• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.334-343
• /
• 2021

Objective: We aimed to develop a prediction model for diagnosing severe aortic stenosis (AS) using computed tomography (CT) radiomics features of aortic valve calcium (AVC) and machine learning (ML) algorithms. Materials and Methods: We retrospectively enrolled 408 patients who underwent cardiac CT between March 2010 and August 2017 and had echocardiographic examinations (240 patients with severe AS on echocardiography [the severe AS group] and 168 patients without severe AS [the non-severe AS group]). Data were divided into a training set (312 patients) and a validation set (96 patients). Using non-contrast-enhanced cardiac CT scans, AVC was segmented, and 128 radiomics features for AVC were extracted. After feature selection was performed with three ML algorithms (least absolute shrinkage and selection operator [LASSO], random forests [RFs], and eXtreme Gradient Boosting [XGBoost]), model classifiers for diagnosing severe AS on echocardiography were developed in combination with three different model classifier methods (logistic regression, RF, and XGBoost). The performance (c-index) of each radiomics prediction model was compared with predictions based on AVC volume and score. Results: The radiomics scores derived from LASSO were significantly different between the severe AS and non-severe AS groups in the validation set (median, 1.563 vs. 0.197, respectively, p < 0.001). A radiomics prediction model based on feature selection by LASSO + model classifier by XGBoost showed the highest c-index of 0.921 (95% confidence interval [CI], 0.869-0.973) in the validation set. Compared to prediction models based on AVC volume and score (c-indexes of 0.894 [95% CI, 0.815-0.948] and 0.899 [95% CI, 0.820-0.951], respectively), eight and three of the nine radiomics prediction models showed higher discrimination abilities for severe AS. However, the differences were not statistically significant (p > 0.05 for all). Conclusion: Models based on the radiomics features of AVC and ML algorithms may perform well for diagnosing severe AS, but the added value compared to AVC volume and score should be investigated further.

• Tuberculosis and Respiratory Diseases
• /
• v.58 no.6
• /
• pp.562-569
• /
• 2005

Background : The severity scoring system is useful for predicting the outcome of critically ill patients. However, the system is quite complicated and cost-ineffective. Simple serologic markers have been proposed to predict the outcome, which include troponin-I, lactate and C-reactive protein(CRP). The aim of this study was to evaluate the prognostic values of troponin-I, lactate and CRP in critically ill non-cardiac patients. Methods : From September 2003 to June 2004, 139 patients(Age: $63.3{\pm}14.7$, M:F = 88:51), who were admitted to the MICU with non-cardiac critical illness at Gyeongsang National University Hospital, were enrolled in this study. This study evaluated the severity of the illness and the multi-organ failure score (Acute Physiologic and Chronic Health EvaluationII, Simplified Acute Physiologic ScoreII and Sequential Organ Failure Assessment) and measured the troponin-I, lactate and CRP within 24 hours after admission in the MICU. Each value in the survivors and non-survivors was compared at the 10th and 30th day after ICU admission. The mortality rate was compared at 10th and 30th day in normal and abnormal group. In addition, the correlations between each value and the severity score were assessed. Results : There were significantly higher troponin-I and CRP levels, not lactate, in the non-survivors than in the survivors at 10th day($1.018{\pm}2.58ng/ml$, $98.48{\pm}69.24mg/L$ vs. $4.208{\pm}10.23ng/ml$, $137.69{\pm}70.18mg/L$) (p<0.05). There were significantly higher troponin-I, lactate and CRP levels in the non-survivors than in the survivors on the 30th day ($0.99{\pm}2.66ng/ml$, $8.02{\pm}9.54ng/dl$, $96.87{\pm}68.83mg/L$ vs. $3.36{\pm}8.74ng/ml$, $15.42{\pm}20.57ng/dl$, $131.28{\pm}71.23mg/L$) (p<0.05). The mortality rate was significantly higher in the abnormal group of troponin-I, lactate and CRP than in the normal group of troponin-I, lactate and CRP at 10th day(28.1%, 31.6%, 18.9% vs. 11.0%, 15.8 %, 0%) and 30th day(38.6%, 47.4%, 25.8% vs. 15.9%, 21.7%, 14.3%) (p<0.05). Troponin-I and lactate were significantly correlated with the SAPS II score($r^2=0.254$, 0.365, p<0.05). Conclusion : Measuring the troponin-I, lactate and CRP levels upon admission may be useful for predicting the outcome of critically ill non-cardiac patients.

• Korean Journal of Acupuncture
• /
• v.26 no.4
• /
• pp.225-235
• /
• 2009

Objective : The purpose of this study was to report a case of a treatment with Scolopendrae Corpus Herbal-Acupuncture for one patient suffering from the Cervical Myelopathy. Scolopendrae Corpus Herbal-Acupuncture has been used as a analgesics and antispasmodics in the oriental medicine and reported to have antiinflammatory effect, sedative action and immunity enhancing activity, on one patient suffering from the Cervical Myelopathy. Methods : TThe patient was treated with Scolopendrae Corpus Herbal-Acupuncture, acupuncture, herbal medication. Scolopendrae Corpus Pharmacopuncture was administered two or three times per week and we injected 0.2~1.0 ml of Scolopendrae Corpus Pharmacopuncture to the patient's neck and both arms. The improvement of the symptoms was evaluated by JOA score(Japanese Orthopedic Association score), Nurick grading, VAS(Visual Analog Scale), reflex testing, Finger escape sign, Grip and Release test. Result : After 5 weeks of treatment, the patient's JOA score, Nurick grading and VAS were improved from 12 to 16, from grade III to grade II and from 10 to 3 respectively. The movement and power of upper and lower limbs were restored to nearly normal range.

• CELLMED
• /
• v.12 no.3
• /
• pp.10.1-10.12
• /
• 2022

Objective: The objective of the study was to evaluate the effect of Sharbat Afsantin in Polycystic Ovarian Disease. Methods: An open observational study was carried out in the Department of Ilmul Qabalat wa Amraze Niswan. Diagnosed cases(n=30) of PCOD were included in the study. Patients with thyroid dysfunction, systemic diseases, on hormonal treatment in last three months, pregnancy and lactation were excluded. Research drug (Sharbat Afsantin) was administered orally in a dose of 25ml twice daily for 15 days/cycle for three consecutive cycles. Outcome measures were, changes in subjective parameters (duration of cycle, duration and amount of flow and weight reduction) and objective parameters {pictorial blood loss assessment chart (PBAC) score, basal metabolic index (BMI), modified Ferriman Gallwey (mFG) score, acanthosis nigricans scale and pelvic ultrasonography}. Data were analyzed using paired Student 't' test. Results: Changes in duration of cycle, duration and amount of flow were achieved in 83.3%, 50% and 40% patients respectively and weight reduction in 30% patients. Changes in PBAC score and BMI were achieved in 50% and 30% patients respectively and 30% patients showed normal findings on pelvic ultrasonography. Conclusion: Sharbat Afsantin can be used as an alternate remedy in PCOD patients, as it has significant effect to regularize menstruation by reduction in BMI and probably by improving insulin resistance in PCOD. No adverse effect of Sharbat Afsantin was noted during the trial.

• Speech Sciences
• /
• v.10 no.2
• /
• pp.77-84
• /
• 2003

In this research, we seek the beginning of the speech and detect the stationary speech region using lip information. Performing running average of the estimated speech signal in the stationary region, we reduce the effect of musical noise which is inherent to the conventional MlMSE (Minimum Mean Square Error) speech enhancement algorithm. In addition to it, SFM (Spectral Flatness Measure) is incorporated to reduce the speech signal estimation error due to speaking habit and some lacking lip information. The proposed algorithm with Wiener filtering shows the superior performance to the conventional methods according to MOS (Mean Opinion Score) test.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.148-150
• /
• 2001

MusicXML, ScoreML과 같은 포맷은 음악을 XML로 표현한 것으로 음정, 박자, 조성, 리듬, 화음 등 모든 정보를 표현하기 위해 고안되었다. 즉, XML이 가지고 있는 간단성, 확장성, 재사용성의 장점을 가지며 분석, 검색, 표기법에 훨씬 큰 장점을 가진 마크업 언어들이다. 기존의 음악 검색에 대한 연구들이 음악파일에 대한 것에 행해졌던 것에 비해 본 논문은 음악을 덱스트로 표현한 XML에서 효과적인 선율 검색을 위해 계이름을 사용한 검색시스템을 제안한다.

• Medical Lasers
• /
• v.9 no.2
• /
• pp.166-171
• /
• 2020

Background and Objectives Melasma is an acquired pigmentary disorder characterized by brown or dark brown colored macules and patches which mostly involve the face. Compared to nanosecond lasers, picosecond lasers have fewer adverse effects on surrounding tissues and give better results for melanin fragmentation. The purpose of this study was to evaluate the efficacy of the pico-toning technique using a low fluence 1,064-nm Nd:YAG laser on melasma patients. Materials and Methods This study is a retrospective analysis of melasma cases treated using the pico-toning technique from June 2017 to November 2020. Based on photographic images, the modified Melasma Area and Severity Index (mMASI) score was blind evaluated by two independent plastic surgeons. Patient satisfaction was assessed through a 5-point Likert scale questionnaire after treatment sessions. All adverse effects and complications were reviewed based on medical records. Results A total of 23 patients were included in the study. The mMASI scores for baseline and 2 months after the last procedure were 5.1 ± 1.4 and 2.6 ± 0.4, respectively. The mean mMASI score reduced significantly after the treatment session (p < 0.05). The patient satisfaction score with the procedure was 3.8 ± 1.0. The subject satisfaction score and difference in the mMASI score before the procedure and 2 months after the last procedure showed a significant correlation. Adverse effects observed in this study were erythema (n = 1) and edema (n = 1). Conclusion The results of the study show that the pico-toning technique is effective in Asian patients with melasma. We believe that safety was enhanced by using low fluence, and thus better results were achieved with fewer adverse effects.

• The Journal of the Korean bone and joint tumor society
• /
• v.16 no.2
• /
• pp.80-86
• /
• 2010

Purpose: The skeleton is commonly affected by metastatic cancer. The purpose of this study was to evaluate the results of treating metastatic pathologic fractures in lower extremities using locking plates. Materials and Methods: Between 2004 and 2010, we evaluated 12 patients (13 cases) of metastatic pathologic fractures in lower extremities, treated with the locking plate. Mean patient age was 62.2 years (range, 50-81 years), the locations of the fractures were; proximal femur in 2 cases, femoral mid-shaft in 3, distal femur in 3, proximal tibia in 4, and distal tibia in 1 case. The interval to wheelchair ambulation, pain relief and complications were evaluated. Additionally, we assessed operation time and postoperative blood loss. Results: Mean time from operation to wheelchair ambulation was 3.2 days (range, 1-6 days). Mean VAS scores improved from a preoperative score of 8.1 points (range, 7-9 points) to a score of 2.7 points (range, 2-4 points) at 1 week postoperatively. No early complications associated with surgery were encountered. Mean operation time was 88.4 minutes (range, 70-105 minutes), and mean postoperative blood loss was 246.5 ml (range, 130-320 ml). Conclusion: Internal fixation of metastatic pathologic fractures using a locking plate in the lower extremity can be an effective treatment option in the meta- or diaphyseal area of long bones with massive bony destruction or poor bone stock by offering early ambulation, pain relief and low postoperative complications.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.1100-1118
• /
• 2021

In a wide range of ML applications, the training data contains privacy-sensitive information that should be kept secure. Training the ML systems by privacy-sensitive data makes the ML model inherent to the data. As the structure of the model has been fine-tuned by training data, the model can be abused for accessing the data by the estimation in a reverse process called model inversion attack (MIA). Although, MIA has been applied to shallow neural network models of recognizers in literature and its threat in privacy violation has been approved, in the case of a deep learning (DL) model, its efficiency was under question. It was due to the complexity of a DL model structure, big number of DL model parameters, the huge size of training data, big number of registered users to a DL model and thereof big number of class labels. This research work first analyses the possibility of MIA on a deep learning model of a recognition system, namely a face recognizer. Second, despite the conventional MIA under the white box scenario of having partial access to the users' non-sensitive information in addition to the model structure, the MIA is implemented on a deep face recognition system by just having the model structure and parameters but not any user information. In this aspect, it is under a semi-white box scenario or in other words a gray-box scenario. The experimental results in targeting five registered users of a CNN-based face recognition system approve the possibility of regeneration of users' face images even for a deep model by MIA under a gray box scenario. Although, for some images the evaluation recognition score is low and the generated images are not easily recognizable, but for some other images the score is high and facial features of the targeted identities are observable. The objective and subjective evaluations demonstrate that privacy cyber-attack by MIA on a deep recognition system not only is feasible but also is a serious threat with increasing alert state in the future as there is considerable potential for integration more advanced ML techniques to MIA.

• Korean Journal of Food Science and Technology
• /
• v.24 no.5
• /
• pp.440-446
• /
• 1992

Samil-ju, the traditional Korean rice wine was brewed and distilled using different columns (unpacked and packed) at different pressure (760, 460, 260 mmHg). Fractions of distillate were collected and analyzed. The sample wine, Samil-ju showed the following compositions; ethanol 14%, total acidity 16.2 g/100 ml, reducing sugar 7.9 mg/ml, total sugar 8.4 mg/ml, acetaldehyde 6 ppm, fusel oil acetaldehyde and ethyl acetate 6 ppm. As distillation proceeds, contents of ethanol, methanol, fusel oil, acetaldehyde and ethyl acetate were decreased but total acidity was increased. Generally at reduced pressure, all the constituents but total acidity showed more decrease than those at atmospheric pressure. In the 1st, 2nd and 3rd fractions of the distillate, ethanol contents were maintained at about 70% but those contents decreased abruptly to below 50% from the 5th fraction. Sixteen sensory characteristics were identified as quality factors of distillate. Among them, four characteristics were identified as aroma properties, seven as tastes and five as aftertastes. Nuruk and cooling flavor were considered as important factors which affect greatly the sensory quality of distillate. Among various fractions, the 2nd, 3rd and 4th fractions obtained from unpacked column at 260 mmHg showed the highest score in the overall quality. The compositions of these fractions were ranged as follows; methanol $24{\sim}36\;ppm$, total acidity $0.21{\sim}0.29\;g/100\;ml$, fusel oil 657-1340 ppm, acetaldehyde $12{\sim}41\;ppm$, and ethylacetate $22{\sim}311\;ppm$, respectively.