• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.669-672
• /
• 2018

캡술내시경은 식도부터 항문까지 소화기관 전체를 한번에 촬영할 수 있는 의료기기로, 한번의 검사에 평균 8~12 시간 정도의 길이와 5만장 이상의 프레임으로 구성된 영상을 생성한다. 그러나 생성된 영상에 대한 분석은 수작업으로 진행되고 있어, 캡술내시경 영상 분석 자동화에 대한 기술적인 수요가 높아지고 있는 추세이다. 이를 위해, 캡슐내시경 영상 분석에 대한 많은 연구가 진행되고 있는데, 본 연구에서는 그 중에서도 폴립 영상에 대한 검출 자동화 연구에 주목하였다. 폴립이란 위장관 내에서 발견될 수 있는 융기성 병변으로, 많은 연구에서 기계학습 혹은 딥러닝 방식을 적용하여 이를 검출하기 위한 연구를 수행하였다. 그러나 캡슐내시경 영상의 특성상, 병번이 있는 영상이 굉장히 적기 때문에 일반적인 딥러닝 방식의 적용으로 좋은 성능을 내기 어렵다. 따라서 본 논문에서는 폴립 검출 컨볼루션 신경망 설계를 위한 멀티 스케일에 대한 원형 검출기법을 결합하여 폴립이 의심되는 영역을 추출해주는 특징 추출 기법으로, 수집한 데이터 150장에 대한 실험한 결과 약 82%의 성능을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.862-863
• /
• 2015

본 연구에서는 조영증강 초음파 진단에서 혈류의 패턴을 효과적으로 판단할 수 있게 하기 위하여 조영제의 확산패턴을 영상으로 표현하는 방법론을 제안한다. 초음파 영상에서 조영제의 전이 시간에 대한 파라미터의 가시화 기법과, 단계별 전이패턴을 단일 영상으로 표현하는 방법을 제시함으로써, 병변의 진단 및 분석과정에서 대상 영역 내 혈류의 형태와 속도를 효과적으로 판별할 수 있게 한다. 분석과정의 필요에 따라 영상에서 정밀도를 선택적으로 적용할 수 있도록 하였으며, 노이즈 제거를 위한 필터링 과정과 단계별 전이 시점의 위치에 대한 영역 분할 과정을 거쳐 영상 생성결과를 개선할 수 있도록 하였다.

• Journal of radiological science and technology
• /
• v.31 no.1
• /
• pp.1-10
• /
• 2008

Ubiquitous health care system, which is one of the developing solution technologies of IT, BT and NT, could give us new medical environments in future. Implementing health information systems can be complex, expensive and frustrating. Healthcare professionals seeking to acquire or upgrade systems do not have a convenient, reliable way of specifying a level of adherence to communication standards sufficient to achieve truly efficient interoperability. Great progress has been made in establishing such standards-DICOM, IHE and HL7, notably, are now highly advanced. IHE has defined a common framework to deliver the basic interoperability needed for local and regional health information networks. It has developed a foundational set of standards-based integration profiles for information exchange with three interrelated efforts. HL7 is one of several ANSI-accredited Standards Developing Organizations operating in the healthcare arena. Most SDOs produce standards (protocols) for a particular healthcare domain such as pharmacy, medical devices, imaging or insurance transactions. HL7's domain is clinical and administrative data. HL7 is an international community of healthcare subject matter experts and information scientists collaborating to create standards for the exchange, management and integration of electronic healthcare information. The ASTM specification for Continuity of Care Record was developed by subcommittee E31.28 on electronic health records, which includes clinicians, provider institutions, administrators, patient advocates, vendors, and health industry. In this paper, there are suggestions that provide a test bed, demonstration and specification of how standards such a IHE, HL7, ASTM can be used to provide an integrated environment.

• Proceedings of the Korean Society of Radiological Science
• /
• 2002.10a
• /
• pp.28-28
• /
• 2002

• Journal of Korean Society of Archives and Records Management
• /
• v.22 no.2
• /
• pp.51-73
• /
• 2022

Currently, an implementation plan of administrative information dataset record management has been prepared; however, analyzing the specificity of various administrative information systems and preparing a reasonable level of management reference table by applying about 1.3% (EA portal registration system: 16,199, consulting system: 214) has its limitations. This study started by recognizing the importance of the records management environment in administrative information datasets. Based on the described information, the current records management environment was analyzed by dividing the six areas of the management reference table of the picture archiving and communication system (PACS) into three groups. Thus, a systematic environmental improvement model was proposed, enhancing the effectiveness of dataset records management in the field. Although there is a limitation in analyzing one of the dataset records management environments of various institutions, it is intended to help broaden the horizons of records management research.

• Journal of radiological science and technology
• /
• v.43 no.3
• /
• pp.195-208
• /
• 2020

Artificial intelligence(AI) is a field of computer science that is defined as allowing computers to imitate human intellectual behavior, even though AI's performance is to imitate humans. It is grafted across software-based fields with the advantages of high accuracy and speed of processing that surpasses humans. Indeed, the AI based technology has become a key technology in the medical field that will lead the development of medical image analysis. Therefore, this article introduces and discusses the concept of deep learning-based medical imaging analysis using the principle of algorithms for convolutional neural network(CNN) and back propagation. The research cases application of the AI based medical imaging analysis is used to classify the various disease(such as chest disease, coronary artery disease, and cerebrovascular disease), and the performance estimation comparing between AI based medical imaging classifier and human experts.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2010.08a
• /
• pp.100-100
• /
• 2010

토모그래피는 플라즈마 물리학뿐만 아니라 의료영상이나 천문학 등의 분야에서 오랫동안 이용되어 온 기법으로 직접 들여다 볼 수 없는 단면을 선적분된 데이터를 이용하여 국지적인 데이터를 재구성해내는 영상진단 방법이다. 플라즈마 물리학의 경우 공간적으로 검출기 배열을 균일하게 배치할 수 없으므로 토모그래피 기법에 균일화는 필수적이다. 이를 위해 본 연구에서는 Phillips-Tikhonov 균일화 방법을 사용하였다. Phillip-Tikhonov 균일화 방법은 인접한 픽셀 사이의 구배(gradient)를 최소화하는 방향으로 단면영상을 재구성하는 방식으로, 다른 토모그래피 알고리듬에 비해 훨씬 더 정확한 결과를 보여준다. 본 연구에서는 플라즈마의 공간분포 진단을 위하여 토모그래피 진단법과 부유탐침 진단법을 사용하였다. 플라즈마의 선적분된 방출광을 디지털카메라로 측정한 후 Phillips-Tikhonov 토모그래피 방법으로 재구성하여 플라즈마의 국지적인 공간분포를 알아내었다. 결과의 타당성을 확보하기 위해 부유탐침 진단결과와 비교 분석하여, 전자온도가 위치에 따라 일정한 상태에서 부유탐침을 통한 밀도분포와 토모그래피 진단법에 의한 플라즈마 방출광 세기의 공간분포가 거의 일치함을 확인할 수 있었다. 이를 통해 플라즈마의 국지적인 공간분포 진단을 위한 디지털카메라를 이용한 토모그래피 진단법의 타당성을 검증하였다.

• Journal of Biomedical Engineering Research
• /
• v.23 no.4
• /
• pp.263-268
• /
• 2002

The image quality of imageguide depends on the structure, material, length of microfibers and the phenomena such as cross-talk and leaky ray between adjacent fibers. These Parameters should be considered as important factors in the image transmission qualify of fibers. However it is considered to be very difficult to assess all the parameters in a consistent way Therefore. two image characteristics, image resolution and image brightness are measured and analyzed to determine the image quality of imageguide. But the exact methods to measure two image characteristics of imageguide are not reported. In this study, the image brightness of imageguide for ultrathin endoscope is determined by measuring of the numerical aperture. the packing fraction and the attenuated power ratio of imageguide. Especially it is possible to obtain more exact results from measuring the numerical aperture of whole image guide than those from theoretical calculation of the single microfiber in an image guide. The image brightness of the image guide which has $3.1\mu m$ microfibers is about 37% less than that with $4.1\mu m$ microfibers.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.279-282
• /
• 2022

Acute lymphoblastic leukemia is an acute leukemia caused by suppression of bone marrow function due to overgrowth of immature lymphocytes in the bone marrow. It accounts for 30% of acute leukemia in adults, and children show a cure rate of over 80% with chemotherapy, while adults show a low survival rate of 20% to 50%. However, research on a machine learning algorithm based on medical image data for the diagnosis of acute lymphoblastic leukemia is in the initial stage. In this paper, we compare and analyze CNN algorithm models for quick and accurate diagnosis. Using four models, an experimental environment for comparative analysis of acute lymphoblastic leukemia diagnostic models was established, and the algorithm with the best accuracy was selected for the given medical image data. According to the experimental results, among the four CNN models, the InceptionV3 model showed the best performance with an accuracy of 98.9%.

• Journal of the Korean Society of Radiology
• /
• v.10 no.2
• /
• pp.81-87
• /
• 2016

In this study we proposed a texture feature analysis algorithm that distinguishes between a normal image and a diseased image using CT images of some fatty liver patients, and generates both Eigen images and test images which can be applied to the proposed computer aided diagnosis system in order to perform a quantitative analysis for 6 parameters. And through the analysis, we derived and evaluated the recognition rate of CT images of fatty liver. As the results of examining over 30 example CT images of fatty liver, the recognition rates representing a specific texture feature-value are as follows: some appeared to be as high as 100% including Average Gray Level, Entropy 96.67%, Skewness 93.33%, and Smoothness while others showed a little low disease recognition rate: 83.33% for Uniformity 86.67% and for Average Contrast 80%. Consequently, based on this research result, if a software that enables a computer aided diagnosis system for medical images is developed, it will lead to the availability for the automatic detection of a diseased spot in CT images of fatty liver and quantitative analysis. And they can be used as computer aided diagnosis data, resulting in the increased accuracy and the shortened time in the stage of final reading.