• International journal of advanced smart convergence
• /
• v.10 no.2
• /
• pp.21-30
• /
• 2021

With the rapid development of artificial intelligence and big data, a lot of medical data is effectively used, and the diagnosis and analysis of diseases has entered the era of intelligence. With the increasing public health awareness, ordinary citizens have also put forward new demands for panic disorder health services. Specifically, people hope to predict the risk of panic disorder as soon as possible and grasp their own condition without leaving home. Against this backdrop, the smart health industry comes into being. In the Internet age, a lot of panic disorder health data has been accumulated, such as diagnostic records, medical record information and electronic files. At the same time, various health monitoring devices emerge one after another, enabling the collection and storage of personal daily health information at any time. How to use the above data to provide people with convenient panic disorder self-assessment services and reduce the incidence of panic disorder in China has become an urgent problem to be solved. In order to solve this problem, this research applies the context awareness to the automatic diagnosis of human diseases. While helping patients find diseases early and get treatment timely, it can effectively assist doctors in making correct diagnosis of diseases and reduce the probability of misdiagnosis and missed diagnosis.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.12
• /
• pp.6013-6021
• /
• 2012

Although there are many patients who suffer from cold hypersensitivity and have a difficult time in living daily lives due to feeling cold at room temperature, it is about true that an accurate diagnostic method and an effective remedy for a cold hypersensitivity have not been developed yet. Therefore, in order to develop traditional medicine equipment for cold hypersensitivity, we have designed new oxygen chamber system which can diagnose cold hypersensitivity with multiple bionic sensors and supply a patient optimum amount of oxygen adaptively to the extent of their illness. In particular, diverging from conventional diagnosis based on the experience of doctor and subjective statements of patient, we introduced accurate method for diagnosis in comparing between output of multiple sensors and threshold derived from clinical trials. After all, the proposed oxygen chamber system will contribute to achieving scientific evidence and manufacturing of korean traditional medicine.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.7
• /
• pp.233-240
• /
• 2022

Most of the recent AI researches has focused on developing AI models. However, recently, artificial intelligence research has gradually changed from model-centric to data-centric, and the importance of learning data is getting a lot of attention based on this trend. However, it takes a lot of time and effort because the preparation of learning data takes up a significant part of the entire process, and the generation of labeling data also differs depending on the purpose of development. Therefore, it is need to develop a tool with various labeling functions to solve the existing unmetneeds. In this paper, we describe a labeling system for creating precise and fast labeling data of medical images. To implement this, a semi-automatic method using Back Projection, Grabcut techniques and an automatic method predicted through a machine learning model were implemented. We not only showed the advantage of running time for the generation of labeling data of the proposed system, but also showed superiority through comparative evaluation of accuracy. In addition, by analyzing the image data set of about 1,000 patients, meaningful diagnostic indexes were presented for men and women in the diagnosis of sarcopenia.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.22
• /
• pp.9927-9931
• /
• 2014

The objectives of this study were to examine serum periplakin expression in patients with urothelial carcinoma of the urinary bladder and in normal controls, and to examine relationships with clinicopathological findings. Detection of serum periplakin was performed in 50 patients and 30 normal controls with anti-periplakin antibodies using the automatic dot blot system, and a micro-dot blot array with a 256 solid-pin system. Levels in patients with urothelial carcinoma of the urinary bladder were significantly lower than those in normal controls (0.31 and 5.68, respectively; p<0.0001). The area under the receiver-operator curve level for urothelial carcinoma of the urinary bladder was 0.845. The sensitivity and specificity, using a cut-off point of 4.045, were 83.7% and 73.3%, respectively. In addition, serum periplakin levels were significantly higher in patients with muscle-invasive cancer than in those with nonmuscle-invasive cancer (P = 0.03). In multivariate Cox proportional hazards regression analysis, none of the clinicopathological factors was associated with an increased risk for progression and cancer-specific survival. Examination of the serum periplakin level may play a role as a non-invasive diagnostic modality to aid urine cytology and cystoscopy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.107-114
• /
• 2017

Iris diagnosis is an alternative medicine to diagnose the disease of the patient by using different of the iris pattern, color and other characteristics. This paper proposed a disease prediction algorithm that using the iris regions that analyze iris change to using differential image of iris image. this method utilize as patient's health examination according to iris change. Because most of previous studies only find a sign pattern in a iris image, it's not enough to be used for a iris diagnosis system. We're developed an iris diagnosis system based on a iris images processing approach, It's presents the extraction algorithms of 8 major iris signs and correction manually for improving the accuracy of analysis. As a result, PNSR of applied edge detection image is about 132, and pattern matching area recognition presented practical use possibility by automatic diagnostic that presume situation of human body by iris about 91%.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.2
• /
• pp.38-45
• /
• 2012

If an infant with congenital hearing loss is diagnosed in good time and get proper treatment as soon as possible, treatment effect could be maximized and the social costs could be considerably reduced. For these reasons, the medical equipment to screen hearing impairment objectively is needed. The ABR(auditory brainstem response) is typical diagnostic tools for this purpose but there are drawbacks in sense that it does not have frequency specificity and shows hearing information of usually high frequency band. The ASSR(auditory steady-state response) is excellent in frequency specificity, but the rate of wrong diagnosis is slightly high. In this study, we proposed the system which can measure both the ABR and the ASSR, and can show the objective and quantitative indices(Fsp and F-test). It was designed to allow various tests without hardware modification by minimizing hardware components and by increasing software roles. The objective assessment of the developed system was evaluated by experiments with 10 normal persons.

• Journal of the Korean Society of Radiology
• /
• v.10 no.6
• /
• pp.443-450
• /
• 2016

In this study, we are using a computer tomography image of the abdomen, as an experimental linear research for the image of the fatty liver patients texture features analysis and computer-aided diagnosis system of implementation using the ROC curve analysis, from the computer tomography image. We tried to provide an objective and reliable diagnostic information of fatty liver to the doctor. Experiments are usually a fatty liver, via the wavelet transform of the abdominal computed tomography images are configured with the experimental image section, shows the results of statistical analysis on six parameters indicating a feature value of the texture. As a result, the entropy, average luminance, strain rate is shown a relatively high recognition rate of 90% or more, the control also, flatness, uniformity showed relatively low recognition rate of about 70%. ROC curve analysis of six parameters are all shown to 0.900 (p = 0.0001) or more, showed meaningful results in the recognition of the disease. Also, to determine the cut-off value for the prediction of disease six parameters. These results are applicable from future abdominal computed tomography images as a preliminary diagnostic article of diseases automatic detection and eventual diagnosis.

• Imaging Science in Dentistry
• /
• v.50 no.2
• /
• pp.169-174
• /
• 2020

Purpose: Periodontal disease causes tooth loss and is associated with cardiovascular diseases, diabetes, and rheumatoid arthritis. The present study proposes using a deep learning-based object detection method to identify periodontally compromised teeth on digital panoramic radiographs. A faster regional convolutional neural network (faster R-CNN) which is a state-of-the-art deep detection network, was adapted from the natural image domain using a small annotated clinical data- set. Materials and Methods: In total, 100 digital panoramic radiographs of periodontally compromised patients were retrospectively collected from our hospital's information system and augmented. The periodontally compromised teeth found in each image were annotated by experts in periodontology to obtain the ground truth. The Keras library, which is written in Python, was used to train and test the model on a single NVidia 1080Ti GPU. The faster R-CNN model used a pretrained ResNet architecture. Results: The average precision rate of 0.81 demonstrated that there was a significant region of overlap between the predicted regions and the ground truth. The average recall rate of 0.80 showed that the periodontally compromised teeth regions generated by the detection method excluded healthiest teeth areas. In addition, the model achieved a sensitivity of 0.84, a specificity of 0.88 and an F-measure of 0.81. Conclusion: The faster R-CNN trained on a limited amount of labeled imaging data performed satisfactorily in detecting periodontally compromised teeth. The application of a faster R-CNN to assist in the detection of periodontally compromised teeth may reduce diagnostic effort by saving assessment time and allowing automated screening documentation.

• Journal of Advanced Navigation Technology
• /
• v.15 no.5
• /
• pp.833-838
• /
• 2011

X-ray device used in the diagnosis has made possible to have more effective and accurate diagnosis, powered by the development of various devices. Based on this, X-ray device has become the most basic and essential diagnostic equipment in clinical medicine. At present, in the image acquisition field using X-ray, the use of Digital radiography which is useful in the acquisition time reduction and transfer of images and is possible to have the dose reduction has expanded. With the structure using one detector, this DR device has disadvantages in that it needs structural changes unlike existing X-ray and the detector should be moved to the desired position depending on the shooting location. Therefore, in this study, using BLDC(Brushless direct current) motor and PID(Proportional integral differential) control method, the automatic control system of 3-axis which is upward and downward, left and right and rotation of detector where having the most movement in DR was designed and produced and its performance was evaluated.

• Korean Journal of Occupational Health Nursing
• /
• v.18 no.1
• /
• pp.44-54
• /
• 2009

Purpose: The aim of this study was to examine the effects of obesity on the physiological levels of adiponectin, leptin and components of metabolic syndrome (MS) in male workers, aged 30-40 years. Methods: Body mass index (BMI) was measured with Anthropometric equipment. Blood pressure and serum parameters were measured with an automatic digital sphygmomanometer and autochemical analyzer, respectively. Adiponectin and leptin were analysed by ELISA kits and MS was defined based on the NCEP-ATP III. Results: Body fat mass of waist and hip, systolic and diastolic blood pressure were significantly higher, as expected, in the BMI>25kg/$m^2$ in comparison with the $BMI{\leq}25kg/m^2$. While fasting glucose, insulin, HOMA-IR and leptin in the BMI>25kg/$m^2$ were also significantly higher compared with $BMI{\leq}25kg/m^2$, HDL-cholesterol and adiponectin were significantly higher in $BMI{\leq}25kg/m^2$. On multiple logistic regression analysis for the components of MS, exercise, adiponectin and leptin were an only independent factor for MS in non-obese male workers($BMI{\leq}25kg/m^2$) after adjustment for age, cigarette smoking and drinking habits. Conclusion: These results suggested that the obesity in men was associated with physiological levels of adiponectin and leptin contributing to feedback control of MS and that dysfunction and/or declination in feedback control system associated with changes in physiological levels of neurptrophics: adiponectin and leptin might ultimately induce MS.