• Korean Journal of Radiology
• /
• v.23 no.12
• /
• pp.1281-1289
• /
• 2022

Objective: Radiomic modeling using multiple regions of interest in MRI of the brain to diagnose juvenile myoclonic epilepsy (JME) has not yet been investigated. This study aimed to develop and validate radiomics prediction models to distinguish patients with JME from healthy controls (HCs), and to evaluate the feasibility of a radiomics approach using MRI for diagnosing JME. Materials and Methods: A total of 97 JME patients (25.6 ± 8.5 years; female, 45.5%) and 32 HCs (28.9 ± 11.4 years; female, 50.0%) were randomly split (7:3 ratio) into a training (n = 90) and a test set (n = 39) group. Radiomic features were extracted from 22 regions of interest in the brain using the T1-weighted MRI based on clinical evidence. Predictive models were trained using seven modeling methods, including a light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, with radiomics features in the training set. The performance of the models was validated and compared to the test set. The model with the highest area under the receiver operating curve (AUROC) was chosen, and important features in the model were identified. Results: The seven tested radiomics models, including light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, showed AUROC values of 0.817, 0.807, 0.783, 0.779, 0.767, 0.762, and 0.672, respectively. The light gradient boosting machine with the highest AUROC, albeit without statistically significant differences from the other models in pairwise comparisons, had accuracy, precision, recall, and F1 scores of 0.795, 0.818, 0.931, and 0.871, respectively. Radiomic features, including the putamen and ventral diencephalon, were ranked as the most important for suggesting JME. Conclusion: Radiomic models using MRI were able to differentiate JME from HCs.

• Information Systems Review
• /
• v.21 no.1
• /
• pp.23-38
• /
• 2019

The social network service (SNS) is one of the important marketing channels, so many companies actively exploit SNSs by posting SNS messages with appropriate content and style for their customers. In this paper, we focused on the psychological distances embedded in the SNS messages and developed a method to measure the psychological distance in SNS message by mixing a traditional content analysis, natural language processing (NLP), and machine learning. Through a traditional content analysis by human coding, the psychological distance was extracted from the SNS message, and these coding results were used for input data for NLP and machine learning. With NLP, word embedding was executed and Bag of Word was created. The Support Vector Machine, one of machine learning techniques was performed to train and test the psychological distance in SNS message. As a result, sensitivity and precision of SVM prediction were significantly low because of the extreme skewness of dataset. We improved the performance of SVM by balancing the ratio of data by upsampling technique and using data coded with the same value in first content analysis. All performance index was more than 70%, which showed that psychological distance can be measured well.

• Korean Journal of Radiology
• /
• v.20 no.4
• /
• pp.683-692
• /
• 2019

Objective: We aimed to evaluate correlations between computed tomography (CT) parameters and pulmonary function test (PFT) parameters according to disease severity in patients with chronic obstructive pulmonary disease (COPD), and to determine whether CT parameters can be used to predict PFT indices. Materials and Methods: A total of 370 patients with COPD were grouped based on disease severity according to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) I-IV criteria. Emphysema index (EI), air-trapping index, and airway parameters such as the square root of wall area of a hypothetical airway with an internal perimeter of 10 mm (Pi10) were measured using automatic segmentation software. Clinical characteristics including PFT results and quantitative CT parameters according to GOLD criteria were compared using ANOVA. The correlations between CT parameters and PFT indices, including the ratio of forced expiratory volume in one second to forced vital capacity (FEV1/FVC) and FEV₁, were assessed. To evaluate whether CT parameters can be used to predict PFT indices, multiple linear regression analyses were performed for all patients, Group 1 (GOLD I and II), and Group 2 (GOLD III and IV). Results: Pulmonary function deteriorated with increase in disease severity according to the GOLD criteria (p < 0.001). Parenchymal attenuation parameters were significantly worse in patients with higher GOLD stages (P < 0.001), and Pi10 was highest for patients with GOLD III (4.41 ± 0.94 mm). Airway parameters were nonlinearly correlated with PFT results, and Pi10 demonstrated mild correlation with FEV1/FVC in patients with GOLD II and III (r = 0.16, p = 0.06 and r = 0.21, p = 0.04, respectively). Parenchymal attenuation parameters, airway parameters, EI, and Pi10 were identified as predictors of FEV₁/FVC for the entire study sample and for Group 1 (R² = 0.38 and 0.22, respectively; p < 0.001). However, only parenchymal attenuation parameter, EI, was identified as a predictor of FEV₁/FVC for Group 2 (R² = 0.37, p < 0.001). Similar results were obtained for FEV₁. Conclusion: Airway and parenchymal attenuation parameters are independent predictors of pulmonary function in patients with mild COPD, whereas parenchymal attenuation parameters are dominant independent predictors of pulmonary function in patients with severe COPD.

• Korean Journal of Radiology
• /
• v.21 no.6
• /
• pp.707-716
• /
• 2020

Objective: To evaluate pharmacokinetic variables from contrast-enhancing lesions (CELs) and non-enhancing T2 high signal intensity lesions (NE-T2HSILs) on dynamic contrast-enhanced (DCE) magnetic resonance (MR) imaging for predicting progression-free survival (PFS) in glioblastoma (GBM) patients. Materials and Methods: Sixty-four GBM patients who had undergone preoperative DCE MR imaging and received standard treatment were retrospectively included. We analyzed the pharmacokinetic variables of the volume transfer constant (Ktrans) and volume fraction of extravascular extracellular space within the CEL and NE-T2HSIL of the entire tumor. Univariate and multivariate Cox regression analyses were performed using preoperative clinical characteristics, pharmacokinetic variables of DCE MR imaging, and postoperative molecular biomarkers to predict PFS. Results: The increased mean Ktrans of the CEL, increased 95th percentile Ktrans of the CELs, and absence of methylated O⁶-methylguanine-DNA methyltransferase promoter were relevant adverse variables for PFS in the univariate analysis (p = 0.041, p = 0.032, and p = 0.083, respectively). The Kaplan-Meier survival curves demonstrated that PFS was significantly shorter in patients with a mean Ktrans of the CEL > 0.068 and 95th percentile Ktrans of the CEL > 0.223 (log-rank p = 0.038 and p = 0.041, respectively). However, only mean Ktrans of the CEL was significantly associated with PFS (p = 0.024; hazard ratio, 553.08; 95% confidence interval, 2.27-134756.74) in the multivariate Cox proportional hazard analysis. None of the pharmacokinetic variables from NE-T2HSILs were significantly related to PFS. Conclusion: Among the pharmacokinetic variables extracted from CELs and NE-T2HSILs on preoperative DCE MR imaging, the mean Ktrans of CELs exhibits potential as a useful imaging predictor of PFS in GBM patients.

• Korean Journal of Radiology
• /
• v.21 no.6
• /
• pp.736-745
• /
• 2020

Objective: To identify the initial chest computed tomography (CT) findings and clinical characteristics associated with the course of coronavirus disease 2019 (COVID-19) pneumonia. Materials and Methods: Baseline CT scans and clinical and laboratory data of 72 patients admitted with COVID-19 pneumonia (39 men, 46.2 ± 15.9 years) were retrospectively analyzed. Baseline CT findings including lobar distribution, presence of ground glass opacities, consolidation, linear opacities, and lung severity score were evaluated. The outcome event was recovery with hospital discharge. The time from symptom onset to discharge or the end of follow-up (for those remained hospitalized) was recorded. Data were censored in events such as death or discharge without recovery. Multivariable Cox proportional hazard regression was used to explore the association between initial CT, clinical or laboratory findings, and discharge with recovery, whereby hazard ratio (HR) values < 1 indicated a lower rate of discharge at four weeks and longer time until discharge. Results: Thirty-two patients recovered and were discharged during the study period with a median length of admission of 16 days (range, 9 to 25 days), while the rest remained hospitalized at the end of this study (median, 17.5 days; range, 4 to 27 days). None died during the study period. After controlling for age, onset time, lesion characteristics, number of lung lobes affected, and bilateral involvement, the lung severity score on baseline CT (> 4 vs. ≤ 4 [reference]: adjusted HR = 0.41 [95% confidence interval, CI = 0.18-0.92], p = 0.031) and initial lymphocyte count (reduced vs. normal or elevated [reference]: adjusted HR = 0.14 [95% CI = 0.03-0.60], p = 0.008) were two significant independent factors that influenced recovery and discharge. Conclusion: Lung severity score > 4 and reduced lymphocyte count at initial evaluation were independently associated with a significantly lower rate of recovery and discharge and extended hospitalization in patients admitted for COVID-19 pneumonia.

• Korean Journal of Biological Psychiatry
• /
• v.9 no.1
• /
• pp.25-33
• /
• 2002

Serotonin transporter(5-HTT) is one of the major action site of antidepressants in neuronal cells. According to the recent studies, it is known that the functional polymorphism in the promoter region of the 5-HTT gene(5-HTT linked polymorphism repetitive element in promoter region, 5-HTTLPR) is associated with antidepressant responsiveness, and the distributions of 5-HTTLPR is various among the different populations. Our preliminary study suggested that it is possible to measure the endophenotype of 5-HTTLPR genotype by examining the pharmacodynamic research of the 5-HTT in platelet membranes. However, there are limitations to predicting the antidepressant responsiveness only from the endophenotypic characteristics of 5-HTT gene promoter polymorphism, and therefore we propose to use the pharmacogenomic methods for overcoming these limitations. We found that the significant correlations existed among the genetic polymorphisms of biogenic amine transporters whose structure and characteristics are similar to the 5-HTT, and the predictable odds ratio of antidepressant responsiveness are increased significantly by combining the effect with other associated polymorphisms, compared to the effect of 5-HTT promoter polymorphism only. These results support the hypothesis that antidepressant treatment has to be individualized according to the genetic and ethnic background of depressed patients. It would be possible to develope the evaluation tools to predict the antidepressant responsiveness and its side effect profile, if scientists reveal the genes related to the action mechanism as well as the metabolism of antidepressants so as to discover the interaction of those genes and contribution of endogenotypes toward antidepressant responsiveness.

• Journal of Korea Water Resources Association
• /
• v.41 no.12
• /
• pp.1219-1230
• /
• 2008

Stream inflows induced by flood runoffs have a higher density than the ambient reservoir water because of a lower water temperature and elevated suspended sediment(SS) concentration. As the propagation of density currents that formed by density difference between inflow and ambient water affects reservoir water quality and ecosystem, an understanding of reservoir density current is essential for an optimization of filed monitoring, analysis and forecast of SS and nutrient transport, and their proper management and control. This study was aimed to quantify the characteristics of inflow density current including plunge depth($d_p$) and distance($X_p$), separation depth($d_s$), interflow thickness($h_i$), arrival time to dam($t_a$), reduction ratio(${\beta}$) of SS contained stream inflow for different flood magnitude in Daecheong Reservoir with a validated two-dimensional(2D) numerical model. 10 different flood scenarios corresponding to inflow densimetric Froude number($Fr_i$) range from 0.920 to 9.205 were set up based on the hydrograph obtained from June 13 to July 3, 2004. A fully developed stratification condition was assumed as an initial water temperature profile. Higher $Fr_i$(inertia-to-buoyancy ratio) resulted in a greater $d_p,\;X_p,\;d_s,\;h_i$, and faster propagation of interflow, while the effect of reservoir geometry on these characteristics was significant. The Hebbert equation that estimates $d_p$ assuming steady-state flow condition with triangular cross section substantially over-estimated the $d_p$ because it does not consider the spatial variation of reservoir geometry and water surface changes during flood events. The ${\beta}$ values between inflow and dam sites were decreased as $Fr_i$ increased, but reversed after $Fr_i$>9.0 because of turbulent mixing effect. The results provides a practical and effective prediction measures for reservoir operators to first capture the behavior of turbidity inflow.

• Journal of Bio-Environment Control
• /
• v.27 no.4
• /
• pp.349-355
• /
• 2018

This study was aimed at predicting the yield of paprika (Capsicum annuum L.) through analyzing the growth characteristics, yield pattern and greenhouse environment. In the greenhouse of the Gyeongnam area (667 m above sea level), the red paprika 'Cupra' and the yellow paprika 'Fiesta' were grown from July 5, 2016 to July 15, 2017. The planting density was $3.66plants/m^2$ and attracted 2 stems. During the cultivation period, the average external radiation of the glasshouse was $14.36MJ/m^2/day$ and the internal average temperature was controlled as $20.1^{\circ}C$. After 42 weeks of planting, the growth rate of 'Cupra' was 7.3 cm/week and that of 'Fiesta' was 6.9 cm/week. The first fruit setting of 'Cupra' appeared at 1.0th node and 'Fiesta' at 2.7th node. The first harvest of 'Fiesta' was 11 weeks after planting and 'Fiesta' was 14 weeks. Comparing the yield per 10 a until the end of the cultivation in July, 'Fiesta' was 19,307 kg, which was 2.4% higher than that of 'Cupra'. And the fruit weight ratio of over 200 g of 'Cupra' was 27.7% which was 7.7% higher than that of 'Fiesta'. The average required days to harvest after fruit setting of 'Cupra' was 72.6 days and 'Fiesta' was 63.8 days. According to the relationship between the average required days to harvest and the cumulative radiation (during from fruit setting to harvest), the more radiation increases the less required days to harvest increases after February. In terms of yield, 'Cupra' increased in yield as the cumulative radiation increased, while 'Fiesta' showed an irregular pattern. Cumulative radiation from fruit setting to harvest was negatively correlated with required days to harvest after February in both cultivars. But in relation to yield, there were difference between 'Cupra' and 'Fiesta'.

• Journal of the Society of Naval Architects of Korea
• /
• v.28 no.2
• /
• pp.52-68
• /
• 1991

A new propeller series is developed using the newly developed blade section(KH18 section) which behaves better cavitation characteristics and higher lift-drag ratio at wide range of angle-of-attack. The pitch and camber distributions are disigned in order to have the same radial and chordwise loading distribution with the selected circumferentially averaged wake input. Since the geometries of the series propeller, such as chord length, thickness, skew and rate distribations, are selected by regression of the recent full scale propeller geometric data, the performance prediction of a propeller at preliminary design stage can be mure realistic. Number of blades of the series propellers is 4 and the expanded blade area ratios are 0.3, 0.45, 0.6 and 0.75. Mean pitch ratios are selected as 0.5, 0.65, 0.8, 0.75 and 1.1 for each expanded area ratio. The new propeller series is composed of 20 propellers and is named as KD(KRISO-DAEWOO) propeller series. Propeller open water tests are performed at the experimental towing tank, and the cavitation observation tests and fluctuating pressure measurements are carried out at the cavitation tunnel of KRISO. $B_{P}-\delta$ curves, which can be used to select the optimum propeller diameter at the preliminary design stage, are derived from a regression analysis of the propeller often water test results. The KD-cavitation chart is derived from the cavitation observation test results by choosing the local maximum lift coefficient and the local cavitation number as parameters. The caviy extent of a propeller can be predicted more accurately by using the KD-cavitation chart at a preliminary design stage, since it is derived from the results of the cavitation observation tests in the selected ship's wake, whereas the existing cavitation charts, such as the Burrill's cavitation chart, are derived from the test results in uniform flow.

• Childhood Kidney Diseases
• /
• v.7 no.2
• /
• pp.150-156
• /
• 2003

Purpose : Efforts to predict the clinicopathological outcome of IgA nephropathy have been made but have yielded conflicting results and have not helped in deciding the appropriate timing of the renal biopsy. In this study, we reviewed the predictive factors of clinicopathological outcome for finding out the criteria of renal biopsy timing of IgA nephropathy. Methods : Forty children diagnosed with biopsy proven IgA nephropathy at Wonju Christian Hospital were studied retrospectively, based on medical records. Results : Among 39 patients, 2 children progressed to higher serum creatinine level. One of them reached to the end stage renal disease within 2 year 7 months. According to WHO histopathological classification, there were 15 cases of class I, 14 cases of class II, 7 cases of class III, and 3 cases of class IV. In the mild histological classes(class I, II), gross hematuria was shown in 23 out of 29 children(P=0.02). In the severe histological classes(class III, IV), gross hematuria was noted in 4 out of 10(P>0.05). The tubulointerstitial changes were grade 1 in 24 cases, grade 2 in 4 cases, grade 3 in 8 cases, and grade 4 in 3 cases. With an increase in the tubulointerstitial grade, the 24 hour urine protein/albumin ratio increased. Serum creatinine less than 0.79 mg/dL could predict the lower grade(grade 1 and 2) of tubulointerstitial changes. But serum creatinine greater than 1.13 mg/dL could predict the higher grade(grade 3 and 4) of tubulointerstitial changes. In children with gross hematuria(n=27), serum creatinine was lower(0.78 vs 1.09 mg/dL, P=0.027), serum IgA was higher(316.3 vs 198.8 mg/dL), and the cases of lower WHO classification(I and II) were more common(23 vs 4, P=0.029) than the children with microscopic hematuria. Conclusion : Serum creatinine less than 0.79 mg/dL, macroscopic hematuria, and higher 24 hour urine protein/albumin ratio would predict the lower grade glomerulo tubulointerstitial lesion in IgA nephropathy and could be used as the criteria delaying the renal biopsy.