• 한국시뮬레이션학회논문지
• /
• 제18권4호
• /
• pp.197-206
• /
• 2009

의료정보 시스템은 의료영상과 진단정보를 공유할 수 있는 환경을 제공해주는 효과적인 진단 보조 도구이지만 단순히 정보의 저장과 전송만을 제공한다. 이러한 단점을 해결하고 진단활동의 효율성을 높이기 위해서는 의료영상 분류 및 검색 시스템이 필요하다. 의료영상 분류 및 검색 시스템은 질환 영상과 유사한 영상을 제공함으로써 진단활동의 효율성을 높이고, 다양한 사례 확인을 통하여 보다 전문적인 의료활동을 제공할 수 있다. 그러나 기존의 영상 분류 및 검색 시스템은 영상의 표면적인 정보만을 이용하므로 영상이 내포하는 의미를 파악하기 어렵다. 그러므로 영상의 표면적인 정보뿐만 아니라 영상을 구성하는 요소들의 관계를 파악하여 영상을 분류할 수 있는 의료영상 분류 시스템이 필요하다. 본 논문에서 제안한 기법은 뇌 자기공명영상에서 영상의 표면적인 정보와 공간정보를 추출하여 뇌 자기공명영상을 학습하고 분류한다. 영상의 표면적인 정보는 영상 자체가 갖는 색상, 모양 등의 정보로 하위 영상정보라 하고, 영상의 논리정보를 상위 영상정보라 한다. 본 논문에서는 하위 영상정보와 상위 영상정보를 추출할 때 뇌의 해부학적 명칭과 구조를 활용하였다. 하위 영상정보는 뇌 영상의 부분 영역들에 대한 해부학적 명칭을 부여하기 위해 활용되고, 상위 영상정보는 명칭이 부여된 부분 영역들의 관계를 활용하여 정보를 추출한다. 각 정보는 학습과 분류에 사용된다. 실험에서는 질환을 갖는 뇌 자기공명영상을 활용하였다.

• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.1528-1535
• /
• 1997

Many radiological modalities has been applied to medicine as a basic fundamental diagnosis and therapy recently. The prevalence of computer systems affect most images to be digitized. However conventional X-ray film images are not digital images eventhough they covers 70% of all radiologica images. This is the hinderacne of building PACS. In this paper all radiological digital imaging parts such as DSA. CR. MRI. SPECT. PET and ultrasonography were briefly introduced and the applications were described. In brief digital radiography contribute to enhance the medical service quality. And the digital substituition of conventional X-ray film image is inevitable.

• 대한핵의학회지
• /
• 제22권2호
• /
• pp.209-213
• /
• 1988

To Appreciate the value of bone scintigraphy in determination of the bony infection, we performed three phase bone scintigraphy in 34 cases of osteomyelitis of extremities prospectively. They were clinically inactive in 11 and active in 23 cases. We confirmed the active osteomyelitis by operation or aspiration within one week after scintigraphy. Perfusion, blood pool and delayed images were analyzed respectively and compared with the plain roentgenograms. All 23 active lesions showed diffusely increased perfusion in affected limbs. The areas of the increased activities on blood pool images were larger than or similar to those on delayed images in 17 cases (73.9%) with active osteomyelitis and smaller in 6 cases (26.1%). 5 of the latter 6 cases showed definite soft tissue activities on blood pool images. In inactive cases bone scintigrams were completely normal in 4 cases. Two of those were normal on plain films and remaining two showed mild focal bony sclerosis. Among 7 inactive lesions, perfusion was normal in 2 cases, diffusely increased in 4 cases and diffusely decreased in 1 case. 6 of these 7 cases showed increased activities both on blood pool and delayed images and the areas of increased activities on blood pool images didn't exceed those on delayed images. Bony sclerosis was noted on plain films in those 7 inactive lesions and the extent of the sclerosis correlated well to delayed images. Large blood pool activity was characteristics of active osteomyelitis. Normal three phase bone scintigram may indicate the time to terminate the treatment, but increased activity on perfusion and blood pool scans is not absolute indication of active lesion if the extent of the lesion on the blood pool image is smaller than that on delayed image and if no difinite soft tissue activity is noted on perfusion and blood pool images in clinically inactive patient.

• 통합자연과학논문집
• /
• 제8권2호
• /
• pp.141-144
• /
• 2015

As the visual quality of X-ray images is a critical reference for the accuracy of the clinical diagnosis, the methods to improve the quality of X-ray images have been investigated. Among many existing methods, using frequency domain filter is a very powerful method to improve the visual quality of images. In this paper, the inherent noises of the input images are suppressed by adding the Laplacian image to the subjected image. The medical X-ray images using the optimal high pass filter has shown improved edges. Further, the optimal high frequency emphasis filter has shown the improved contrast of flat areas by using the result image from the optimal high pass filter. Also the resulting images of the global contrast have improved by the histogram equalization. As a result, the proposed methods have shown enhanced contrast and edges of the images with noise canceling effect.

• 한국의학물리학회지:의학물리
• /
• 제30권2호
• /
• pp.49-58
• /
• 2019

Purpose: Automated analytical systems have begun to emerge as a database system that enables the scanning of medical images to be performed on computers and the construction of big data. Deep-learning artificial intelligence (AI) architectures have been developed and applied to medical images, making high-precision diagnosis possible. Materials and Methods: For diagnosis, the medical images need to be labeled and standardized. After pre-processing the data and entering them into the deep-learning architecture, the final diagnosis results can be obtained quickly and accurately. To solve the problem of overfitting because of an insufficient amount of labeled data, data augmentation is performed through rotation, using left and right flips to artificially increase the amount of data. Because various deep-learning architectures have been developed and publicized over the past few years, the results of the diagnosis can be obtained by entering a medical image. Results: Classification and regression are performed by a supervised machine-learning method and clustering and generation are performed by an unsupervised machine-learning method. When the convolutional neural network (CNN) method is applied to the deep-learning layer, feature extraction can be used to classify diseases very efficiently and thus to diagnose various diseases. Conclusions: AI, using a deep-learning architecture, has expertise in medical image analysis of the nerves, retina, lungs, digital pathology, breast, heart, abdomen, and musculo-skeletal system.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권3호
• /
• pp.1167-1187
• /
• 2020

With the development of medical imaging technology, image registration has been widely used in the field of disease diagnosis. The registration between different modal images of brain magnetic resonance (MR) is particularly important for the diagnosis of brain diseases. However, previous registration methods don't take advantage of the prior knowledge of bilateral brain symmetry. Moreover, the difference in gray scale information of different modal images increases the difficulty of registration. In this paper, a multimodal medical image registration method based on image segmentation and symmetric self-similarity is proposed. This method uses modal independent self-similar information and modal consistency information to register images. More particularly, we propose two novel symmetric self-similarity constraint operators to constrain the segmented medical images and convert each modal medical image into a unified modal for multimodal image registration. The experimental results show that the proposed method can effectively reduce the error rate of brain MR multimodal medical image registration with rotation and translation transformations (average 0.43mm and 0.60mm) respectively, whose accuracy is better compared to state-of-the-art image registration methods.

• Journal of Multimedia Information System
• /
• 제8권2호
• /
• pp.79-84
• /
• 2021

Detecting brain tumors of different sizes is a challenging task. This study aimed to identify brain tumors using detection algorithms. Most studies in this area use segmentation; however, we utilized detection owing to its advantages. Data were obtained from 64 patients and 11,200 MR images. The deep learning model used was RetinaNet, which is based on ResNet152. The model learned three different types of pre-processing images: normal, general histogram equalization, and contrast-limited adaptive histogram equalization (CLAHE). The three types of images were compared to determine the pre-processing technique that exhibits the best performance in the deep learning algorithms. During pre-processing, we converted the MR images from DICOM to JPG format. Additionally, we regulated the window level and width. The model compared the pre-processed images to determine which images showed adequate performance; CLAHE showed the best performance, with a sensitivity of 81.79%. The RetinaNet model for detecting brain tumors through deep learning algorithms demonstrated satisfactory performance in finding lesions. In future, we plan to develop a new model for improving the detection performance using well-processed data. This study lays the groundwork for future detection technologies that can help doctors find lesions more easily in clinical tasks.

• Journal of Korean Neurosurgical Society
• /
• 제62권4호
• /
• pp.476-486
• /
• 2019

Objective : The functional information of $^{11}C$-methionine positron emission tomography (MET-PET) images can be applied for Gamma knife radiosurgery (GKR) and its image quality may affect defining the tumor. This study conducted the phantom-based evaluation for geometric accuracy and functional characteristic of diagnostic MET-PET image co-registered with stereotactic image in Leksell $GammaPlan^{(R)}$ (LGP) and also investigated clinical application of these images in metastatic brain tumors. Methods : Two types of cylindrical acrylic phantoms fabricated in-house were used for this study : the phantom with an array-shaped axial rod insert and the phantom with different sized tube indicators. The phantoms were mounted on the stereotactic frame and scanned using computed tomography (CT), magnetic resonance imaging (MRI), and PET system. Three-dimensional coordinate values on co-registered MET-PET images were compared with those on stereotactic CT image in LGP. MET uptake values of different sized indicators inside phantom were evaluated. We also evaluated the CT and MRI co-registered stereotactic MET-PET images with MR-enhancing volume and PET-metabolic tumor volume (MTV) in 14 metastatic brain tumors. Results : Imaging distortion of MET-PET was maintained stable at less than approximately 3% on mean value. There was no statistical difference in the geometric accuracy according to co-registered reference stereotactic images. In functional characteristic study for MET-PET image, the indicator on the lateral side of the phantom exhibited higher uptake than that on the medial side. This effect decreased as the size of the object increased. In 14 metastatic tumors, the median matching percentage between MR-enhancing volume and PET-MTV was 36.8% on PET/MR fusion images and 39.9% on PET/CT fusion images. Conclusion : The geometric accuracy of the diagnostic MET-PET co-registered with stereotactic MR in LGP is acceptable on phantom-based study. However, the MET-PET images could the limitations in providing exact stereotactic information in clinical study.