• Journal of Cardiovascular Imaging
• /
• v.31 no.1
• /
• pp.41-48
• /
• 2023

BACKGROUND: The function of left atrium (LA) is difficult to assess because of its ventricle-dependent, dynamic movement. The aim of this study was to assess LA function using velocity vector imaging (VVI) and compare LA function in patients with hypertrophic cardiomyopathy (HCMP) and left ventricular hypertrophy (LVH) with normal controls. METHODS: Fourteen patients with HCMP (72% male, mean age of 52.6 ± 9.8), 15 hypertensive patients with LVH (88% male, mean age of 54.0 ± 15.3), and 10 age-matched controls (83% male, mean age of 50.0 ± 4.6) were prospectively studied. Echocardiographic images of the LA were analyzed with VVI, and strain rate (SR) was compared among the 3 groups. RESULTS: The e' velocity (7.7 ± 1.1; 5.1 ± 0.8; 4.5 ± 1.3 cm/sec, p = 0.013), E/e' (6.8 ± 1.6; 12.4 ± 3.3; 14.7 ± 4.2, p = 0.035), and late diastolic SR at mid LA (-1.65 ± 0.51; -0.97 ± 0.55; -0.82 ± 0.32, p = 0.002) were significantly different among the groups (normal; LVH; HCMP, respectively). The e' velocity, E/e', and late diastolic SR at mid LA were significantly different between normal and LVH (p = 0.001; 0.022; 0.018), whereas LA size was similar between normal and LVH (p = 0.592). The mean late diastolic peak SR of mid LA was significantly correlated with indices of diastolic function (E/e', e', and LA size). CONCLUSIONS: The SR is a useful tool for detailed evaluation of LA function, especially early dysfunction of LA in groups with normal LA size.

• Advanced Industrial SCIence
• /
• v.3 no.1
• /
• pp.17-22
• /
• 2024

History, which began with the emergence of mankind, has a means of recording. Today, we can check the past through data. Generated data may only be generated and stored at a certain moment, but it is not only continuously generated over a certain time interval from the past to the present, but also occurs in the future, so making predictions using it is an important task. In order to find out trends in the use of time series data among numerous data, this paper analyzes the concept of time series data, analyzes Recurrent Neural Network and Long-Short Term Memory, which are mainly used for time series data analysis in the machine learning field, and analyzes the use of these models. Through case studies, it was confirmed that it is being used in various fields such as medical diagnosis, stock price analysis, and climate prediction, and is showing high predictive results. Based on this, we will explore ways to utilize it in the future.

• Journal of Internet Computing and Services
• /
• v.25 no.3
• /
• pp.19-25
• /
• 2024

The worldwide aging population trend is causing an increase in the incidence of major retinal diseases that can lead to blindness, including glaucoma, cataract, and macular degeneration. In the field of ophthalmology, there is a focused interest in diagnosing diseases that are difficult to prevent in order to reduce the rate of blindness. This study proposes a deep learning approach to accurately diagnose ocular diseases in fundus photographs using less data than traditional methods. For this, Convolutional Neural Network (CNN) models capable of effective learning with limited data were selected to classify Conventional Fundus Images (CFI) from various ocular disease patients. The chosen CNN models demonstrated exceptional performance, achieving high Accuracy, Precision, Recall, and F1-score values. This approach reduces manual analysis by ophthalmologists, shortens consultation times, and provides consistent diagnostic results, making it an efficient and accurate diagnostic tool in the medical field.

• Korean Journal of Veterinary Research
• /
• v.38 no.4
• /
• pp.898-908
• /
• 1998

The aim of this experiments were to assess the time-interval change of motional characteristics in frozen-thawed semen of Korean native cattle (KNC) by using computer aided semen analysis (CASA) technology. Twenty-six KNC frozen semen straws were obtained from Korean KNC improvement department, livestock improvement main division, national livestock cooperatives federation in Korea. Specimens were allowed to thaw at $37^{\circ}C$ for 30 sec in water bath. Semen analysis was performed on semen image analysis system (SIAS, Medical supply, Korea) adjusted to the gate settings and used the semen droplet ($5{\mu}l$) placed on Makler counting chamber (Sefi medical instrument, Israel) prewarmed at $37^{\circ}C$. The same person used the same micropipette to fill the Makler counting chamber. A total of 150 or more of sperms were analysed in each specimen by a single trained person by scanning at least 5 to 10 fields. The measurement parameters in SIAS were as follows ; frame rate = 30 frames per sec, image capture = 1 sec, minimum motile speed = $10{\mu}m/s$, maximum countable sperm number = 400. Statistical analysis was done by Student t-test with use of the Sigma plot program on a IBM personal computer. The dancemean(DNM) and hyperactivated sperm(HYP) of frozen-thawed KNC semen kinematics were significantly decreased(p < 0.05) after 10 min of incubation at $37^{\circ}C$ water bath. But, wobble(WOB) of same sample semen was significantly increased(p < 0.05) after 10 min of incubation and significantly decrease(p < 0.05) after 60 min of same incubation. And, after 30 mim of incubation, significantly differences were found most of motion kinematics, motifity(MOT), curvilinear velocity(VCL), straight line velocity(VSL), average path velocity(VAP), amplitude of lateral head displacement(ALH), beat cross frequency(BCF), mean angular displacement(MAD), dance(DNC), on same sample semen. The DNM of KNC semen sample was variable kinematics after 30 min of incubation. Also, the linearity(LIN) and straightness(STR) was significantly decreased(p < 0.05) from 60 min of incubation. In conclusion, the AI within 30 min after thawing of frozen semen can be an effective method for obtaining high fertility rate in KNC reproductive program.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.1
• /
• pp.225-229
• /
• 2012

Background: Males have a higher prevalence of hepatocellular carcinoma (HCC) than females in general, but the reasons for the sex disparity are still obscure. DNA copy number alteration (CNA) is a major feature of solid tumors including HCC, but whether CNA plays a role in sex-related differences in HCC development has never been evaluated. Methods: High-resolution array comparative genomic hybridization (CGH) was used to examine 17 female and 46 male HCC patients with chronic hepatitis B virus (HBV) infection in Shanghai, China. Two-tailed Fisher's exact or ${\chi}^2$ tests was used to compare CNAs between females and males. Results: The overall frequencies and patterns of CNAs in female and male cases were similar. However, female HCC tumors presented more copy number gains compared to those in males on 1q21.3-q22 (76.5% vs. 37.0%, P = 0.009), 11q11 (35.3% vs. 0.0%, P = 0.0002) and 19q13.31-q13.32 (23.5% vs. 0.0%, P = 0.004), and loss on 16p11.2 (35.3% vs. 6.5%, P = 0.009). Relative to females, male cases had greater copy number loss on 11q11 (63.0% vs. 17.6%, P = 0.002). Further analyses showed that 11q11 gain correlated with 19q13.31-q13.32 gain (P = 0.042), 11q11 loss (P = 0.011) and 16p11.2 loss (P = 0.033), while 1q21.3-q22 gain correlated with 19q13.31-q13.32 gain (P = 0.046). Conclusions: These findings suggest that CNAs may play a role in sex-related differences in HBVassociated HCC development.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.8
• /
• pp.3581-3586
• /
• 2014

Aim: To investigate the effects of tetramethypyrazine (TMP) on proliferation and apoptosis of the human gastric carcinoma cell line 7901 and its possible mechanism of action. Methods: The viability of TMP-treated 7901 cells was measured with a 3-(4, 5-dimethyl-thiazol-2-yl)-2,5-diphenyltetrazolium bromide assay (MTT) and cell apoptosis was analyzed by flow cytometry. The distribution of cells in different phases of cell cycle after exposure of TMPs was analyzed with flow cytometry. To investigate the molecular mechanisms of TMP-mediated apoptosis, the expression of NF-${\kappa}Bp65$, cyclinD1 and p16 in SGC-7901 cells was analyzed by reverse transcription-polymerase chain reaction (RT-PCR) and western blotting. Results: TMP inhibited the proliferation of human gastric carcinoma cell line 7901 in dose and time dependent manners. Cell growth was suppressed by TMP at different concentrations (0.25, 0.5, 1.0, 2.0 mg/ml), the inhibition rate is 0.46%, 4.36%, 14.8%, 76.1% (48h) and 15.5%, 18.5%, 41.2%, 89.8% (72h) respectively. When the concentration of TMPs was 2.0mg/ml, G1-phase arrest in the SGC-7901 cells was significant based on the data for cell cycle distribution. RT-PCR demonstrated that NF-${\kappa}Bp65$ and cyclin D1 mRNA expression was significantly down-regulated in 7901 cells treated with 2.0 mg/ml TMP for 72h (p<0.05), while the p16 mRNA level was up-regulated (p<0.05). The protein expression of NF-${\kappa}Bp65$ and cyclin D1 decreased gradually with the increase in TMP concentration, compared with control cells (p<0.05), while expression of protein p16 was up-regulated (p<0.01). Conclusion: TMP exhibits significant anti-proliferative and pro-apoptotic effects on the human gastric carcinoma cell line SGC-7901. NF-${\kappa}Bp65$, cyclinD1 and p16 may also play important roles in the regulation mechanisms.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.23 no.3
• /
• pp.685-694
• /
• 2009

This experimental study was designed to investigate the inhibitory effects of ethanol extract of modified Yukgunja-tang(mYGJT) on high-fat diet-induced obesity and hyperlipidemia in Sprague-Dawley rats, Animals were divided into normal, control, mYGJT(100 mg/kg and 200 mg/kg) treated groups. Obesity with hyperlipidemia was induced by high fat diet treatment for 6 weeks. mYGJT was given to the amimals by oral gavage for 4 weeks, starting at the high-fat diet regimen, The effect of mYGJT on the differentiation of 3T3 L1 adipocytes in vitro and serological paramamters for obesity and hyperlipidemia in vivo were evaluated, mYGJT significnatly inhibited the differentiation of 3T3 L1 adipocytes in a concentration dependent manner. mYGJT treatment siginficantly reduced body weight, abdominal and epididymal fat weight, and FER(Food Efficiency Ratio) compared with control group in a dose dependent manner. It also signficantly inhibited the levels of serum total lipid, triglyceride, phospholipid, total cholesterol, LDL, AI(Atherosclerosis Index) and returned the serum HDL to normal. Total lipids, triglycerides and cholesterols in the liver, as well as malondialdehyde(MDA) and hydroxy radical in the serum were significantly reduced. However, superoxide dismutase(SOD) activity was significantly increased in mYGJT treated group compared with control group. Finally, mYGJT treatment signficantly decreased the MDA and protein carbonyl concentrations of the hepatic homogenate but signficantly increased the activities of SOD, GSH-Px and Catalase. Taken together, these results suggest that mYGJT can be clinically useful in inhibiting high-fat diet-induced obesity and hyperlipidemia.

• Journal of Digital Convergence
• /
• v.17 no.8
• /
• pp.249-255
• /
• 2019

Type 2 diabetes mellitus(T2DM) is included in metabolic disorders characterized by hyperglycemia, which causes many complications, and requires long-term treatment resulting in massive medical expenses each year. There have been many studies to solve this problem, but the existing studies have not been accurate by learning and predicting the data at specific time point. Thus, this study proposed a model using RNN to increase the accuracy of prediction of T2DM. This work propose a T2DM prediction model based on Korean Genome and Epidemiology study(Ansan, Anseong Korea). We trained all of the data over time to create prediction model of diabetes. To verify the results of the prediction model, we compared the accuracy with the existing machine learning methods, LR, k-NN, and SVM. Proposed prediction model accuracy was 0.92 and the AUC was 0.92, which were higher than the other. Therefore predicting the onset of T2DM by using the proposed diabetes prediction model in this study, it could lead to healthier lifestyle and hyperglycemic control resulting in lower risk of diabetes by alerted diabetes occurrence.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.21-31
• /
• 2021

As the COVID-19 pandemic rapidly changes healthcare around the globe, the need for smart healthcare that allows for remote diagnosis is increasing. The current classification of respiratory diseases cost high and requires a face-to-face visit with a skilled medical professional, thus the pandemic significantly hinders monitoring and early diagnosis. Therefore, the ability to accurately classify and diagnose respiratory sound using deep learning-based AI models is essential to modern medicine as a remote alternative to the current stethoscope. In this study, we propose a deep learning-based respiratory sound classification model using data collected from medical experts. The sound data were preprocessed with BandPassFilter, and the relevant respiratory audio features were extracted with Log-Mel Spectrogram and Mel Frequency Cepstral Coefficient (MFCC). Subsequently, a Parallel CNN network model was trained on these two inputs using stacking ensemble techniques combined with various machine learning classifiers to efficiently classify and detect abnormal respiratory sounds with high accuracy. The model proposed in this paper classified abnormal respiratory sounds with an accuracy of 96.9%, which is approximately 6.1% higher than the classification accuracy of baseline model.

• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.1-6
• /
• 2022

Deep learning is a collection of algorithms that enable learning by summarizing the key contents of large amounts of data; it is being developed to diagnose lesions in the medical imaging field. To evaluate the accuracy of the cerebral hemorrhage diagnosis, we used a convolutional neural network (CNN) to derive the diagnostic accuracy of cerebral parenchyma computed tomography (CT) images and the cerebral parenchyma CT images of areas where cerebral hemorrhages are suspected of having occurred. We compared the accuracy of CNN with different numbers of hidden layers and discovered that CNN with more hidden layers resulted in higher accuracy. The analysis results of the derived CT images used in this study to determine the presence of cerebral hemorrhages are expected to be used as foundation data in studies related to the application of artificial intelligence in the medical imaging industry.