• The Korean Journal of Nuclear Medicine Technology
• /
• v.24 no.1
• /
• pp.15-19
• /
• 2020

Purpose Generative Adversarial Network(GAN) is one of deep learning technologies. This is a way to create a real fake image after learning the real image. In this study, after acquiring artificial intelligence images through GAN, We were compared and evaluated with real scan time images. We want to see if these technologies are potentially useful. Materials and Methods 30 patients who underwent ¹⁸F-FDG Brain PET/CT scanning at Severance Hospital, were acquired in 15-minute List mode and reconstructed into 1,2,3,4,5 and 15minute images, respectively. 25 out of 30 patients were used as learning images for learning of GAN and 5 patients used as verification images for confirming the learning model. The program was implemented using the Python and Tensorflow frameworks. After learning using the Pix2Pix model of GAN technology, this learning model generated artificial intelligence images. The artificial intelligence image generated in this way were evaluated as Mean Square Error(MSE), Peak Signal to Noise Ratio(PSNR), and Structural Similarity Index(SSIM) with real scan time image. Results The trained model was evaluated with the verification image. As a result, The 15-minute image created by the 5-minute image rather than 1-minute after the start of the scan showed a smaller MSE, and the PSNR and SSIM increased. Conclusion Through this study, it was confirmed that AI imaging technology is applicable. In the future, if these artificial intelligence imaging technologies are applied to nuclear medicine imaging, it will be possible to acquire images even with a short scan time, which can be expected to reduce artifacts caused by patient movement and increase the efficiency of the scanning room.

• Journal of Wetlands Research
• /
• v.21 no.1
• /
• pp.84-94
• /
• 2019

The Seocheon and Yubu Island mudflats in Geum Estuary are important stopover sites for migratory birds as energy supplementation area in the East Asia-Australasian Flyway. Benthic invertebrates in the tidal flats are important food resources for the migratory birds. In other words, benthic invertebrates in the tidal flats play an important ecological role in energy flow. This study was conducted to investigate the relationship between benthic invertebrate assemblages and environmental factors in Seocheon and Yubudo tidal flats in the Geum Estuary. As a result of the benthic invertebrate assemblage during the fall migration season, the total species number was 147, density and biomass were $1,772{\pm}1,342individuals/m^2$ and $445.1{\pm}807.6g/m^2$, respectively. Based on the appearance species and the density data, the result of analysis of mutual similarity among sampling sites was divided into two groups. Group A was the Macrophthalmus-Heteromastus community and Group B was the Spio-Urothoe-Mandibulophoxus community. Group B showed higher mean species number, density and biomass than Group A. The BIO-ENV analysis showed that the benthic invertebrate assemblages were most affected by the combination of sand content % and sediment sorting (${\rho}=0.500$). The variables of significant relationship with species number and biomass were sediment sorting (p=0.015) and the pore water DO(Dissolved Oxygen, p=0.003) in sediment, respectively.

• Journal of Life Science
• /
• v.28 no.12
• /
• pp.1477-1488
• /
• 2018

This study investigated the muscles, intestines, and gonads of Sulculus diversicolor supertexta to examine the diversity of microbial communities within examples collected from the Jeju Coast. Using different media, initial pure isolation in MA, 1% BHIA, and 1% TSA indicated that the muscles, intestines, and gonads supported more communities, respectively. In analysis of relative similarity with 16s rRNA sequencing, 190 pure colonies were isolated, and further analysis with NBLAST identified 71 species, 39 genera, 25 families, and five phyla. Homogeny with the reference strain was 91-100%. Microbial communities in S. supertexta consisted of gamma and alpha Proteobacteria (48%), Actinobacteria (32.5%), Firmicutes (16.9%), Deinococcus-Thermus (1.3%), and Bacteroides (1.3%). In all tissue, Psychrobacter cibarius in Moraxellaceae was dominant. Alteromonadaceae, Enterobacteriaceae, Pasturellaceae, Moraxellaceae, Rhodobacteraceae, Geminicoccaceae, Dietziaceae, Intrasporangiaceae, Microbacteriaceae, Micrococcaceae, Micromonosporaceae, Streptomycetaceae, Aerococcaceae, Bacillaceae, Paenibacillaceae, Planococcaceae, and Staphylcoccaceae were commonly isolated across all tissues, and Flavobacteriaceae, Corynebacteriaceae, Yesiniaceae, Vibrionaceae, Hahellaceae, Pseudomonadaceae were also identified from the intestines. In microbial monitoring of four harmful bacteria, Streptomyces albus (96%) showed antibacterial activity against all four strains, and Agrococcus baldri (99%) and Psychrobacter nivimaris (99%) presented against E. Coli and E. aerogens. In addition, some strains with low homogeny were isolated and further experiments are therefore required, for example to refine the antimicrobial substances including new strain investigations. These additional experiments would aim to establish generic resources for the microbial communities in S. Supertexta and provide basic data for applied microbiological research.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.1-11
• /
• 2021

The purpose of this study was to analyze the trends and characteristics of 'stress urinary incontinence' research through word frequency analysis, and their relationships were modeled using word embedding. Abstract data of 9,868 papers containing abstracts in PubMed's MEDLINE were extracted using a Python program. Then, through frequency analysis, 10 keywords were selected according to the high frequency. The similarity of words related to keywords was analyzed by Word2Vec machine learning algorithm. The locations and distances of words were visualized using the t-SNE technique, and the groups were classified and analyzed. The number of studies related to stress urinary incontinence has increased rapidly since the 1980s. The keywords used most frequently in the abstract of the paper were 'woman', 'urethra', and 'surgery'. Through Word2Vec modeling, words such as 'female', 'urge', and 'symptom' were among the words that showed the highest relevance to the keywords in the study on stress urinary incontinence. In addition, through the t-SNE technique, keywords and related words could be classified into three groups focusing on symptoms, anatomical characteristics, and surgical interventions of stress urinary incontinence. This study is the first to examine trends in stress urinary incontinence-related studies using the keyword frequency analysis and word embedding of the abstract. The results of this study can be used as a basis for future researchers to select the subject and direction of the research field related to stress urinary incontinence.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.2
• /
• pp.305-318
• /
• 2023

The complexity of software products led many manufacturers to stitch open-source software for composing a product. Using open-source help reduce the development cost, but the difference in the different development life cycles makes it difficult to keep the product up-to-date. For this reason, even the patches for known vulnerabilities are not adopted quickly enough, leaving the entire product under threat. Existing studies propose to use binary differentiation techniques to determine if a product is left vulnerable against a particular vulnerability. Despite their effectiveness in finding real-world vulnerabilities, they often fail to locate the evidence of a vulnerability if it is a small function that usually is inlined at compile time. This work presents our tool FunRank which is designed to identify the short functions. Our experiments using synthesized and real-world software products show that FunRank can identify the short, inlined functions that suggest that the program is left vulnerable to a particular vulnerability.

• Progress in Medical Physics
• /
• v.33 no.4
• /
• pp.150-157
• /
• 2022

Purpose: Elekta synergy^® was commissioned in the Seoul National University Veterinary Medical Teaching Hospital. Recently, Chung-Ang University Gwang Myeong Hospital commissioned Elekta Versa HD^TM. The beam characteristics of both machines are similar because of the same Agility^TM MLC Model. We compared measured beam data calculated using the Elekta treatment planning system, Monaco^®, for each institute. Methods: Beam of the commissioning Elekta linear accelerator were measured in two independent institutes. After installing the beam model based on the measured beam data into the Monaco^®, Monte Carlo (MC) simulation data were generated, mimicking the beam data in a virtual water phantom. Measured beam data were compared with the calculated data, and their similarity was quantitatively evaluated by the gamma analysis. Results: We compared the percent depth dose (PDD) and off-axis profiles of 6 MV photon and 6 MeV electron beams with MC calculation. With a 3%/3 mm gamma criterion, the photon PDD and profiles showed 100% gamma passing rates except for one inplane profile at 10 cm depth from VMTH. Gamma analysis of the measured photon beam off-axis profiles between the two institutes showed 100% agreement. The electron beams also indicated 100% agreement in PDD distributions. However, the gamma passing rates of the off-axis profiles were 91%-100% with a 3%/3 mm gamma criterion. Conclusions: The beam and their comparison with MC calculation for each institute showed good performance. Although the measuring tools were orthogonal, no significant difference was found.

• Korean Journal of Radiology
• /
• v.24 no.4
• /
• pp.294-304
• /
• 2023

Objective: We aimed to investigate whether image standardization using deep learning-based computed tomography (CT) image conversion would improve the performance of deep learning-based automated hepatic segmentation across various reconstruction methods. Materials and Methods: We collected contrast-enhanced dual-energy CT of the abdomen that was obtained using various reconstruction methods, including filtered back projection, iterative reconstruction, optimum contrast, and monoenergetic images with 40, 60, and 80 keV. A deep learning based image conversion algorithm was developed to standardize the CT images using 142 CT examinations (128 for training and 14 for tuning). A separate set of 43 CT examinations from 42 patients (mean age, 10.1 years) was used as the test data. A commercial software program (MEDIP PRO v2.0.0.0, MEDICALIP Co. Ltd.) based on 2D U-NET was used to create liver segmentation masks with liver volume. The original 80 keV images were used as the ground truth. We used the paired t-test to compare the segmentation performance in the Dice similarity coefficient (DSC) and difference ratio of the liver volume relative to the ground truth volume before and after image standardization. The concordance correlation coefficient (CCC) was used to assess the agreement between the segmented liver volume and ground-truth volume. Results: The original CT images showed variable and poor segmentation performances. The standardized images achieved significantly higher DSCs for liver segmentation than the original images (DSC [original, 5.40%-91.27%] vs. [standardized, 93.16%-96.74%], all P < 0.001). The difference ratio of liver volume also decreased significantly after image conversion (original, 9.84%-91.37% vs. standardized, 1.99%-4.41%). In all protocols, CCCs improved after image conversion (original, -0.006-0.964 vs. standardized, 0.990-0.998). Conclusion: Deep learning-based CT image standardization can improve the performance of automated hepatic segmentation using CT images reconstructed using various methods. Deep learning-based CT image conversion may have the potential to improve the generalizability of the segmentation network.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.4
• /
• pp.35-50
• /
• 2023

As urbanization progresses, there is a growing and continuous demand for green spaces that provide ecosystem services. However, increasing the quantity of green spaces within major cities is challenging. Therefore, it is essential to pursue qualitative improvements that consider ecological characteristics of existing green spaces. In this study, we focus on local neighborhood parks in Seoul and present the following two questions through an evaluation utilizing ecological design indicators and land use data: 1. Which factor, design or location, has a greater influence on the ecological quality of neighborhood parks in Seoul? 2. Additionally, when evaluating ecological characteristics, is there similarity between assessments based on land-use data and those utilizing ecological design indicators? For this study, we conducted research on 30 neighborhood parks in Seoul and classified them into mountainous types (adjacent to mountains, natural terrain parks) and urban types (independently designed within 300m without existing forests) based on previous studies. Firstly, we conducted evaluations according to park location types. When comparing the evaluation scores of urban types (14 parks) and mountainous types (16 parks), significant differences were observed with scores of 16.86 and 35.94, respectively. Statistical analysis showed a significant difference between park types. In terms of habitat quality, the average values for urban and mountainous parks were 0.33 and 0.53, respectively, and statistically significant differences were observed between park types indicating differences in ecological potential according to park location. Secondly, when comparing the results of ecological potential evaluations based on park design and external connectivity, a correlation was found between habitat quality and total scores according to evaluation indicators. The correlation analysis showed significant linear relationships between habitat quality and total scores, biodiversity scores, and ecosystem function scores, with high positive correlation coefficients of 0.829, 0.861, and 0.802, respectively. This study holds significance in analyzing the ecological aspects of urban parks through the lens of both park location characteristics and design indicators. The analysis results underscore the importance of planning and managing ecologically sound urban parks contingent upon their location. Moreover, the utilization of appropriate ecological design indicators can help alleviate environmental limitations surrounding parks. Integrating these considerations could enhance the ecological quality and ecosystem services of urban green spaces.

• Korean Chemical Engineering Research
• /
• v.47 no.2
• /
• pp.220-229
• /
• 2009

Strain improvement and morphology investigation in bioreactor cultures were undertaken in suspended cultures of Phellinus linteus mycelia for mass production of protein-bound polysaccharides(soluble ${\beta}$-D-glucan), a powerful immuno-stimulating agent. Phellineus sp. screened for this research was identified as Phellinus linteues through ITS rDNA sequencing method and blast search, demonstrating 99.7% similarity to other Phellinus linteus strains. Intensive strain improvement program was carried out by obtaining large amounts of protoplasts for the isolation of single cell colonies. Rapid and large screening of high-yielding producers was possible because large numbers of protoplasts ($1{\times}10^5{\sim}10^6\;protoplasts/ml$) formed using the banding filtration method with the cell wall-disrupting enzymes could be regenerated in relatively high regeneration frequency($10^{-2}{\sim}10^{-3}$) in the newly developed regeneration medium. It was demonstrated that the strains showing high performances in the protoplast regeneration and solid growth medium were able to produce 5.8~6.4%(w/w) of ${\beta}$-D-glucan and 13~15 g/L of biomass in stable manners in suspended shake-flask cultures of P. linteus mycelia. In addition, cell mass increase was observed to be the most important in order to enhance ${\beta}$-D-glucan productivity during the course of strain improvement program, since the amount of ${\beta}$-D-glucan extracted from the cell wall of P. linteus mycelia was almost constant on the unit biomass basis. Therefore we fully investigated the fungal cell morphology, generally known as one of the key factors affecting cell growth extent in the bioreactor cultures of mycelial fungal cells. It was found that, in order to obtain as high cell mass as possible in the final production bioreactor cultures, the producing cells should be proliferated in condensed filamentous forms in the growth cultures, and optimum amounts of these filamentous cells should be transferred as active inoculums to the production bioreactor. In this case, ideal morphologies consisting of compacted pellets less than 0.5mm in diameter were successfully induced in the production cultures, resulting in shorter period of lag phase, 1.5 fold higher specific cell growth rate and 3.3 fold increase in the final biomass production as compared to the parallel bioreactor cultures of different morphological forms. It was concluded that not only the high-yielding but also the good morphological characteristics led to the significantly higher biomass production and ${\beta}$-D-glucan productivity in the final production cultures.

• Journal of the HCI Society of Korea
• /
• v.8 no.1
• /
• pp.1-9
• /
• 2013

This is to develop a new way of testing self-esteem by adopting DAP(Draw a Person) test and to make a platform to digitalize it for young people in the adolescent stage. This approach is to get high effectiveness of the self-esteem measurement using DAP test, including some personal inner situations which can be easily missed in the large statistical analysis. The other objective of this study is digitalize to recover limits of DAP test in the subjective rating standard. It is based on the distribution of the figure drawing expressed numerically by the anxiety index of Handler. For these two examinations, we made experiment through 4 stages with second grade middle school 73 students from July 30th to October 31th in 2009 during 4 months. Firstly, we executed 'Self Values Test' for all 73 people, and divided them into two groups; one is high self-esteem group of 36 people, the other is low self-esteem group of 37 people. Secondly, we regrouped them following D (Depression), Pd (Psychopathic Deviate), Sc (Schizophrenia) scales of MMPI; one is high self-esteem group of 7 people, the other is low self-esteem group of 13 people. Thirdly, we conducted DAP test separately for these 20 people. We intended to verify necessity and appropriateness of direction of 'Digitalizing Measurement System' by comparing and analyzing relation between DAP and Self-esteem following evaluation criteria which has similarity in 3 tests, after executing DAP to reflect peculiarity of adolescents sufficiently. We compared and analyzed result abstracted by sampling DAP test of two groups; One is high self-esteem group of 2 people, the other is low self-esteem group of 2 people; to confirm whether we can improve limitation that original psychological testing has by comparing mutual reliance of measurement test. Finally, with DAP test gained from correlations between self-esteem and melancholia following as above-mentioned steps, we discovered possibility of realization to get a concrete and individual criteria of evaluation based on Expert System as a way of enhancing accessibility in quantitative manner. 'Digitalizing Measurement Program' of DAP test suggested in this study promote results' reliability based on existing tests and measurement.