• Journal of Biomedical Engineering Research
• /
• v.43 no.3
• /
• pp.153-160
• /
• 2022

As new types of medical devices are emerging through convergence with advanced technology, innovative technologies are becoming hot issues in health policy because of their disruptiveness. This study analyzed the innovative medical device management systems in the US, China and Korea. Innovative medical devices have been defined differently depending on the country's management system, but in common, they are defined as products that do not exist or have dramatically improved performance compare to existing products by applying innovative technologies. Innovative medical devices have been supported by regulatory authorities during product development and approval processes. While the US and China have more than 300 products designated as innovative medical devices with diverse functions, application fields, and manufacturing countries considering the initial situation of the implementation for the system, Korea has only 16 products, mainly radiology and diagnostic devices and made in Korea only as innovative medical device. In addition, Korea shows the highest market approval rate of innovative medical devices compare to the US and China, and it is necessary to prepare the approval process in consideration of product diversity.

• Genomics & Informatics
• /
• v.19 no.3
• /
• pp.34.1-34.6
• /
• 2021

Digital PCR (dPCR) is the third-generation PCR that enables real-time absolute quantification without reference materials. Recently, global diagnosis companies have developed new dPCR equipment. In line with the development, the Lab On An Array (LOAA) dPCR analyzer (Optolane) was launched last year. The LOAA dPCR is a semiconductor chip-based separation PCR type equipment. The LOAA dPCR includes Micro Electro Mechanical System that can be injected by partitioning the target gene into 56 to 20,000 wells. The amount of target gene per wells is digitized to 0 or 1 as the number of well gradually increases to 20,000 wells because its principle follows Poisson distribution, which allows the LOAA dPCR to perform precise absolute quantification. LOAA determined region of interest first prior to dPCR operation. To exclude invalid wells for the quantification, the LOAA dPCR has applied various filtering methods using brightness, slope, baseline, and noise filters. As the coronavirus disease 2019 has now spread around the world, needs for diagnostic equipment of point of care testing (POCT) are increasing. The LOAA dPCR is expected to be suitable for POCT diagnosis due to its compact size and high accuracy. Here, we describe the quantitative principle of the LOAA dPCR and suggest that it can be applied to various fields.

• Korean Journal of Audiology
• /
• v.25 no.1
• /
• pp.1-7
• /
• 2021

The scope of teleaudiology has been noted with telehealth due to Coronavirus disease (COVID-19) recently. As the notion has been around us for more than 20 years ever since 1999, it is necessary to perceive the knowledge accurately and prepare for the successful implementation of it. Therefore, the literature review including screening and diagnostic audiometry, cochlear implants and hearing aids, and aural rehabilitation, telecommunications technology regarding several fields of teleaudiology, and considerations for practicing were identified. Although overall internet-based audiological services showed benefits in terms of outcome and accessibility, uncertainties of cost-effectiveness, the optimal level of support, and a need for further studies of many aspects for teleaudiology has arisen. In the view of technology, the store-and-forward (asynchronous/hybrid) and a real-time (synchronous) methods were introduced with one applied and nine registered patents recorded from 2004 to 2020 for the invention of teleaudiology in the United States. Also, 10 checklists were suggested for planning teleaudiology practice from prior experience in hosting the teleaudiology program. Conclusively, it is hoped that this review sheds light on recognizing and improving the existing teleaudiology services and helps overcome the challenges faced in the era of pandemic and untact world to come.

• Journal of Audiology & Otology
• /
• v.25 no.1
• /
• pp.1-7
• /
• 2021

The scope of teleaudiology has been noted with telehealth due to Coronavirus disease (COVID-19) recently. As the notion has been around us for more than 20 years ever since 1999, it is necessary to perceive the knowledge accurately and prepare for the successful implementation of it. Therefore, the literature review including screening and diagnostic audiometry, cochlear implants and hearing aids, and aural rehabilitation, telecommunications technology regarding several fields of teleaudiology, and considerations for practicing were identified. Although overall internet-based audiological services showed benefits in terms of outcome and accessibility, uncertainties of cost-effectiveness, the optimal level of support, and a need for further studies of many aspects for teleaudiology has arisen. In the view of technology, the store-and-forward (asynchronous/hybrid) and a real-time (synchronous) methods were introduced with one applied and nine registered patents recorded from 2004 to 2020 for the invention of teleaudiology in the United States. Also, 10 checklists were suggested for planning teleaudiology practice from prior experience in hosting the teleaudiology program. Conclusively, it is hoped that this review sheds light on recognizing and improving the existing teleaudiology services and helps overcome the challenges faced in the era of pandemic and untact world to come.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.2
• /
• pp.323-328
• /
• 2021

Diagnostic models are required. Data augmentation is one of the best ways to improve deep learning performance. Traditional augmentation techniques that modify image brightness or spatial information are difficult to achieve great results. To overcome this, a generative adversarial network (GAN) technology that generates virtual data to increase deep learning performance has emerged. GAN can create realistic-looking fake images by competitive learning two networks, a generator that creates fakes and a discriminator that determines whether images are real or fake made by the generator. GAN is being used in computer vision, IT solutions, and medical imaging fields. It is essential to secure additional learning data to advance deep learning-based fault diagnosis solutions in the power industry where facilities are strictly maintained more than other industries. In this paper, we propose a method for generating power facility images using GAN and a strategy for improving performance when only used a small amount of data. Finally, we analyze the performance of the augmented image to see if it could be utilized for the deep learning-based diagnosis system or not.

• Journal of Biomedical Engineering Research
• /
• v.43 no.4
• /
• pp.259-270
• /
• 2022

Artificial intelligence (AI) has been studied in various fields of medical imaging. Currently, top-notch deep learning (DL) techniques have led to high diagnostic accuracy and fast computation. However, they are rarely used in real clinical practices because of a lack of reliability concerning their results. Most DL models can achieve high performance by extracting features from large volumes of data. However, increasing model complexity and nonlinearity turn such models into black boxes that are seldom accessible, interpretable, and transparent. As a result, scientific interest in the field of explainable artificial intelligence (XAI) is gradually emerging. This study aims to review diverse XAI approaches currently exploited in medical imaging. We identify the concepts of the methods, introduce studies applying them to imaging modalities such as computational tomography (CT), magnetic resonance imaging (MRI), and endoscopy, and lastly discuss limitations and challenges faced by XAI for future studies.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.265-272
• /
• 2022

As the risk of lung cancer has increased, early-stage detection and treatment of cancers have received a lot of attention. Among various medical imaging approaches, computer tomography (CT) has been widely utilized to examine the size and growth rate of lung nodules. However, the process of manual examination is a time-consuming task, and it causes physical and mental fatigue for medical professionals. Recently, many computer-aided diagnostic methods have been proposed to reduce the workload of medical professionals. In recent studies, encoder-decoder architectures have shown reliable performances in medical image segmentation, and it is adopted to predict lesion candidates. However, localizing nodules in lung CT images is a challenging problem due to the extremely small sizes and unstructured shapes of nodules. To solve these problems, we utilize atrous spatial pyramid pooling (ASPP) to minimize the loss of information for a general U-Net baseline model to extract rich representations from various receptive fields. Moreover, we propose mixed-up attention mechanism of reverse, boundary and convolutional block attention module (CBAM) to improve the accuracy of segmentation small scale of various shapes. The performance of the proposed model is compared with several previous attention mechanisms on the LIDC-IDRI dataset, and experimental results demonstrate that reverse, boundary, and CBAM (RB-CBAM) are effective in the segmentation of small nodules.

• Nuclear Engineering and Technology
• /
• v.55 no.1
• /
• pp.100-108
• /
• 2023

In this study, a neural network model inspired by a one-dimensional convolution U-net is developed to automatically accelerate edge localized mode (ELM) detection from big diagnostic data of fusion devices and increase the detection accuracy regardless of the hyperparameter setting. This model recognizes the input signal patterns and overcomes the problems of existing detection algorithms, such as the prominence algorithm and those of differential methods with high sensitivity for the threshold and signal intensity. To train the model, 10 sets of discharge radiation data from the KSTAR are used and sliced into 11091 inputs of length 12 ms, of which 20% are used for validation. According to the receiver operating characteristic curves, our model shows a positive prediction rate and a true prediction rate of approximately 90% each, which is comparable to the best detection performance afforded by other algorithms using their optimized hyperparameters. The accurate and automatic ELM-burst detection methodology used in our model can be beneficial for determining plasma properties, such as the ELM frequency from big data measured in multiple experiments using machines from the KSTAR device and ITER. Additionally, it is applicable to feature detection in the time-series data of other engineering fields.

• The Journal of Fisheries Business Administration
• /
• v.53 no.4
• /
• pp.27-49
• /
• 2022

This study focused on diagnosing and analyzing the level of sustainable development for each fishing communities by applying the sustainable development index in the fishing communities to support the policy of revitalizing the fishing communities. In terms of methodology, diagnostic indicators for rural areas were used through previous studies and literature surveys, and three categories, five fields and 27 indicators were finally selected through collecting opinions from experts. After deriving the weight for each indicator in detail, the final sustainable development index of the fishing communities was applied to fishing village fraternity. Based on the results of the analysis of the application of sustainable development cases in fishing communities, policy support should be implemented differentially according to regional decline factors and potential growth factors. In the population and social sector, it is necessary to consider ways to reduce population and reduce aging. In the industrial and economic sectors, fishing activation and systematic support for fishing-related industries should be provided. In the marine and built environment sector, the government's active project execution and budget support are required. In addition, it is expected to be used in various ways in the process of developing fishing communities and establishing revitalization plans that reflect the characteristics of the region.

• Progress in Medical Physics
• /
• v.21 no.2
• /
• pp.232-237
• /
• 2010

The shielding materials designed for replacement of lead equivalent materials for lighter apron than that of lead in diagnostic photon beams. The absorption characteristics of elements were applied to investigate the lead free material for design the shielding materials through the 50 kVp to 110 kVp x-ray energy in interval of 20 kVp respectively. The idea focused to the effect of K-edge absorption of variable elements excluding the lead material for weight reduction. The designed shielding materials composited of Tin 34.1%, Antimon 33.8% and Iodine 26.8% and Polyisoprene 5.3% gram weight account for 84 percent of weight of lead equivalent of 0.5 mm thickness. The size of lead-free shielder was $200{\times}200{\times}1.5\;mm^3$ and $3.2\;g/cm^3$ of density which is equivalent to 0.42 mm of Pb. The lead equivalent of 0.5 mm thickness generally used for shielding apron of diagnostic X rays which is transmitted 0.1% for 50 kVp, 0.9% for 70 kVp and 3.2% for 90 kVp and 4.8% for 110 kVp in experimental measurements. The experiment of transmittance for lead-free shielder has showed 0.3% for 50 kVp, 0.6% for 70 kVp, 2.0% for 90 kVp and 4.2% for 110 kVp within ${\pm}0.1%$. respectively. Using the attenuation coefficient of experiments for 0.5 mm Pb equivalent of lead-free materials showed 0.1%. 0.3%, 1.0% and 2.4%, respectively. Furthermore, the transmittance of lead-free shielder for scatter rays has showed the 2.4% in operation energy of 50 kVp and 5.9% in energy of 110 kVp against 2.4% and 5.1% for standard lead thickness within ${\pm}0.2%$ discrepancy, respectively. In this experiment shows the designed lead-free shielder is very effective for reduction the apron weight in diagnostic radiation fields.