• 한국간담췌외과학회지
• /
• 제27권4호
• /
• pp.428-432
• /
• 2023

Minimally invasive pancreatoduodenectomy (MIS PD) is a well reported technique with several advantages over conventional open pancreatoduodenectomy. In comparison to distal pancreatectomy, the adoption of MIS PD has been slow due to the technical challenges involved, particularly in the reconstruction phase of the pancreatojejunostomy (PJ) anastomosis. Hence, we introduce a lowcost model for PJ anastomosis simulation in MIS PD. We fashioned a model of a cut pancreas and limb of jejunum using economical and easily accessible materials comprising felt fabric and the modelling compound, Play-Doh. Surgeons can practice MIS PJ suturing using this model to help mount their individual learning curve for PJ creation. Our video demonstrates that this model can be utilized in simulation practice mimicking steps during live surgery. Our model is a cost-effective and easily replicable tool for surgeons looking to simulate MIS PJ creation in preparation for MIS PD.

• Journal of Information Processing Systems
• /
• 제20권4호
• /
• pp.491-500
• /
• 2024

In hopes of resolving the issue of poor quality of information input for teaching spoken English online, the study creates an English teaching assistance model based on a recognition algorithm named dynamic time warping (DTW) and relies on automated voice recognition technology. In hopes of improving the algorithm's efficiency, the study modifies the speech signal's time-domain properties during the pre-processing stage and enhances the algorithm's performance in terms of computational effort and storage space. Finally, a simulation experiment is employed to evaluate the model application's efficacy. The study's revised DTW model, which achieves recognition rates of above 95% for all phonetic symbols and tops the list for cloudy consonant recognition with rates of 98.5%, 98.8%, and 98.7% throughout the three tests, respectively, is demonstrated by the study's findings. The enhanced model for DTW voice recognition also presents higher efficiency and requires less time for training and testing. The DTW model's KS value, which is the highest among the models analyzed in the KS value analysis, is 0.63. Among the comparative models, the model also presents the lowest curve position for both test functions. This shows that the upgraded DTW model features superior voice recognition capabilities, which could significantly improve online English education and lead to better teaching outcomes.

• 한국응용과학기술학회지
• /
• 제37권3호
• /
• pp.473-483
• /
• 2020

본 논문은 지각된 가치가 적용된 관광 행동의도 정보를 이용한 지능형 클라우드 환경에서의 관광추천시스템을 제안한다. 이 제안 시스템은 관광정보와 관광객의 지각적 가치가 행동의도에 반영되는 실증적 분석 정보를 와이드 앤 딥러닝 기술을 이용하여 관광추천시스템에 적용하였다. 본 제안 시스템은 다양하게 수집할 수 있는 관광 정보와 관광객이 평소에 지각하고 있던 가치와 사람의 행동에서 나타나는 의도를 수집 분석하여 관광 추천시스템에 적용하였다. 이는 기존에 활용되던 다양한 분야의 관광플랫폼에 관광 정보, 지각된 가치 및 행동의도에 대한 연관성을 분석하고 매핑하여, 실증적 정보를 제공한다. 그리고 관광정보와 관광객의 지각적 가치가 행동의도에 반영되는 실증적 분석 정보를 선형 모형 구성요소와 신경만 구성요소를 합께 학습하여 한 모형에서 암기 및 일반화 모두를 달성할 수 있는 와이드 앤 딥러닝 기술을 이용한 관광추천 시스템을 제시하였고, 파이프라인 동작 방법을 제시하였다. 본 논문에서 제시한 추천시스템은 와이드 앤 딥러닝 모형을 적용한 결과 관광관련 앱 스토어 방문 페이지 상의 앱 가입률이 대조군 대비 3.9% 향상했고, 다른 1% 그룹에 변수는 동일하고 신경망 구조의 깊은 쪽만 사용한 모형을 적용하여 결과 와이드 앤 딥러닝 모형은 깊은 쪽만 사용한 모형 대비해서 가입률을 1% 증가하였다. 또한, 데이터셋에 대해 수신자 조작 특성 곡선 아래 면적(AUC)을 측정하여, 오프라인 AUC 또한 와이드 앤 딥러닝 모형이 다소 높지만 온라인 트래픽에서 영향력이 더 강하다는 것을 도출하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -1
• /
• pp.417-420
• /
• 2002

Recent works in the area of multimedia studies focus on a wide range of issues from the impact of multimedia on culture to its impact on economics and anything in between. The interconnectedness of the issues raised by this new practice is complicated by the fact that media are rapidly converging: in a very real way, multimedia is becoming a media prism that reflects the way in which media continually influence each other across disciplines and cultural borders. Thus, the impact of multimedia reflects a complicated crossroads where media, human experience, culture and technology converge. An effective design is generally based on shaping aesthetics for function and utility, with an emphasis on ease of use. However, in designing for cyberspace, it is possible to create narratives that challenge the interactor by encoding in the design an instructional aspect that teaches new approaches and forms. Such a design offers an equally aesthetic experience for the interactor as they explore the meaning of the work. This design approach has been used constructively in many applications. The crucial concern is to determine how little or how much information must be presented for the interactor to achieve a suitable level of cognition. This is always a balancing act: too much difficulty will result in interactor frustration and the abandonment of the activity and too little will result in boredom leading to the same negative result In addition, it can be anticipated that the interactor will bring her or his own level of experiential cognition and/or accretion, to the experience providing reflective cognition and/or restructure the learning curve. If the design of the application is outside their present experience, interactors will begin with established knowledge in order to explore the new work. Thus, it may be argued that the interactor explores, learns and cognates simultaneously based on primary experiential cognition. Learning is one of the most important keys to establishing a comfort level in a new media work. Once interactors have learned a new convention, they apply this cognitive knowledge to other new media experiences they may have. Pierre Levy would describe this process as a "new nomadism" that creates "an invisible space of understanding, knowledge, and intellectual power, within which new qualities of being and new ways of fashioning a society will flourish and mutate" (Levy xxv 1997). Thus, navigation itself of offers the interactors the opportunity to both apply and loam new cognitive skills. This suggests that new media narrative strategies are still in the process of developing unique conventions and, as a result, have not reached a level of coherent grammar. This paper intends to explore the cognitive aspects of new media design and in particular, will explore issues related to the design of new media interfaces. The paper will focus on the creation of narrative strategies that engage interactors through loaming curves thus enhancing interactivity.vity.

• Safety and Health at Work
• /
• 제10권4호
• /
• pp.452-460
• /
• 2019

Background: Monitoring and control of PM_2.5 are being recognized as key to address health issues attributed to PM_2.5. Availability of low-cost PM_2.5 sensors made it possible to introduce a number of portable PM_2.5 monitors based on light scattering to the consumer market at an affordable price. Accuracy of light scatteringe-based PM_2.5 monitors significantly depends on the method of calibration. Static calibration curve is used as the most popular calibration method for low-cost PM_2.5 sensors particularly because of ease of application. Drawback in this approach is, however, the lack of accuracy. Methods: This study discussed the calibration of a low-cost PM_2.5-monitoring device (PMD) to improve the accuracy and reliability for practical use. The proposed method is based on construction of the PM_2.5 sensor network using Message Queuing Telemetry Transport (MQTT) protocol and web query of reference measurement data available at government-authorized PM monitoring station (GAMS) in the republic of Korea. Four machine learning (ML) algorithms such as support vector machine, k-nearest neighbors, random forest, and extreme gradient boosting were used as regression models to calibrate the PMD measurements of PM_2.5. Performance of each ML algorithm was evaluated using stratified K-fold cross-validation, and a linear regression model was used as a reference. Results: Based on the performance of ML algorithms used, regression of the output of the PMD to PM_2.5 concentrations data available from the GAMS through web query was effective. The extreme gradient boosting algorithm showed the best performance with a mean coefficient of determination (R²) of 0.78 and standard error of 5.0 ㎍/㎥, corresponding to 8% increase in R² and 12% decrease in root mean square error in comparison with the linear regression model. Minimum 100 hours of calibration period was found required to calibrate the PMD to its full capacity. Calibration method proposed poses a limitation on the location of the PMD being in the vicinity of the GAMS. As the number of the PMD participating in the sensor network increases, however, calibrated PMDs can be used as reference devices to nearby PMDs that require calibration, forming a calibration chain through MQTT protocol. Conclusions: Calibration of a low-cost PMD, which is based on construction of PM_2.5 sensor network using MQTT protocol and web query of reference measurement data available at a GAMS, significantly improves the accuracy and reliability of a PMD, thereby making practical use of the low-cost PMD possible.

• 디지털융복합연구
• /
• 제17권2호
• /
• pp.217-230
• /
• 2019

본 연구는 기존 동반질환을 이용한 중증도 보정 방법의 제한점을 보완하기 위해 급성심근경색증 환자의 맞춤형 중증도 보정방법을 개발하고, 이의 타당성을 평가하기 위해 수행되었다. 이를 위하여 질병관리본부에서 2006년부터 2015년까지 10년간 수집한 퇴원손상심층조사 자료 중 주진단이 급성심근경색증인 한국표준질병사인분류(KCD-7) 코드 I20.0~I20.9의 대상자를 추출하였고, 동반질환 중증도 보정 도구로는 기존 활용되고 있는 CCI(Charlson comorbidity index), ECI(Elixhauser comorbidity index)와 새로이 제안하는 CCS(Clinical Classification Software)를 사용하였다. 이에 대한 중증도 보정 사망예측모형 개발을 위하여 머신러닝 기법인 로지스틱 회귀분석, 의사결정나무, 신경망, 서포트 벡터 머신기법을 활용하여 비교하였고 각각의 AUC(Area Under Curve)를 이용하여 개발된 모형을 평가하였다. 이를 평가한 결과 중증도 보정도구로는 CCS 가 가장 우수한 것으로 나타났으며, 머신러닝 기법 중에서는 서포트 벡터 머신을 이용한 모형의 예측력이 가장 우수한 것으로 확인되었다. 이에 향후 의료서비스 결과평가 등 중증도 보정을 위한 연구에서는 본 연구에서 제시한 맞춤형 중증도 보정방법과 머신러닝 기법을 활용하도록 하는 것을 제안한다.

• Korean Journal of Radiology
• /
• 제22권7호
• /
• pp.1213-1224
• /
• 2021

Objective: To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. Materials and Methods: Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. Results: Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. Conclusion: CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.

• Korean Journal of Radiology
• /
• 제25권4호
• /
• 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.

• Korean Journal of Radiology
• /
• 제23권7호
• /
• pp.720-731
• /
• 2022

Objective: We aimed to develop and test a deep learning algorithm (DLA) for fully automated measurement of the volume and signal intensity (SI) of the liver and spleen using gadoxetic acid-enhanced hepatobiliary phase (HBP)-magnetic resonance imaging (MRI) and to evaluate the clinical utility of DLA-assisted assessment of functional liver capacity. Materials and Methods: The DLA was developed using HBP-MRI data from 1014 patients. Using an independent test dataset (110 internal and 90 external MRI data), the segmentation performance of the DLA was measured using the Dice similarity score (DSS), and the agreement between the DLA and the ground truth for the volume and SI measurements was assessed with a Bland-Altman 95% limit of agreement (LOA). In 276 separate patients (male:female, 191:85; mean age ± standard deviation, 40 ± 15 years) who underwent hepatic resection, we evaluated the correlations between various DLA-based MRI indices, including liver volume normalized by body surface area (LV_BSA), liver-to-spleen SI ratio (LSSR), MRI parameter-adjusted LSSR (aLSSR), LSSR × LV_BSA, and aLSSR × LV_BSA, and the indocyanine green retention rate at 15 minutes (ICG-R15), and determined the diagnostic performance of the DLA-based MRI indices to detect ICG-R15 ≥ 20%. Results: In the test dataset, the mean DSS was 0.977 for liver segmentation and 0.946 for spleen segmentation. The Bland-Altman 95% LOAs were 0.08% ± 3.70% for the liver volume, 0.20% ± 7.89% for the spleen volume, -0.02% ± 1.28% for the liver SI, and -0.01% ± 1.70% for the spleen SI. Among DLA-based MRI indices, aLSSR × LV_BSA showed the strongest correlation with ICG-R15 (r = -0.54, p < 0.001), with area under receiver operating characteristic curve of 0.932 (95% confidence interval, 0.895-0.959) to diagnose ICG-R15 ≥ 20%. Conclusion: Our DLA can accurately measure the volume and SI of the liver and spleen and may be useful for assessing functional liver capacity using gadoxetic acid-enhanced HBP-MRI.

• Korean Journal of Radiology
• /
• 제23권10호
• /
• pp.949-958
• /
• 2022

Objective: To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA). Materials and Methods: Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions. Results: Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram. Conclusion: Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.