• 인터넷정보학회논문지
• /
• 제25권5호
• /
• pp.53-65
• /
• 2024

Currently, artificial intelligence (AI) is being applied in the medical field to collect and analyze data such as personal genetic information, medical information, and lifestyle information. In particular, in the medical imaging field, AI is being applied to the medical imaging field to analyze patients' medical image data and diagnose diseases. Deep learning (DL) of deep neural networks such as CNN and GAN have been introduced to medical image analysis and medical data augmentation to facilitate lesion detection, quantification, and classification. In this paper, we examine AI used in the medical imaging field and review related medical image data acquisition devices, medical information systems for transmitting medical image data, problems with medical image data, and the current status of explainable artificial intelligence (XAI) that has been actively applied recently. In the future, the continuous development of AI and information and communication technology (ICT) is expected to make it easier to analyze medical image data in the medical field, enabling disease diagnosis, prognosis prediction, and improvement of patients' quality of life. In the future, AI medicine is expected to evolve from the existing treatment-centered medical system to personalized healthcare through preemptive diagnosis and prevention.

• Journal of Electrical Engineering and Technology
• /
• 제10권6호
• /
• pp.2384-2392
• /
• 2015

The technical development and practical applications of big-data for health is one hot topic under the banner of big-data. Big-data medical image fusion is one of key problems. A new fusion approach with coding based on Spherical Coordinate Domain (SCD) in Wireless Sensor Network (WSN) for big-data medical image is proposed in this paper. In this approach, the three high-frequency coefficients in wavelet domain of medical image are pre-processed. This pre-processing strategy can reduce the redundant ratio of big-data medical image. Firstly, the high-frequency coefficients are transformed to the spherical coordinate domain to reduce the correlation in the same scale. Then, a multi-scale model product (MSMP) is used to control the shrinkage function so as to make the small wavelet coefficients and some noise removed. The high-frequency parts in spherical coordinate domain are coded by improved SPIHT algorithm. Finally, based on the multi-scale edge of medical image, it can be fused and reconstructed. Experimental results indicate the novel approach is effective and very useful for transmission of big-data medical image(especially, in the wireless environment).

• 융복합기술연구소 논문집
• /
• 제11권1호
• /
• pp.1-5
• /
• 2021

Deep learning based methods achieve state-of-the-art accuracy, however, they typically rely on supervised training with large labeled datasets. It is known in many medical applications that labeling medical images requires significant expertise and much time, and typical hand-tuned approaches for data augmentation fail to capture the complex variations in such images. This paper proposes a 3D image augmentation method to overcome these difficulties. It allows us to enrich diversity of training data samples that is essential in medical image segmentation tasks, thus reducing the data overfitting problem caused by the fact the scale of medical image dataset is typically smaller. Our numerical experiments demonstrate that the proposed approach provides significant improvements over state-of-the-art methods for 3D medical image segmentation.

• 한국컴퓨터정보학회논문지
• /
• 제7권4호
• /
• pp.8-15
• /
• 2002

본 논문은 의료영상을 데이터베이스화 시켜 그것을 영구적으로 보관할 수 있는 시스템 개발이다. 즉, 정형외과의 관절경을 이용한 수술이나 진단 시 수집되는 영상 자료를 데이터베이스화하여 복수의 적용 업무나 응용프로그램이 데이터를 공유할 수 있도록 하며, 동일한 자료의 중복을 피하고 검색과 갱신이 효율적으로 되도록 데이터를 관리하는 시스템이다. 본 시스템은 다섯 가지 구성요소로 이루어져 있다. 즉, 내시경으로부터 영상자료를 받는 입력모듈, 입력받은 영상자료를 저장하는 모듈, 환자의 진료내역 및 영상자료를 저장하는 데이터베이스 설계 및 구현, 사용하기 편리한 인터페이스 설계 및 구현, 간단하고 편리한 데이터 검색을 위한 엔진 등이다. 시스템의 특징은 다음과 같다. DirectShow를 이용한 영상 캡쳐 프로그램은 어떤 영상 캡쳐 보드와 호환이 가능하다. 영상 캡쳐 알고리즘을 공용 모듈로 만들었기 때문에 인터넷상에서 비디오. 오디오 컨텐츠를 개발할 때 작업효율을 높일 수 있다.

• 한국인터넷방송통신학회논문지
• /
• 제12권5호
• /
• pp.39-54
• /
• 2012

오늘날 의료정보화 수준향상과 디지털 병원화의 흐름에 따라 PACS는 의료기관의 핵심 인프라 중 하나로 자리매김하였다. 이와 함께 생산되는 디지털 의료영상의 종류 및 의료영상 데이터가 양적으로 급증하고 있으며, 이는 의료영상 데이터의 효과적인 보관을 위한 의료영상 압축을 중요한 요소로 부각시킨다. 현재 의료영상에 관한 사실상의 표준인 DICOM 규격에서는 의료영상 압축을 위하여 무손실 압축기법인 RLE를 명시하고 있으나, 무손실 범용 압축기법인 RLE는 인체의 대칭성을 가지는 많은 의료영상에 적용하면 높은 압축율 기대하기 힘들다. 이 논문에서는 다양한 의료영상 중 대칭 특성을 크게 내포하는 뇌 CT 영상을 대상으로 하여 영상 내 관심영역을 검출하고 대칭특성에 따라 영상의 픽셀 값을 재코딩하는 전처리 하고 영상을 압축하는 기법을 제안한다. 실험에 의하면, 제안한 기법은 RLE 압축과 영상 내 관심영역을 검출하지 않고 압축할 때와 비교하여 높은 압축률을 보인다.

• 한국정보처리학회논문지
• /
• 제5권12호
• /
• pp.3275-3284
• /
• 1998

본 논문에서는 각종 단층 촬영 의료영상 장비로 촬영한 2차원 단면화상 데이터들을 차원 재구성 알고리즘을 사용하여 3차원 영상으로 재구성한 다음, 웹 서버의 데이터베이스에 저장하고 관리하며, 인터넷 가상현실 표준언어인 VRML(Virtual Reality Modeling Language)로 표현된 3차원 의료영상을 비롯한 각종 의료영상 정보를 웹브라우저를 사용하여 검색해 볼 수 있는 의료영상정보시스템(Medical Image Information System)에 관하여 기술한다. 본 연구를 통하여 개발한 의료영상정보시스템에서는 단층 촬영된 2차원 단면화상을 처리한 다음, 3차원 의료 영상을 생성하기 위하여 표면기반 랜더링 방법(Surface-based Rendering Method)을 사용하였다. 인터넷을 통하여 전송되는 영상파일의 크기를 줄이기 위하여 삼각형 매쉬(Triangle Meshes)을 이루는 다각형의 개수를 줄이는 알고리즘을 사용하며, 3차원 의료영상 데이터의 크기를 약 50%이상 줄일 수 있다. 아울러, 3차원 영상 데이터 파일을 압축을 하게 되면 파일의 크기를 80%이상 줄일 수 가 있으므로 웹상에서 신속하게 3차원 의료영상 데이터를 검색할 수 있고, 의료영상을 VRML을 사용하여 표현하므로 고성능의 그래픽 카드가 없는 일반 PC에서도 인터넷을 통하여 디스플레이 할 수 있다. 또한, CGI(Common Gateway Interface)방식을 사용하여 서버의 데이터베이스에 저장되어 있는 CT(Computerized Tomography), MRI(Magnetic Resonance Imaging), PET(Positron Emission Tomography), SPECT(Single Photon Emission Computed Tomography)등의 단층 촬영 장비로 촬영한 다양한 종류의 디지털 의료영상을 사용자에게 의료영상정보시스템을 통하여 2차원 단면화상 또는 3차원 영상으로 표현하여 보여주고, 환자에 관한 각종 정보와 진단정보 등을 신속하게 제공한다. 본 논문에서 제안하는 의료영상정보시스템은 초고속 정보통신 망을 통하여 원격의료시스템을 구축하는데 활용될 수 있을 것이다.

• 한국정보처리학회논문지
• /
• 제7권3호
• /
• pp.977-991
• /
• 2000

In this paper, a medical image processing system was designed and implemented for morphometric and functional analysis of a human brain. The system is composed of image registration, ROI(region of interest) analysis, functional analysis, image visualization, 3D medical image database management system(DBMS), and database. The software processes an anatomical and functional image as input data, and provides visual and quantitative results. Input data and intermediate or final output data are stored to the database as several data types by the DBMS for other further image processing. In the experiment, the ROI analysis, for a normal, a tumor, a Parkinson's decease, and a depression case, showed that the system is useful for morphometric and functional analysis of a human brain.

• 대한의용생체공학회:의공학회지
• /
• 제15권4호
• /
• pp.475-480
• /
• 1994

For the effective management of medical images, it becomes popular to use computing machines in medical practice, namely PACS. However, the amount of image data is so large that there is a lack of storage space. We usually use data compression techniques to save storage, but the process speed of machines is not fast enough to meet surgical requirement. So a special hardware system processing medical images faster is more important than ever. To meet the demand for high speed image processing, especially image compression and decompression, we designed and implemented the medical image CODEC (COder/DECoder) based on MISD (Multiple Instruction Single Data stream) architecture to adopt parallelism in it. Considering not being a standard scheme of medical image compression/decompression, the CODEC is designed programable and general. In this paper, we use JPEG (Joint Photographic Experts Group) algorithm to process images and evalutate the CODEC.

• 보건행정학회지
• /
• 제24권4호
• /
• pp.367-379
• /
• 2014

Background: Over the last decade, medical tourism industry has grown in Korea. Especially the number of Mongolian medical tourists has increased rapidly. Therefore, the Mongolia is one of the targets for Korea medical tourism. The purpose of this study is to investigate the effects of destination image and expected attributes of medical services on Mongolian's intention to use Korean medical tourism service. Methods: This study empirically collected survey data from Mongolian lived in Mongolia. The study analyzed the data using a PLS model. Results: Our results are as follows. First, the country image didn't significantly have causal effects on expected medical service quality and perceived risk. Second, tourism image (e.g., entertainment, economic feasibility, and local convenience) has significantly causal effects on expected medical service quality and perceived risk. However, tourist site as tourism image didn't significantly have causal effects on expected medical service quality and perceived risk. Third, medical image made a statistically significant effect on expected medical service quality and perceived risk. Fourth, the expected medical service quality showed a significant effect on intention to use Korean medical tourism service. Fifth, the perceived risk of medical tourism showed a significant effect on the reliability of medical tourism, but didn't show a significant effect on the intention to use Korean medical tourism service. Finally, the reliability has a significant effect on the intention to use Korean medical tourism service. Conclusion: From our empirical results, this study concluded that as a strategy attracting Mongolian patients, it is more effective to strengthen Korean hospital image and tourism image than Korean country image.

• 대한의용생체공학회:의공학회지
• /
• 제15권2호
• /
• pp.121-128
• /
• 1994

In this paper, MIlS (Medical Image Information System) has been designed and implemented using INGRES RDBMS, which is based on a client/server architecture. The implemnted system allows users to register and retrieve patient information, medical images and diagnostic reports. It also provides the function to display these information on workstation windows simultaneously by using the designed menu-driven graphic user interface. The medical image compression! decompression techniques are implemented and integrated into the medical image database system for the efficient data storage and the fast access through the network.