• Asian-Australasian Journal of Animal Sciences
• /
• v.18 no.7
• /
• pp.949-956
• /
• 2005

The weekly ultrasound scanner (US) observations of reproductive organs in a commercial dairy herd with the popular stanchion style management were conducted for over 26 months. Based on reproductive records, the following were evaluated: 1) the effect of postpartum period commencement of US monitoring on herd reproductive efficacy, and 2) the effectiveness of a US monitoring-based diagnosis and subsequent treatments of reproductive disorders on postpartum reproductive efficiency. The reproductive parameters of cows, which were subjected to US monitoring between Days 30-40 (Day 0 = day of parturition), Days 41-50, Days 51-60, and above Day 61, were compared. The reproductive parameters of cows diagnosed as having reproductive disorders (RD) with US monitoring before or after the first artificial insemination (AI) were also compared. It was found that the day of commencement of US monitoring in cows diagnosed with and without RD significantly affected the period towards the first AI and the open period. In particular, cystic follicles and anoestrus detected either before or after the first AI significantly affected herd reproductive efficiency. The implementation of US monitoring improved reproductive efficiency by reducing the open period and increasing the number of milking cows in the herd. The results of this field trial indicate that the postpartum reproductive management of dairy cows with the use of the US monitoring system is one strategy to improve reproductive efficiency, especially in a high-yielding dairy herd reared stanchion management style.

• Convergence Security Journal
• /
• v.22 no.5
• /
• pp.89-94
• /
• 2022

Efforts to improve the quality of university education, that is, advanced plans for innovative university education, are needed in the face of changes in educational demand due to rapid changes in new industries and society and the competition for survival due to a rapidly decreasing school-age population with the full-fledged start of the era of the 4th industrial revolution is being demanded. In particular, it is necessary to apply a system for student counseling and guidance management through college life adjustment diagnosis from students entering college to graduation. Accordingly, each university is promoting a project to upgrade a course-linked integrated platform based on core technologies of the 4th industrial revolution era, such as big data and artificial intelligence (AI). Therefore, in this study, based on the field of information security major, we intend to present a plan to advance the student management system for innovative university education.

• Korean Journal of Agricultural Science
• /
• v.37 no.3
• /
• pp.393-398
• /
• 2010

Early pregnancy diagnosis of bovine is an essential component for efficient reproductive plan in farms because long term of non-pregnancy results in economic losses by failure of offspring production and low milk yield in dairy cattle. The major steroid hormones related with reproduction are known to be progesterone and estrogen in bovine pregnancy. To evaluate detection level of hormones in milk, plasma and milk progestrone and estrogen of Holstein cows was analyzed during artificial insemination (AI) and embryo transfer (ET). Progesterone concentration at 21 days postestrus was significantly different in plasma and milk between pregnant and non-pregnant cows. Estrogen concentration at estrus was higher in pregnant recipients than that in non-pregnant recipients. To analyze correlation between hormone levels and conception rates in Holstein, the conception and return rates were checked following AI, and the returned cows were on the track of pregnancy after consecutive AI. Pregnant cows following first AI were considered as high conception group while pregnant cows following third AI were rated as low conception group. Proportion of high and low conception groups in this study was 78.2% and 9.1%, respectively. Hormone analysis indicated that high conception group had higher estrogen level during estrus than low conception group ($26.45{\pm}3.32$ vs $19.017{\pm}2.97$). Progesterone level was not different between high and low conception groups during estrus but increased significantly after 21 days postestrus (21 day: $4.95{\pm}1.12$ vs $0.95{\pm}0.23$, 35 day: $12.47{\pm}3.82$ vs $2.41{\pm}1.21$). In conclusion, the pattern of progesterone and estrogen secretion in Holstein milk samples could be a good candidate for early pregnancy detection and selection of recipients during ET.

• The Journal of Korean Medicine
• /
• v.35 no.3
• /
• pp.155-165
• /
• 2014

Objectives: The pulse diagnosis to identify the symptoms has been considered important in Korean medicine. The position and character of disease would be confirmed by pulse diagnosis of left and right radial artery. This paper is to analyze the characteristics and differences of left and right blood vessels. Methods: In this study, left and right radial artery and dorsalis pedis artery was measured and analyzed by using condenser typed pulse analyzer. Commercially available pulse analyzer was used to measure the radial artery. The pulse wave was measured in 20 laboratory healthy men and women. The blood vessel aging degree and index of augmentation of blood vessel was obtained from the measured pulse wave graph and the characteristics and differences of the left and right blood vessel was analyzed. Results: The significant difference of pulse transit time between the right handed and non-right handed was not found. The correlation of radial artery and dorsalis pedis artery had no significant difference. By obtaining the blood vessel aging index (AGI) and augmentation index (AI) of blood vessel at the left and right radial artery, the significant difference between right handed and non-right handed was not found. Conclusions: The result of this study would help to explain the characteristic of blood vessel with respect to the left and right handed. We suggest that research of pulse wave of the left and right blood vessel using pulse analyzer should be needed in further study.

• Journal of the Korea Convergence Society
• /
• v.8 no.12
• /
• pp.77-84
• /
• 2017

With the entry into the aging society, we are increasingly interested in wellness, and personalized medical services through artificial intelligence are expanding. In order to provide personalized medical services, it is difficult to provide accurate medical analysis services only with the existing hospital system components PM / PA, OCS, EMR, PACS, and LIS. Therefore, it is necessary to present the hospital system model and the construction plan suitable for personalized medical service. Currently, some medical cloud services and artificial intelligence diagnosis services using Watson are being introduced in domestic. However, there are not many examples of systematic hospital system construction. Therefore, this paper proposes a hospital system model suitable for personalized medical service. To do this, we design a model that integrates medical big data construction and AI medical analysis system into the existing hospital system components, and suggest development plan of each module. The proposed model is meaningful as a basic research that provides guidelines for the construction of new hospital system in the future.

• Korean Journal of Radiology
• /
• v.23 no.3
• /
• pp.343-354
• /
• 2022

Objective: To develop and evaluate a deep learning-based artificial intelligence (AI) model for detecting skull fractures on plain radiographs in children. Materials and Methods: This retrospective multi-center study consisted of a development dataset acquired from two hospitals (n = 149 and 264) and an external test set (n = 95) from a third hospital. Datasets included children with head trauma who underwent both skull radiography and cranial computed tomography (CT). The development dataset was split into training, tuning, and internal test sets in a ratio of 7:1:2. The reference standard for skull fracture was cranial CT. Two radiology residents, a pediatric radiologist, and two emergency physicians participated in a two-session observer study on an external test set with and without AI assistance. We obtained the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity along with their 95% confidence intervals (CIs). Results: The AI model showed an AUROC of 0.922 (95% CI, 0.842-0.969) in the internal test set and 0.870 (95% CI, 0.785-0.930) in the external test set. The model had a sensitivity of 81.1% (95% CI, 64.8%-92.0%) and specificity of 91.3% (95% CI, 79.2%-97.6%) for the internal test set and 78.9% (95% CI, 54.4%-93.9%) and 88.2% (95% CI, 78.7%-94.4%), respectively, for the external test set. With the model's assistance, significant AUROC improvement was observed in radiology residents (pooled results) and emergency physicians (pooled results) with the difference from reading without AI assistance of 0.094 (95% CI, 0.020-0.168; p = 0.012) and 0.069 (95% CI, 0.002-0.136; p = 0.043), respectively, but not in the pediatric radiologist with the difference of 0.008 (95% CI, -0.074-0.090; p = 0.850). Conclusion: A deep learning-based AI model improved the performance of inexperienced radiologists and emergency physicians in diagnosing pediatric skull fractures on plain radiographs.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.27-40
• /
• 2022

Medical AI, which has lately made significant advances, is playing a vital role, such as assisting clinicians with diagnosis and decision-making. The field of chest X-rays, in particular, is attracting a lot of attention since it is important for accessibility and identification of chest diseases, as well as the current COVID-19 pandemic. However, despite the vast amount of data, there remains a limit to developing an effective AI model due to a lack of labeled data. A research that used federated learning on chest X-ray data to lessen this difficulty has emerged, although it still has the following limitations. 1) It does not consider the problems that may occur in the Non-IID environment. 2) Even in the federated learning environment, there is still a shortage of labeled data of clients. We propose a method to solve the above problems by using the self-supervised learning model as a global model of federated learning. To that aim, we investigate a self-supervised learning methods suited for federated learning using chest X-ray data and demonstrate the benefits of adopting the self-supervised learning model for federated learning.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.6
• /
• pp.243-250
• /
• 2023

Chest X-ray is radiological examination for xeamining the lungs and haert, and is particularly widely used for diagnosing lung disease. Since the quality of these chest X-rays can affect the doctor's diagnosis, the process of evaluating the quality must necessarily go through. This process can involve the subjectivity of radiologists and is manual, so it takes a lot of time and csot. Therefore, in this paper, based on the chest X-ray quality assessment guidelines used in clinical settings, we propose a tool that automates the five quality assessments of artificial shadow, coverage, patient posture, inspiratory level, and permeability. The proposed tool reduces the time and cost required for quality judgment, and can be further utilized in the pre-processing process of selecting high-quality learning data for the development of a learning model for diagnosing chest lesions.

• Journal of the Korean Medical Association
• /
• v.61 no.12
• /
• pp.765-775
• /
• 2018

With growing interest in novel digital healthcare devices, such as artificial intelligence (AI) software for medical diagnosis and prediction, and their potential impacts on healthcare, discussions have taken place regarding the regulatory approval, coverage, and clinical implementation of these devices. Despite their potential, 'digital exceptionalism' (i.e., skipping the rigorous clinical validation of such digital tools) is creating significant concerns for patients and healthcare stakeholders. This white paper presents the positions of the Korean Society of Radiology, a leader in medical imaging and digital medicine, on the clinical validation, regulatory approval, coverage decisions, and clinical implementation of novel digital healthcare devices, especially AI software for medical diagnosis and prediction, and explains the scientific principles underlying those positions. Mere regulatory approval by the Food and Drug Administration of Korea, the United States, or other countries should be distinguished from coverage decisions and widespread clinical implementation, as regulatory approval only indicates that a digital tool is allowed for use in patients, not that the device is beneficial or recommended for patient care. Coverage or widespread clinical adoption of AI software tools should require a thorough clinical validation of safety, high accuracy proven by robust external validation, documented benefits for patient outcomes, and cost-effectiveness. The Korean Society of Radiology puts patients first when considering novel digital healthcare tools, and as an impartial professional organization that follows scientific principles and evidence, strives to provide correct information to the public, make reasonable policy suggestions, and build collaborative partnerships with industry and government for the good of our patients.

• International Journal of Advanced Culture Technology
• /
• v.12 no.3
• /
• pp.148-158
• /
• 2024

We investigate Autism Spectrum Disorder (ASD), which is typified by deficits in social interaction, repetitive behaviors, limited vocabulary, and cognitive delays. Traditional diagnostic methodologies, reliant on expert evaluations, frequently result in deferred detection and intervention, particularly in South Korea, where there is a dearth of qualified professionals and limited public awareness. In this study, we employ advanced deep learning algorithms to enhance early ASD screening through automated video analysis. Utilizing architectures such as Convolutional Long Short-Term Memory (ConvLSTM), Long-term Recurrent Convolutional Network (LRCN), and Convolutional Neural Networks with Gated Recurrent Units (CNN+GRU), we analyze video data from platforms like YouTube and TikTok to identify stereotypic behaviors (arm flapping, head banging, spinning). Our results indicate that the LRCN model exhibited superior performance with 79.61% accuracy on the augmented platform video dataset and 79.37% on the original SSBD dataset. The ConvLSTM and CNN+GRU models also achieved higher accuracy than the original SSBD dataset. Through this research, we underscore AI's potential in early ASD detection by automating the identification of stereotypic behaviors, thereby enabling timely intervention. We also emphasize the significance of utilizing expanded datasets from social media platform videos in augmenting model accuracy and robustness, thus paving the way for more accessible diagnostic methods.