Search

Background: Computed tomography scans are widely used in everyday medical practice due to speed, image reliability, and detectability of a wide range of pathologies. Each scan exposes the patient to a radiation dose, and performing a fast estimation of the effective dose (E) is an important step for radiological safety. The aim of this work is to estimate E from patient and CT acquisition parameters in the absence of a dose-tracking software exploiting machine learning., Methods: In total, 69,037 CT acquisitions were collected with the dose-tracking software (DTS) available at our institution. E calculated by DTS was chosen as the target value for prediction. Different machine learning algorithms were selected, optimizing parameters to achieve the best performance for each algorithm. Effective dose was also estimated using DLP and k-factors, and with multiple linear regression. Mean absolute error (MAE, mean absolute percentage error (MAPE), and R 2 were used to evaluate predictions in the test set and in an external dataset of 3800 acquisitions., Results: The random forest regressor (MAE: 0.416 mSv; MAPE: 7%; and R 2 : 0.98) showed best performances over the neural network and the support vector machine. However, all three machine learning algorithms outperformed effective dose estimation using k-factors (MAE: 2.06; MAPE: 26%) or multiple linear regression (MAE: 0.98; MAPE: 44.4%). The random forest regressor on the external dataset showed an MAE of 0.215 mSv and an MAPE of 7.1%., Conclusions: Our work demonstrated that machine learning models trained with data calculated by a dose-tracking software can provide good estimates of the effective dose just from patient and scanner parameters, without the need for a Monte Carlo approach. more...

Purpose: The Council Directive 2013/59/EURATOM considers interventional radiology to be a special practice involving high doses of radiation and requiring strict monitoring to ensure the best quality assurance programs. This work reports the early experience of managing dose data from patients undergoing angiography in a multicentre study., Materials and Methods: The study was based on a survey of about 15,200 sample procedures performed in 21 Italian hospitals centres involved on a voluntary basis. The survey concerned the collection of data related to different interventional radiology procedures: interventional cardiology, radiology, neuroradiology, vascular surgery, urology, endoscopy and pain therapy from a C-Arm and fixed units. The analysis included 11 types of procedures and for each procedure, air-kerma, kerma-area product and fluoroscopy time were collected., Results: The duration and dose values of fluoroscopic exposure for each procedure is strongly dependent on individual clinical circumstances including the complexity of the procedure; the observed distribution of patient doses was very wide, even for a specified protocol. The median values of the parameters were compared with the diagnostic reference levels (DRL) proposed for some procedures in Italy (ISTISAN) or internationally. This work proposes local DRL values for three procedures., Conclusion: This first data collection serves to take stock of the situation on patient's dosimetry in several sectors and is the starting point for obtaining and updating DRL recalling that these levels are dependent on experience and technology available., (Copyright © 2019. Published by Elsevier Ltd.) more...