• Korean Journal of Radiology
• /
• v.25 no.4
• /
• pp.363-373
• /
• 2024

Objective: To develop and evaluate a deep learning model for automated segmentation and detection of bone metastasis on spinal MRI. Materials and Methods: We included whole spine MRI scans of adult patients with bone metastasis: 662 MRI series from 302 patients (63.5 ± 11.5 years; male:female, 151:151) from three study centers obtained between January 2015 and August 2021 for training and internal testing (random split into 536 and 126 series, respectively) and 49 MRI series from 20 patients (65.9 ± 11.5 years; male:female, 11:9) from another center obtained between January 2018 and August 2020 for external testing. Three sagittal MRI sequences, including non-contrast T1-weighted image (T1), contrast-enhanced T1-weighted Dixon fat-only image (FO), and contrast-enhanced fat-suppressed T1-weighted image (CE), were used. Seven models trained using the 2D and 3D U-Nets were developed with different combinations (T1, FO, CE, T1 + FO, T1 + CE, FO + CE, and T1 + FO + CE). The segmentation performance was evaluated using Dice coefficient, pixel-wise recall, and pixel-wise precision. The detection performance was analyzed using per-lesion sensitivity and a free-response receiver operating characteristic curve. The performance of the model was compared with that of five radiologists using the external test set. Results: The 2D U-Net T1 + CE model exhibited superior segmentation performance in the external test compared to the other models, with a Dice coefficient of 0.699 and pixel-wise recall of 0.653. The T1 + CE model achieved per-lesion sensitivities of 0.828 (497/600) and 0.857 (150/175) for metastases in the internal and external tests, respectively. The radiologists demonstrated a mean per-lesion sensitivity of 0.746 and a mean per-lesion positive predictive value of 0.701 in the external test. Conclusion: The deep learning models proposed for automated segmentation and detection of bone metastases on spinal MRI demonstrated high diagnostic performance.

• Journal of the Korean Society of Radiology
• /
• v.82 no.5
• /
• pp.1218-1230
• /
• 2021

Purpose To compare the per-patient diagnostic performance of simulated abbreviated MRI (AMRI) to that of conventional MRI (CMRI) with full-sequence dynamic gadoxetic acid (GA) enhancement for early-stage hepatocellular carcinoma (HCC) screening in high-risk patients. Materials and Methods A total of 201 consecutive patients at high-risk for HCC, who underwent 3T liver MRI, were included in this retrospective study. The AMRI protocol comprised T2-weighted imaging, hepatobiliary phase imaging after GA injection, and diffusion-weighted imaging. For each patient, two AMRI and CMRI image sets were independently reviewed by two radiologists. Inter-reader agreement was assessed using Cohen's kappa value. A composite reference standard was used to determine the diagnostic performance of each image set for each reader. Results A total of 93 HCCs were detected in 79 patients. The inter-reader agreement was almost perfect for both image sets (κ = 0.839, 0.948). In AMRI, the per-patient sensitivity and negative predictive values (NPV) were 94.9% and 96.4%, respectively. In CMRI, the per-patient sensitivity and NPV were 96.2% and 97.5%, respectively. Conclusion AMRI, using only three sequences, had a comparable diagnostic performance to CMRI in screening early-stage HCC. AMRI could be an alternative HCC screening tool for high-risk HCC patients.

• Korean Journal of Radiology
• /
• v.24 no.10
• /
• pp.1028-1037
• /
• 2023

Objective: To evaluate the computed tomography (CT) features for diagnosing metastatic cervical lymph nodes (LNs) in patients with differentiated thyroid cancer (DTC) and validate the CT-based risk stratification system suggested by the Korean Thyroid Imaging Reporting and Data System (K-TIRADS) guidelines. Materials and Methods: A total of 463 LNs from 399 patients with DTC who underwent preoperative CT staging and ultrasound-guided fine-needle aspiration were included. The following CT features for each LN were evaluated: absence of hilum, cystic changes, calcification, strong enhancement, and heterogeneous enhancement. Multivariable logistic regression analysis was performed to identify independent CT features associated with metastatic LNs, and their diagnostic performances were evaluated. LNs were classified into probably benign, indeterminate, and suspicious categories according to the K-TIRADS and the modified LN classification proposed in our study. The diagnostic performance of both classification systems was compared using the exact McNemar and Kosinski tests. Results: The absence of hilum (odds ratio [OR], 4.859; 95% confidence interval [CI], 1.593-14.823; P = 0.005), strong enhancement (OR, 28.755; 95% CI, 12.719-65.007; P < 0.001), and cystic changes (OR, 46.157; 95% CI, 5.07-420.234; P = 0.001) were independently associated with metastatic LNs. All LNs showing calcification were diagnosed as metastases. Heterogeneous enhancement did not show a significant independent association with metastatic LNs. Strong enhancement, calcification, and cystic changes showed moderate to high specificity (70.1%-100%) and positive predictive value (PPV) (91.8%-100%). The absence of the hilum showed high sensitivity (97.8%) but low specificity (34.0%). The modified LN classification, which excluded heterogeneous enhancement from the K-TIRADS, demonstrated higher specificity (70.1% vs. 62.9%, P = 0.016) and PPV (92.5% vs. 90.9%, P = 0.011) than the K-TIRADS. Conclusion: Excluding heterogeneous enhancement as a suspicious feature resulted in a higher specificity and PPV for diagnosing metastatic LNs than the K-TIRADS. Our research results may provide a basis for revising the LN classification in future guidelines.

• Korean Journal of Radiology
• /
• v.21 no.10
• /
• pp.1187-1195
• /
• 2020

Objective: This study aimed to determine the sonographic features suggestive of extrathyroidal extension (ETE) of thyroid cancers. Materials and Methods: We retrospectively reviewed the sonographic images of 1656 consecutive patients who had undergone thyroidectomy in 2017. The diagnostic performance of sonographic features suggestive of ETE was evaluated using operation and histopathologic reports. Sonographic features for gross ETE to the strap muscle and minor ETE were assessed for thyroid cancer abutting the anterolateral thyroid capsule. Sonographic features for tracheal invasion were assessed according to whether the angle between the tumor and the trachea was an acute, right, or obtuse angle. Sonographic features for recurrent laryngeal nerve (RLN) invasion were assessed based on the association between the tumor and tracheoesophageal groove (TEG) as preserved normal tissue, abutting or protruding into the TEG. Results: ETE was observed in 783 patients (47.3%), including 123 patients with gross ETE (7.4% [strap muscle, n = 97; RLN, n = 24; and trachea, n = 14]) and 660 patients with minor ETE (39.9%). Regarding the diagnosis of gross and minor ETE to the strap muscle, sonographic features of replacement of the strap muscle and capsular disruption showed the highest positive predictive value (75.9% and 58.5%, respectively). Thyroid cancer forming an obtuse angle with the trachea had the highest sensitivity for the diagnosis of tracheal invasion (85.7%), and thyroid cancer protrusion into the TEG showed the highest sensitivity for the diagnosis of RLN (83.3%). Conclusion: Sonography is considered beneficial in the diagnosis of ETE to the strap muscle, trachea, and RLN. Assessment of ETE is important for the accurate staging of thyroid cancer, which in turn determines the extent of surgery or whether active surveillance is appropriate or not.

• Journal of the Korean Society of Radiology
• /
• v.84 no.6
• /
• pp.1324-1336
• /
• 2023

Purpose This study aimed to compare the diagnostic performance of cardiac CT and transthoracic echocardiogram (TTE) depending on the degree of valvular calcification and bicuspid aortic valve (BAV) subtype. Materials and Methods This retrospective study included 266 consecutive patients (106 with BAV and 160 with tricuspid aortic valve) who underwent cardiac CT and TTE before aortic valve replacement. Cardiac CT was used to evaluate the morphology of the aortic valve, and a calcium scoring scan was used to quantify valve calcium. The aortic valves were classified into fused and two-sinus types. The diagnostic accuracy of cardiac CT and TTE was calculated using a reference standard for intraoperative inspection. Results CT demonstrated significantly higher sensitivity, negative predictive value, and accuracy than TTE in detecting BAV (p < 0.001, p < 0.001, and p = 0.003, respectively). The TTE sensitivity tended to decrease as valvular calcification increased. The error rate of TTE for CT was 10.9% for the twosinus type of BAV and 28.3% for the fused type (p = 0.044). Conclusion Cardiac CT had a higher diagnostic performance in detecting BAV than TTE and may help diagnose BAV, particularly in patients with severe valvular calcification.

• Resources Recycling
• /
• v.33 no.4
• /
• pp.3-14
• /
• 2024

The preheating and calcination processes in cement manufacturing, which are crucial for producing the cement intermediate product clinker, require a substantial quantity of fossil fuels to generate high-temperature thermal energy. However, owing to the ever-increasing severity of environmental pollution, considerable efforts are being made to reduce carbon emissions from fossil fuels in the cement industry. Several preliminary studies have focused on increasing the usage of alternative fuels like refuse-derived fuel (RDF). Alternative fuels offer several advantages, such as reduced carbon emissions, mitigated generation of nitrogen oxides, and incineration in preheaters and kilns instead of landfilling. However, owing to the diverse compositions of alternative fuels, estimating their calorific value is challenging. This makes it difficult to regulate the preheater stability, thereby limiting the usage of alternative fuels. Therefore, in this study, a model based on deep neural networks is developed to accurately predict the preheater temperature and propose optimal fuel input quantities using explainable artificial intelligence. Utilizing the proposed model in actual preheating process sites resulted in a 5% reduction in fossil fuel usage, 5%p increase in the substitution rate with alternative fuels, and 35% reduction in preheater temperature fluctuations.

• Journal of Korean Physical Therapy Science
• /
• v.31 no.3
• /
• pp.31-50
• /
• 2024

Background: The lung capacity prediction formula in Korea is an important judgment standard. Since there is no appropriate lung capacity prediction formula, various prediction formulas are used for foreigners such as Northeast Asians. The purpose of this study is to develop a lung capacity prediction equation by selecting data and setting the selection criteria for normal subjects in accordance with international standards through strict quality control, and to propose a new prediction model. Design: Preliminary feasibility study Methods: A total of 857 people who met the criteria for normal people were finally collected. The tester used for the lung capacity test was the V-Max Encore 22 (Carefusion, California, USA), which is a lung capacity tester proposed by the Korean Society of Tuberculosis and Respiratory Medicine and satisfies accuracy and precision. Among the indicators measured using spirometry, forced vital capacity (FVC), forced expiratory volume in 1 second (FEV₁), forced expiratory volume ratio in 1 second (FEV₁/FVC), forced mid-expiratory flow (Forced expiratory flow 25-75%, FEF25-75%) and peak expiratory flow (PEF) values were collected. Results: This study confirmed a significant correlation between age, height, weight, and pulmonary function indicators. Additionally, it found a correlation between body mass index, which considers the diversity of physical conditions, and pulmonary function indicators. Graphs depicting age-specific pulmonary function indicators by gender, presented as generalized additive model results from collected data, showed a pattern where both FVC and FEV1 increased until the mid-20s and then gradually decreased with aging. FEV1% and PEF exhibited a continuous decrease with aging. Conclusion: This study confirms that there is a significant correlation between weight and pulmonary function in the prediction formula for lung capacity. Additionally, it verifies the correlation between body mass index, which considers the diversity of physical conditions, and pulmonary function. The study suggests that the predicted values are relatively low due to factors such as aging and environmental influences like COVID-19. This preliminary study holds clinical significance for improving the diagnostic accuracy of respiratory symptoms in the elderly.

• Pediatric Infection and Vaccine
• /
• v.17 no.2
• /
• pp.169-176
• /
• 2010

Purpose : We aimed to evaluate predictive parameters for non-response to intravenous immunoglobulin (IVIG) in patients with Kawasaki disease (KD) before IVIG use using two controls. Methods : We evaluated 229 consecutive KD patients who were treated with 2 g/kg of IVIG at a single center. Those who had persistent fever >24 hours after IVIG infusion made up the 23 IVIG non-responders; the first control included a total 206 defervesced cases and the second control included 46 cases that were matched for age and pre-treatment fever duration to non-responders. Results : Demographic and clinical characteristics were similar in IVIG non-responders and responders at presentation. As for laboratory findings, the neutrophil differential, CRP, AST, ALT, and LDH were higher, and lymphocyte differential, total protein, albumin, platelet count, and total cholesterol were significantly lower in IVIG non-responders compared to responders by univariate analysis in both study designs. However in multivariate analysis, non-responders showed a significantly higher neutrophil differential (cutoff value, >77%, sensitivity 68.4% and specificity 79.5%) and lower cholesterol (<124 mg/dL, sensitivity 79% and specificity 70.5%). Whereas plasma albumin (<3.6 g/dL, sensitivity 73.7% and specificity 60%) was the sole laboratory parameter of non-responders in the second study design. Conclusion : Severity of inflammation in KD was reflected by higher or lower laboratory values at presentation. Because the multivariate analysis for these indices may be influenced by some confounding factors, including the numbers of patients of different ages and fever duration, other assessment modalities are needed for KD patients with the greatest risk of coronary artery lesions.

• Pediatric Infection and Vaccine
• /
• v.17 no.2
• /
• pp.108-113
• /
• 2010

Purpose : The aim of this study was to identify clinical availability of serum procalcitonin (PCT) compared with C-reactive protein (CRP) in prediction of bacterial infection in children. Methods : A retrospective study was conducted with children who had been admitted to the Department of Pediatrics with bacterial and viral infection between April 2008 and March 2009 and children who were admitted with Juvenile rheumatoid arthritis (JRA) between August 2007 and July 2009. Serum PCT levels were measured using an enzyme-linked fluorescent assay. Results : The study population included 10 patients with bacterial infection (group I), 69 with viral infection (group II), and 35 with JRA (group III). Mean PCT levels were significantly higher in group I than in group II or group III (P<0.05). Mean CRP levels were significantly higher in group I than in group II (P<0.05); however, mean CRP levels were not significantly higher in group I than in group III (P>0.05). Using a cutoff of 0.5 ng/mL for PCT and 8 mg/L for CRP, sensitivity and specificity in distinguishing between group I and the other groups were 60.0% and 92.3% for PCT and 60.0% and 40.1% for CRP, respectively. Positive and negative predictive values were 42.9% and 96.0% for PCT and 10.0% and 92.6% for CRP, respectively. Conclusion : Measurement of PCT concentrations appears to be more useful than CRP for distinguishing between bacterial infection and non-bacterial diseases in children.

• The Korean Journal of Pesticide Science
• /
• v.8 no.3
• /
• pp.151-161
• /
• 2004

Three dimensional quantitative structure-activity relationships (3D-QSAR) studies for the protox inhibition activities against root and shoot of rice plant (Orysa sativa L.) and barnyardgrass (Echinochloa crus-galli) by a series of new A=3,4,5,6-tetrahydrophthalimino, B=3-chloro-4,5,6,7-tetrahydro-2H-indazolyl and C=3,4-dimethylmaleimino group, and R-group substituted on the phenyl ring in 1-(5-methyl-3-phenylisoxazolin-5-yl)methoxy-2chloro-4-fluorobenzene derivatives were performed using comparative molecular field analyses (CoMFA) methodology with Gasteiger-Huckel charge. Four CoMFA models for the protox inhibition activities against root and shoot of the two plants were generated using 46 molecules as training set and the predictive ability of the each models was evaluated against a test set of 8 molecules. And the statistical results of these models with combination (SIH) of standard field, indicator field and H-bond field showed the best predictability of the protox inhibition activities based on the cross-validated value $r^2_{cv.}$ $(q^2=0.635\sim0.924)$, conventional coefficient $(r^2_{ncv.}=0.928\sim0.977)$ and PRESS value $(0.091\sim0.156)$, respectively. The activities exhibited a strong correlation with steric $(74.3\sim87.4%)$, electrostatic $(10.10\sim18.5%)$ and hydrophobic $(1.10\sim8.30%)$ factors of the molecules. The steric feature of molecule may be an important factor for the activities. We founded that an novel selective and higher protox inhibitors between the two plants may be designed by modification of X-subsitutents for barnyardgrass based upon the results obtained from CoMFA analyses.