머신러닝 기반 신체 계측정보를 이용한 CT 피폭선량 예측모델 비교
Comparison of CT Exposure Dose Prediction Models Using Machine Learning-based Body Measurement Information
2
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
This study aims to develop a patient-specific radiation exposure dose prediction model based on anthropometric data that can be easily measurable during CT examination, and to be used as basic data for DRL setting and radiation dose management system in the future. In addition, among the machine learning algorithms, the most suitable model for predicting exposure doses is presented. The data used in this study were chest CT scan data, and a data set was constructed based on the data including the patient's anthropometric data. In the pre-processing and sample selection of the data, out of the total number of samples of 250 samples, only chest CT scans were performed without using a contrast agent, and 110 samples including height and weight variables were extracted. Of the 110 samples extracted, 66% was used as a training set, and the remaining 44% were used as a test set for verification. The exposure dose was predicted through random forest, linear regression analysis, and SVM algorithm using Orange version 3.26.0, an open software as a machine learning algorithm. Results Algorithm model prediction accuracy was R^2 0.840 for random forest, R^2 0.969 for linear regression analysis, and R^2 0.189 for SVM. As a result of verifying the prediction rate of the algorithm model, the random forest is the highest with R^2 0.986 of the random forest, R^2 0.973 of the linear regression analysis, and R^2 of 0.204 of the SVM, indicating that the model has the best predictive power.
Abstract
This study aims to develop a patient-specific radiation exposure dose prediction model based on anthropometric data that can be easily measurable during CT examination, and to be used as basic data for DRL setting and radiation dose management system in the future. In addition, among the machine learning algorithms, the most suitable model for predicting exposure doses is presented. The data used in this study were chest CT scan data, and a data set was constructed based on the data including the patient's anthropometric data. In the pre-processing and sample selection of the data, out of the total number of samples of 250 samples, only chest CT scans were performed without using a contrast agent, and 110 samples including height and weight variables were extracted. Of the 110 samples extracted, 66% was used as a training set, and the remaining 44% were used as a test set for verification. The exposure dose was predicted through random forest, linear regression analysis, and SVM algorithm using Orange version 3.26.0, an open software as a machine learning algorithm. Results Algorithm model prediction accuracy was R^2 0.840 for random forest, R^2 0.969 for linear regression analysis, and R^2 0.189 for SVM. As a result of verifying the prediction rate of the algorithm model, the random forest is the highest with R^2 0.986 of the random forest, R^2 0.973 of the linear regression analysis, and R^2 of 0.204 of the SVM, indicating that the model has the best predictive power.
참고문헌 (17)
- Sources and effects of ionizing radiation, "UNSCEAR", ~, pp.UNSCEAR 2010 Report (2010)
- 이서영, "전산화단층촬영에서 촬영 목적 부위와 주변 결정장기에 대한 피폭선량 평가: 선량 권고량 중심으로", 한국방사선학회논문지, 7(2), pp.121~129 (2013), 한국방사선학회[DOI]
- Mo KH, "Analysis of exposure dose according to chest and abdomen combine CT exam method", Dept. of Radiology, pp.2016
- Fukushima Y, "Diagnostic reference level of computed tomography (CT) in Japan", Radiat Prot Dosimetry, 151(1), pp.51~57 (2012)
- IAEA, "International basic safety standards for protection against ionizing radiation and for the safety of radiation sources. IAEA Safety Series No. 115", ~ (1996)
- Brenner DJ, "Computed tomography : An increasing source of radiation exposure", N Engl J Med, 357(22), pp.2277~2284 (2007)
- Lee BJ, "Identification of the best anthropometric predictors of serum high-and low-density lipoproteins using machine learning", IEEE J Biomed Health Inform, 19(5), pp.1747~1756 (2015)[DOI]
- Lee BJ, "Indicators of hypertriglyceridemia from anthropometric measures based on data mining", Comput Biol Med, 57, pp.201~211 (2015)[DOI]
- 이범주, "머신러닝 기반 체지방 측정정보를 이용한 고콜레스테롤혈증 예측모델", 문화기술의 융합, 5(4), pp.413~420 (2019), 국제문화기술진흥원
- Cho YJ, "Big Data, New SPSS Analysis Technique;Neural Network, SVM, Random Forest" (2018), Hanarae Academic
- Carlos MR, "Data mining for the study of the Epidemic (SARS-CoV-2) COVID-19: Algorithm for the identification of patients speaking the native language in the Totonacapan area – Mexico", Munich Personal RePEc Archive, 102039, pp.1~14 (2020)
- Brenner DJ, "Computed tomography : An increasing source of radiation exposure", N Engl J Med, 357(22), pp.2277~2284 (2007)
- Individualized and intelligent radiation dose exposure guide and management system with clinical test operation. Health Technology R&D Project, "Lee CH", ~ (2017)
- Kalender WA, "Computed tomography" (2000), John Wiley and Sons
- Dougeni E, "A review of patient dose and optimisation methods in adult and paediatric CT scanning", Eur J Radiol, 81(4), pp.e665~e683 (2012)
- Woo SK, "Synthesis of contrast CT image using deep learning network", Proceedings of the Korean Society of Computer Information Conference, pp.465~467 (2019)
- 홍준용, "코로나바이러스 감염증19 데이터베이스에 기반을 둔 인공신경망 모델의 특성 평가", 방사선기술과학, 43(5), pp.397~404 (2020), 대한방사선과학회