• Journal of Korean Neurosurgical Society
• /
• v.62 no.4
• /
• pp.442-449
• /
• 2019

Objective : Bone mineral density (BMD) is an important consideration during fusion surgery. Although dual X-ray absorptiometry is considered as the gold standard for assessing BMD, quantitative computed tomography (QCT) provides more accurate data in spine osteoporosis. However, QCT has the disadvantage of additional radiation hazard and cost. The present study was to demonstrate the utility of artificial intelligence and machine learning algorithm for assessing osteoporosis using Hounsfield units (HU) of preoperative lumbar CT coupling with data of QCT. Methods : We reviewed 70 patients undergoing both QCT and conventional lumbar CT for spine surgery. The T-scores of 198 lumbar vertebra was assessed in QCT and the HU of vertebral body at the same level were measured in conventional CT by the picture archiving and communication system (PACS) system. A multiple regression algorithm was applied to predict the T-score using three independent variables (age, sex, and HU of vertebral body on conventional CT) coupling with T-score of QCT. Next, a logistic regression algorithm was applied to predict osteoporotic or non-osteoporotic vertebra. The Tensor flow and Python were used as the machine learning tools. The Tensor flow user interface developed in our institute was used for easy code generation. Results : The predictive model with multiple regression algorithm estimated similar T-scores with data of QCT. HU demonstrates the similar results as QCT without the discordance in only one non-osteoporotic vertebra that indicated osteoporosis. From the training set, the predictive model classified the lumbar vertebra into two groups (osteoporotic vs. non-osteoporotic spine) with 88.0% accuracy. In a test set of 40 vertebrae, classification accuracy was 92.5% when the learning rate was 0.0001 (precision, 0.939; recall, 0.969; F1 score, 0.954; area under the curve, 0.900). Conclusion : This study is a simple machine learning model applicable in the spine research field. The machine learning model can predict the T-score and osteoporotic vertebrae solely by measuring the HU of conventional CT, and this would help spine surgeons not to under-estimate the osteoporotic spine preoperatively. If applied to a bigger data set, we believe the predictive accuracy of our model will further increase. We propose that machine learning is an important modality of the medical research field.

• Journal of the Korean Society of Radiology
• /
• v.16 no.6
• /
• pp.741-749
• /
• 2022

Radiography-Testing that verify the quality of welding structures without destruction are overwhelmingly used in industries, but many safety precautions are required as radiation is used. The workers for Radiography-Testing perform the inspection by moving the Iridium-192 radiation source embedded in the transport container of the gamma-ray irradiator within or outside the facility. The general facility is completely blocked about radiation from the outside with thick concrete, but if it is difficult for worker to handle object of inspection, facilities ceiling can be opened. A general facility may be constructed using a theoretical dose evaluation method because all exterior facilities are blocked, but if the ceiling is open, it is not appropriate to evaluate radiation safety with a simple theoretical calculation method due to the skyshine effect. Therefore, in this study, the radiation safety of the facility was evaluated in the actual field through an ion chamber survey-meter and an accumulated dose-meter called as OSLD, and the actual evaluation environment was modeled and evaluated using the Monte Carlo simulation code as FLUKA. According to the direction of the irradiation, the radiation dose at the facility boundary was difficult to meet the standards set by the regulatory authority, and radiation safety could be secured through additional methods. In addition, it was confirmed that the simulation results using the Iridium-192 source were valid evaluation with the actual measured results.

• Progress in Medical Physics
• /
• v.27 no.1
• /
• pp.31-36
• /
• 2016

The paper discusses radiation dose of dual energy CT on which copper modulation layer, is mounted in order to improve diagnostic performance of the dual energy CT. The radiation dose is estimated using MCNPX and its results are compared with that of the conventional dual energy CT system. CT X-ray spectra of 80 and 120 kVp, which are usually used for thorax, abdominal, head, and neck CT scans, were generated by the SPEC78 code and were used for the source specification 'SDEF' card for MCNPX dose modeling. The copper modulation layer was located 20 cm away from a source covering half of the X-ray window. The radiation dose was measured as changing its thickness from 0.5 to 2.0 mm at intervals of 0.5 mm. Since the MCNPX tally provides only normalized values to a single particle, the dose conversion coefficients of F6 tally for the modulation layer-based dual energy CBCT should be calculated for matching the modeling results into the actual dose. The dose conversion coefficient is $7.2*10^4cGy/output$ that is obtained from dose calibration curve between F6 tally and experimental results in which GAFCHORMIC EBT3 films were exposed by an already known source. Consequently, the dose of the modulation layer-based dual energy cone beam CT is 33~40% less than that of the single energy CT system. On the basis of the results, it is considered that scattered dose produced by the copper modulation layer is very small. It shows that the modulation layer-based dual energy CBCT system can effectively reduce radiation dose, which is the major disadvantage of established dual energy CT.