• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.10
• /
• pp.530-540
• /
• 2005

Virtual colonoscopy is an easy and fast method to reconstruct the shape of colon and diagnose tumors inside the colon based on computed tomography images. This is a non-invasive method, which resolves weak points of previous invasive methods. The path for virtual colonoscopy should be generated rapidly and accurately for clinical examination. However, previous methods are computationally expensive because the data structure such as distance map should be constructed in the preprocessing and positions of all the points of the path needs to be calculated. In this paper, we propose the automatic path generation method based on visibility to decrease path generation time. The proposed method does not require preprocessing and generates small number of control points representing the Path instead of all points to generate the path rapidly. Also, our method generates the path based on visibility so that a virtual camera moves smoothly and a comfortable and accurate path is calculated for virtual navigation. Also, our method can be used for general virtual navigation of various kinds of pipes.

• Journal of the Korean Society of Radiology
• /
• v.15 no.5
• /
• pp.613-620
• /
• 2021

The purpose of this study is to propose a convolutional neural network model that can classify normal and abnormal(cardiomegaly) in chest X-ray images. The training data and test data used in this paper were used by acquiring chest X-ray images of patients diagnosed with normal and abnormal(cardiomegaly). Using the proposed deep learning model, we classified normal and abnormal(cardiomegaly) images and verified the classification performance. When using the proposed model, the classification accuracy of normal and abnormal(cardiomegaly) was 99.88%. Validation of classification performance using normal images as test data showed 95%, 100%, 90%, and 96% in accuracy, precision, recall, and F1 score. Validation of classification performance using abnormal(cardiomegaly) images as test data showed 95%, 92%, 100%, and 96% in accuracy, precision, recall, and F1 score. Our classification results show that the proposed convolutional neural network model shows very good performance in feature extraction and classification of chest X-ray images. The convolutional neural network model proposed in this paper is expected to show useful results for disease classification of chest X-ray images, and further study of CNN models are needed focusing on the features of medical images.

• The Journal of the Korea Contents Association
• /
• v.19 no.8
• /
• pp.284-292
• /
• 2019

To evaluate the usefulness of pediatric chest CT scans by comparing the dose, examination time, and image quality by applying Helical mode, High-pitch mode, and Volume Axial mode to minimize the radiation exposure and obtain high diagnostic value. Revolution (GE Healthcare, Wisconsin USA) was used to divide PBU-70 phantom into Helical mode, High-pitch mode, and Volume Axial mode. After acquiring images, ROI is set for each image, heart, bone, lung, and back-ground air, and the average value is obtained by measuring CT number (HU) and noise (SD). SNR and CNR were measured and compared with DLP values provided directly by the equipment. Determining statistical significance Statistical analysis was performed using ONE-WAY-ANAOVA using SPSS 21.0. In this experiment, it was possible to inspect at a short time without deterioration of image quality with the lowest dose when using volume axial mode. Although the detector coverage of 16 cm is limited to all pediatric chest CT scans, it is recommended to be actively used in pediatric patients, and further study is needed to apply other test sites in volume axial mode.

• The Journal of the Korea Contents Association
• /
• v.20 no.8
• /
• pp.152-161
• /
• 2020

The purpose of this study was to conduct a task-based field experience program for medical care support departments in hospitals for 1st medical students, and then to analyze the their experiences and its meanings phenomenologically. We selected the following department in hospital; nursing, medical records, pharmacy, diagnosis laboratory, radiology, administration, customer consulting center, organ transplant center, palliative medical ward, and international medical center. The students visited the department and used various methods such as interviewing, observation, and experience to solve the given task. As a result, in the program satisfaction, students rated the highest as having many department in the hospital and understanding their role. The essential structure of the experience of medical care support department in the reflection journal written by the students was the recognition of reality, respect and collaboration, and self-reflection from experience recognition.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2010.06a
• /
• pp.374-374
• /
• 2010

본 연구는 Roll-to-Roll Sputtering 장비를 사용하여 제작된 Flexible ITO electrode 필름의 방사선 검출기로의 적용가능성을 알아보기 위해 기존의 Glass ITO electrode의 전기적 특성을 비교 평가하였다. 본 연구는 Flexible ITO electrode와 Glass ITO electrode을 하부전극으로 형성하고, 최근에 X-ray 변환체로 활발히 연구되고 있는 Powder 형태의 반도체물질인 HgI2 와 PbI2를 Binder와 일정한 비율로 혼합하여 3-Rolls-Miller를 사용하여 Powder를 일정한 미세크기로 만들고, 대면적 제작이 용이한 Screen-Printing method을 이용하여 시편을 제작하였다. 제작된 필름은 하부전극의 종류에 따른 X-ray 입사 후의 전기적신호의 차이를 측정하고, HgI2와 PbI2 중 Flexible ITO electrode와 더욱 효율적으로 반응하여 기존의 Glass ITO electrode를 대체할 수 있는 전극을 발견하여 진단용 의료영상의 왜곡 현상을 제거할 수 있는 Flexible 방사선 검출기의 제작의 초석을 제공하는 연구를 목적으로 한다. SEM(Scanning Electron Microscope) 통하여 반도체 물질의 결정구조와 크기를 알아보았고, 하부 전극의 종류에 따른 전기적 신호검출을 위해 제작된 필름의 암전류(Dark current) 와 민감도(Sensitivity)를 측정한 후, SNR (Signal -to- Noise)을 계산하여 평가하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.11
• /
• pp.2077-2082
• /
• 2008

Recent the advanced technologies in medical imaging such as magnetic resonance imaging (MRI) and computed tomography (CT) make doctors improve the diagnostic skill with detailed anatomical information. In general, it is necessary to get a number of MRI images in order to obtain more detail information. However, the performance of MRI machines of privately run hospitals is not good and thus we may obtain only a few of MRI images. If 3D surface reconstruction is accomplished with a few slices, then it generates 3D surface of poor qualify. This paper propose a way to Set a 3D surface of high quality from a few of number of slices. First of all, our algorithm detects the boundary of tissues which we want to reconstruct as a 3D object and find out the set of vortices on the boundary. And then we generate a 3D implicit surface to interpolate the boundary points by using radial basis function. Lastly, we render the 3D implicit surface by using Marching cube algorithms.

• Journal of Advanced Navigation Technology
• /
• v.27 no.1
• /
• pp.139-145
• /
• 2023

When a doctor examines a patient in a hospital, the doctor directly checks the patient's condition and conducts a face-to-face diagnosis through dialogue with the patient. However, it is often difficult for doctors to directly treat patients. Recently, several types of telemedicine systems have been developed. However, the systems have lack of capabilities to observe heart disease, neck condition, skin condition, inside ear condition, etc. To solve this problem, in this paper, an interactive telemedicine robot system with autonomous driving in a room capable of visual examination and auscultation of patients is developed. The developed robot can be controlled remotely through the WebRTC platform to move toward the patient and check a patient's condition under the doctor's observation using the multi-joint robot arm. The video information, audio information, patient's heart sound, and other data obtained remotely from patients can be transmitted to a doctor through the web RTC platform. The developed system can be applied to the various places where doctors are not possible to attend.

• Journal of the Korean Society of Radiology
• /
• v.17 no.3
• /
• pp.401-410
• /
• 2023

A radiographer is a job in charge of diagnostic imaging equipment, and must contribute to the promotion of public health by suggesting an appropriate level of work. To this end, we intend to present an appropriate level of work through evaluation of human harm according to work, statistical evaluation through questionnaires, and domestic and international trends. In the case of human harm evaluation, considering radiation exposure, 42.6%, shield work, 69.7%, and in the case of magnetic resonance imaging, the maximum length of stay in the examination room should be adjusted to 15 minutes and not exceed 30 times. According to the survey statistics, it was confirmed that the physical and mental burden increased due to the high workload and difficulty compared to working hours. Based on domestic and international trends, it is necessary to adjust the examination standards for domestic radiographers to 36.8% to promote national health through qualitative improvement of radiological examinations. something to do.

• Journal of Digestive Cancer Research
• /
• v.4 no.1
• /
• pp.21-28
• /
• 2016

Hepatocellular carcinoma (HCC) is rather unique. Most of HCC patients have underlying chronic liver diseases with or without cirrhosis and the prognosis of HCC depends on the liver function, as well as the tumor extent. Non-invasive diagnosis of HCC can be made with certain risk factors and specific imaging findings (e.g. hypervascularity). Patients with HCC can receive surgical resection, radiotherapy, and systemic chemotherapy as other solid malignancies. HCC has more treatment options such as liver transplantation, transarterial chemoembolization (TACE) and radiofrequency ablation (RFA). A variety of practice guidelines for HCC has been published by many academic societies. Different healthcare systems and availability of resources also affect the practice guidelines; therefore, practice guidelines have similarities and dissimilarities. Herein, we review the current status of practice guidelines for HCC and future perspectives for the improvement of guidelines are also discussed.

• Journal of the Korean Society of Radiology
• /
• v.14 no.6
• /
• pp.773-780
• /
• 2020

With the development of the 4th industrial, research is being conducted to prevent diseases and reduce damage in various fields of science and technology such as medicine, health, and bio. As a result, artificial intelligence technology has been introduced and researched for image analysis of radiological examinations. In this paper, we will directly apply a deep learning model for classification and detection of pneumonia using chest X-ray images, and evaluate whether the deep learning model of the Inception series is a useful model for detecting pneumonia. As the experimental material, a chest X-ray image data set provided and shared free of charge by Kaggle was used, and out of the total 3,470 chest X-ray image data, it was classified into 1,870 training data sets, 1,100 validation data sets, and 500 test data sets. I did. As a result of the experiment, the result of metric evaluation of the Inception V3 deep learning model was 94.80% for accuracy, 97.24% for precision, 94.00% for recall, and 95.59 for F1 score. In addition, the accuracy of the final epoch for Inception V3 deep learning modeling was 94.91% for learning modeling and 89.68% for verification modeling for pneumonia detection and classification of chest X-ray images. For the evaluation of the loss function value, the learning modeling was 1.127% and the validation modeling was 4.603%. As a result, it was evaluated that the Inception V3 deep learning model is a very excellent deep learning model in extracting and classifying features of chest image data, and its learning state is also very good. As a result of matrix accuracy evaluation for test modeling, the accuracy of 96% for normal chest X-ray image data and 97% for pneumonia chest X-ray image data was proven. The deep learning model of the Inception series is considered to be a useful deep learning model for classification of chest diseases, and it is expected that it can also play an auxiliary role of human resources, so it is considered that it will be a solution to the problem of insufficient medical personnel. In the future, this study is expected to be presented as basic data for similar studies in the case of similar studies on the diagnosis of pneumonia using deep learning.