• Korean Journal of Radiology
• /
• v.21 no.10
• /
• pp.1150-1160
• /
• 2020

Objective: To describe the experience of implementing a deep learning-based computer-aided detection (CAD) system for the interpretation of chest X-ray radiographs (CXR) of suspected coronavirus disease (COVID-19) patients and investigate the diagnostic performance of CXR interpretation with CAD assistance. Materials and Methods: In this single-center retrospective study, initial CXR of patients with suspected or confirmed COVID-19 were investigated. A commercialized deep learning-based CAD system that can identify various abnormalities on CXR was implemented for the interpretation of CXR in daily practice. The diagnostic performance of radiologists with CAD assistance were evaluated based on two different reference standards: 1) real-time reverse transcriptase-polymerase chain reaction (rRT-PCR) results for COVID-19 and 2) pulmonary abnormality suggesting pneumonia on chest CT. The turnaround times (TATs) of radiology reports for CXR and rRT-PCR results were also evaluated. Results: Among 332 patients (male:female, 173:159; mean age, 57 years) with available rRT-PCR results, 16 patients (4.8%) were diagnosed with COVID-19. Using CXR, radiologists with CAD assistance identified rRT-PCR positive COVID-19 patients with sensitivity and specificity of 68.8% and 66.7%, respectively. Among 119 patients (male:female, 75:44; mean age, 69 years) with available chest CTs, radiologists assisted by CAD reported pneumonia on CXR with a sensitivity of 81.5% and a specificity of 72.3%. The TATs of CXR reports were significantly shorter than those of rRT-PCR results (median 51 vs. 507 minutes; p < 0.001). Conclusion: Radiologists with CAD assistance could identify patients with rRT-PCR-positive COVID-19 or pneumonia on CXR with a reasonably acceptable performance. In patients suspected with COVID-19, CXR had much faster TATs than rRT-PCRs.

• Journal of Korean Elementary Science Education
• /
• v.43 no.2
• /
• pp.233-251
• /
• 2024

Meaningful learning occurs through an active process of engaging with the content in a lively interaction between teacher and student. In this study, we explored teachers' learning, challenges, and changes as they learned and practiced responsive teaching (RT), a practice that supports students to put their ideas at the center of their lessons. As a result, we found that teachers initially embraced RT from different perspectives and struggled to implement it in ways they understood. We then explored RT more deeply by focusing on the case of a teacher who was teaching science herself, and found that her experience was both rewarding and confusing. However, by the end of the learning process, the teachers were able to define RT in their own ways, which strengthened their commitment to implementing RT in elementary science education. Based on this teacher learning process, it was suggested that teachers should be viewed as curriculum experts, that they should learn and explore collaboratively through a community of teachers, and that they should be researchers who continue to explore various practices in the field.

• Journal of Radiation Protection and Research
• /
• v.44 no.4
• /
• pp.149-155
• /
• 2019

Background: Magnetic resonance (MR) image guided radiation therapy system, enables real time MR guided radiotherapy (RT) without additional radiation exposure to patients during treatment. However, MR image lacks electron density information required for dose calculation. Image fusion algorithm with deformable registration between MR and computed tomography (CT) was developed to solve this issue. However, delivered dose may be different due to volumetric changes during image registration process. In this respect, synthetic CT generated from the MR image would provide more accurate information required for the real time RT. Materials and Methods: We analyzed 1,209 MR images from 16 patients who underwent MR guided RT. Structures were divided into five tissue types, air, lung, fat, soft tissue and bone, according to the Hounsfield unit of deformed CT. Using the deep learning model (U-NET model), synthetic CT images were generated from the MR images acquired during RT. This synthetic CT images were compared to deformed CT generated using the deformable registration. Pixel-to-pixel match was conducted to compare the synthetic and deformed CT images. Results and Discussion: In two test image sets, average pixel match rate per section was more than 70% (67.9 to 80.3% and 60.1 to 79%; synthetic CT pixel/deformed planning CT pixel) and the average pixel match rate in the entire patient image set was 69.8%. Conclusion: The synthetic CT generated from the MR images were comparable to deformed CT, suggesting possible use for real time RT. Deep learning model may further improve match rate of synthetic CT with larger MR imaging data.

• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.213-222
• /
• 2024

This study analyzed the volumes generated by deep learning and atlas-based automatic segmentation methods, as well as the Dice similarity coefficient and 95% Hausdorff distance, according to the conditions of conduction voltage and conduction current in computed tomography for lung radiotherapy. The first result, the volumes generated by the atlas-based smart segmentation method showed the smallest volume change as a function of the change in tube voltage and tube current, while Aview RT ACS and OncoStudio using deep learning showed smaller volumes at tube currents lower than 100 mA. The second result, the Dice similarity coefficient, showed that Aview RT ACS was 2% higher than OncoStuido, and the 95% Hausdorff distance results also showed that Aview RT ACS analyzed an average of 0.2-0.5% higher than OncoStudio. However, the standard deviation of the respective results for tube current and tube voltage is lower for OncoStudio, which suggests that the results are consistent across volume variations. Therefore, caution should be exercised when using deep learning-based automatic segmentation programs at low perfusion voltages and low perfusion currents in CT imaging conditions for lung radiotherapy, and similar results were obtained with conventional atlas-based automatic segmentation programs at certain perfusion voltages and perfusion currents.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.38-59
• /
• 2022

Web services instances can be classified into two categories, namely trusted and untrusted from users. A web service with high throughput (TP) and low response time (RT) instance values is a trusted web service. Web services are not trustworthy due to the mismatch in the guaranteed instance values and the actual values achieved by users. To perform web services selection from users' attained TP and RT values, we need to verify the correct prediction of trusted and untrusted instances from invoked web services. This accurate prediction of web services instances is used to perform the selection of web services. We propose to construct fuzzy rules to label web services instances correctly. This paper presents web services selection using a well-known machine learning algorithm, namely REPTree, for the correct prediction of trusted and untrusted instances. Performance comparison of REPTree with five machine learning models is conducted on web services datasets. We have performed experiments on web services datasets using a ten k-fold cross-validation method. To evaluate the performance of the REPTree classifier, we used accuracy metrics (Sensitivity and Specificity). Experimental results showed that web service (WS1) gained top selection score with the (47.0588%) trusted instances, and web service (WS2) was selected the least with (25.00%) trusted instances. Evaluation results of the proposed web services selection approach were found as (asymptotic sig. = 0.019), demonstrating the relationship between final selection and recommended trust score of web services.

• Physical Therapy Korea
• /
• v.10 no.3
• /
• pp.17-27
• /
• 2003

Repetitive transcranial magnetic stimulation (rTMS) modulates cortical excitability beyond the duration of the rTMS trains themselves. Depending on rTMS parameters, a lasting inhibition or facilitation of cortical excitability can be induced. Therefore, rTMS of high or low frequency over motor cortex may change certain aspects of motor learning performance and cortical activation. This study investigated the effect of high and low frequency subthreshold rTMS applied to the motor cortex on motor learning of sequential finger movements and brain activation using functional MRI (fMRI). Three healthy right-handed subjects (mean age 23.3) were enrolled. All subjects were trained with sequences of seven-digit rapid sequential finger movements, 30 minutes per day for 5 consecutive days using their left hand. 10 Hz (high frequency) and 1 Hz (low frequency) trains of rTMS with 80% of resting motor threshold and sham stimulation were applied for each subject during the period of motor learning. rTMS was delivered on the scalp over the right primary motor cortex using a figure-eight shaped coil and a Rapid(R) stimulator with two Booster Modules (Magstim Co. Ltd, UK). Functional MRI (fMRI) was performed on a 3T ISOL Forte scanner before and after training in all subjects (35 slices per one brain volume TR/TE = 3000/30 ms, Flip angle $60^{\circ}$, FOV 220 mm, $64{\times}64$ matrix, slice thickness 4 mm). Response time (RT) and target scores (TS) of sequential finger movements were monitored during the training period and fMRl scanning. All subjects showed decreased RT and increased TS which reflecting learning effects over the training session. The subject who received high frequency rTMS showed better performance in TS and RT than those of the subjects with low frequency or sham stimulation of rTMS. In fMRI, the subject who received high frequency rTMS showed increased activation of primary motor cortex, premotor, and medial cerebellar areas after the motor sequence learning after the training, but the subject with low frequency rTMS showed decreased activation in above areas. High frequency subthreshold rTMS on the motor cortex may facilitate the excitability of motor cortex and improve the performance of motor sequence learning in normal subject.

• The Journal of the Korea Contents Association
• /
• v.17 no.10
• /
• pp.30-40
• /
• 2017

The purpose of this study is to analyze the long term mediating effects of Self-regulated Learning(SRL) in the Relationships among the Perceptions of Middle School Students on the Democratic Attitude of Parenting(DAP) and their Relationships with Teachers(RT), and their Self-esteem(SE). The data sources were from the first (2010) and the third (2012) Korean Children & Youth Panel Survey(KCYPS). As a result, first, the perceived DAP had significant effects on the students' SE both directly and indirectly through SRL. Second, the perception on RT had indirect effects on their SE mediated by SRL. Third, this pattern in first year continued in two-year-later-SE. This study implies that DAP, RT, and SRL play important roles in the continuous development of adolescents' self-esteem.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.323-328
• /
• 2020

Recently, new approaches that significantly improve performance in object detection and recognition using deep learning technology have been proposed quickly. Of the various techniques for object detection, especially facial object detection (Faster R-CNN, R-CNN, YOLO, SSD, etc), SSD is superior in accuracy and speed to other techniques. At the same time, multiple object detection networks are also readily available. In this paper, among object detection networks, Mobilenet v2 network is used, models combined with SSDs are trained, and methods for detecting objects at a rate of four times or more than conventional performance are proposed using TensorRT engine, and the performance is verified through experiments. Facial object detector was created as an application to verify the performance of the proposed method, and its behavior and performance were tested in various situations.

• Advances in materials Research
• /
• v.11 no.1
• /
• pp.75-90
• /
• 2022

In this paper, functionality of soft computing algorithms such as Group method of data handling (GMDH), Random forest (RF), Random tree (RT), Linear regression (LR), M5P, and artificial neural network (ANN) have been looked out to predict the compressive strength of concrete mixed with marble powder. Assessment of result suggests that, the overall performance of ANN based model gives preferable results over the different applied algorithms for the estimate of compressive strength of concrete. The results of coefficient of correlation were maximum in ANN model (0.9139) accompanied through RT with coefficient of correlation (CC) value 0.8241 and minimum root mean square error (RMSE) value of ANN (4.5611) followed by RT with RMSE (5.4246). Similarly, other evaluating parameters like, Willmott's index and Nash-sutcliffe coefficient value of ANN was 0.9458 and 0.7502 followed by RT model (0.8763 and 0.6628). The end result showed that, for both subsets i.e., training and testing subset, ANN has the potential to estimate the compressive strength of concrete. Also, the results of sensitivity suggest that the water-cement ratio has a massive impact in estimating the compressive strength of concrete with marble powder with ANN based model in evaluation with the different parameters for this data set.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.5
• /
• pp.102-108
• /
• 1996

Adaptive resonance theory (ART2) characterized by its built-in mechanism of handling the stability-plasticity switching and by the adaptive learning without forgetting informations learned in the past, is based on an unsupervised template matching. We propose an improved tow-stage learning algorithm for aRT2: the original unsupervised learning followed by a new supervised learning. Each of the output nodes, after the unsupervised learning, is labeled according to the category informations to reinforce the template pattern associated with the target output node belonging to the same category some dominant classes from exhausting a finite number of template patterns in ART2 inefficiently. Experimental results on a set of 2545 FLIR images show that the ART2 trained by the two-stage learning algorithm yields better accuracy than the original ART2, regardless of th esize of the network and the methods of evaluating the accuracy. This improvement shows the effectiveness of the two-stage learning process.