TY - GEN
T1 - Classification of computed tomography scanner manufacturer using support vector machine
T2 - 5th International Winter Conference on Brain-Computer Interface, BCI 2017
AU - Lee, Seung Bo
AU - Jeong, Eun Jin
AU - Son, Yunsik
AU - Kim, Dong Ju
N1 - Funding Information:
This research was supported by the MSIP(Ministry of Science, ICT and Future Planning), Korea, under the ITRC(Information Technology Research Center) support program (IITP-2016-R2720-16-0007) supervised by the IITP(Institute for Information & communications Technology Promotion)
PY - 2017/2/16
Y1 - 2017/2/16
N2 - Computed tomography (CT) is useful to investigate the presence and severity of injury during acute stage of traumatic brain injury (TBI) due to its availability and short image acquisition time. Recently, quantitative CT analysis have shown promising results in objective and accurate assessment of lesion and the prediction of outcome. To conduct further multicenter, longitudinal follow-up studies using quantitative analysis, the effect of CT scanner manufacturer should be investigated. In this study, CT images were acquired from 326 subjects without any apparent intracranial abnormalities. The images were scanned by three different scanner manufacturers. The quantitative analysis was performed and plotted as density distribution. The acquired density distributions were served as input features of support vector machine (SVM) using Gaussian kernet function, which is designed for c1assifying the CT images based on the scanner manufacturers. The optimal hyperparameters were explored via grid search test and the model increased the robustness by 5-fold cross validation. The best predictive performance was obtained when C = 100 and "I = 0.1 (accuracy = 91.1 %). The resuIts showed significant difference in density distribution according to the scanner manufacturers, and thus suggest that the manufacturer should be standardized to conduct the quantitative analysis on the brain CT images.
AB - Computed tomography (CT) is useful to investigate the presence and severity of injury during acute stage of traumatic brain injury (TBI) due to its availability and short image acquisition time. Recently, quantitative CT analysis have shown promising results in objective and accurate assessment of lesion and the prediction of outcome. To conduct further multicenter, longitudinal follow-up studies using quantitative analysis, the effect of CT scanner manufacturer should be investigated. In this study, CT images were acquired from 326 subjects without any apparent intracranial abnormalities. The images were scanned by three different scanner manufacturers. The quantitative analysis was performed and plotted as density distribution. The acquired density distributions were served as input features of support vector machine (SVM) using Gaussian kernet function, which is designed for c1assifying the CT images based on the scanner manufacturers. The optimal hyperparameters were explored via grid search test and the model increased the robustness by 5-fold cross validation. The best predictive performance was obtained when C = 100 and "I = 0.1 (accuracy = 91.1 %). The resuIts showed significant difference in density distribution according to the scanner manufacturers, and thus suggest that the manufacturer should be standardized to conduct the quantitative analysis on the brain CT images.
KW - Computed tomography
KW - Quantitative analysis
KW - Support vector mahcine
KW - Traumatic brain injury
UR - http://www.scopus.com/inward/record.url?scp=85015993597&partnerID=8YFLogxK
U2 - 10.1109/IWW-BCI.2017.7858167
DO - 10.1109/IWW-BCI.2017.7858167
M3 - Conference contribution
AN - SCOPUS:85015993597
T3 - 5th International Winter Conference on Brain-Computer Interface, BCI 2017
SP - 85
EP - 87
BT - 5th International Winter Conference on Brain-Computer Interface, BCI 2017
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 9 January 2017 through 11 January 2017
ER -