌 (21)
- Chang KH, "Clinical implications of High Definition Multileaf Collimator(HDMLC)Dosimetric Leaf Gap(DLG)Variations", Prog Med Phys, 27(3), pp.111~116 (2016)[DOI]
- Cho B, "Intensity-modulated radiation therapy : A review with a physics perspective", Radiat Oncol J, 36(1), pp.1~10 (2018)[DOI]
- Thiyagarajan R, "Analyzing the performance of ArcCHECK diode array detector for VMAT plan", Reports of Practical Oncology & Radiotherapy, 21(1), pp.50~56 (2016)[DOI]
- Chang KH, "Treatment planning guideline of EBT-film based delivery quality assurance using statistical process control in helical tomotherapy", Journal of Radiological Science and Technology, 45(5), pp.439~448 (2022)[DOI]
- Chang KH, "A comparison of patient-specific delivery quality assurance (DQA) devices in radiation therapy", Journal of Radiological Science and Technology, 46(3), pp.231~238 (2023)
- Guckenberger M, "Precision required for dose-escalated treatment of spinal metastases and implications for image-guided radiation therapy(IGRT)", Radiother Oncol, 84(1), pp.56~63 (2007)[DOI]
- Montgomery DC, "Statistical quality control" (2009), Wiley
- Chung E, "Clinical implementation of Dosimetry Check™ for TomoTherapy®delivery quality assurance", J Appl Clin Med Phys, 19(6), pp.193~199 (2018)[DOI]
- McCowan PM, "A model-based 3D patient-specific pre-treatment QA method for VMAT using the EPID", Phys Med Biol, 62(4), pp.1600~1612 (2017)[DOI]
- Chang KH, "Dosimetric comparison of four commercial patient-specific quality assurance devices for helical tomotherapy", J Korean Phys Soc, 76, pp.257~263 (2020)[DOI]
- Chang KH, "Statistical analysis of treatment planning parameters for prediction of delivery quality assurance failure for helical tomotherapy", Technol Cancer Res Treat, 19, pp.1533033820979692~ (2020)[DOI]
- Siddalingappa R, "K-nearest-neighbor algorithm to predict the survival time and classification of various stages of oral cancer : A machine learning approach", F1000Res, 16(11), pp.70~ (2023)[DOI]
- Kubat M, "An introduction to machine learning" (2015), Springer Publishing Company
- Cilla S, "Prediction and classification of VMAT dosimetric accuracy using plan complexity and log-files analysis", Phys Med, 103, pp.76~88 (2022)[DOI]
- Wall PDH, "Application and comparison of machine learning models for predicting quality assurance outcomes in radiation therapy treatment planning", Informatics in Medicine Unlocked, 18, pp.100292~ (2020)[DOI]
- Kononenko I, "Inductive and bayesian learning in medical diagnosis", Appl Artif Intell, 7(4), pp.317~337 (1993)[DOI]
- Jierula A, "Study on accuracy metrics for evaluating the predictions of damage locations in deep piles using artificial neural networks with acoustic emission data", Applied Sciences, 11(5), pp.2314~ (2021)[DOI]
- Thomas SJ, "Implications of leaf fluence opening factors on transfer of plans between matched helical tomotherapy machines", Biomedical Physics & Engineering Express, 4(1), pp.017001~ (2017)[DOI]
- Cavinato S, "Prediction models as decision-support tools for virtual patient-specific quality assurance of helical tomotherapy plans", Phys Imaging Radiat Oncol, 26, pp.100435~ (2023)[DOI]
- Zhu H, "Patient-specific quality assurance prediction models based on machine learning for novel dual-layered MLC linac", Med Phys, 50(2), pp.1205~1214 (2023)[DOI]
- Kusunoki T, "Evaluation of prediction and classification performances in different machine learning models for patient-specific quality assurance of head-and-neck VMAT plans", Med Phys, 49(1), pp.727~741 (2022)[DOI]