• Proceedings of the IEEK Conference
• /
• 2001.06e
• /
• pp.73-76
• /
• 2001

A segmentation is a prior processing for medical image analysis and 3D reconstruction. This Paper provides the method to segment 3D Visible Human color images. Firstly, the reference images that have a initial curve are segmented using Balloon and the results are propagated to the adjacent images. In the propagation processing, the result of the adjacent slice is modified by Edge-limited SRG Finally, the 3D Balloon improves the segmentation results of each 2D slice. the proposed method's performance was verified through the experiments to segment thigh muscles of Visible Human color images.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.271-274
• /
• 2001

미국의 National Library of Medicine에서 제공하는 Visible human 컬러영상을 이용하여, 신체 장기의 3차원 모델링 및 가시화 하기 위한 영역 분할 방법 연구가 활발히 진행되고 있다. 특히 다른 신체 장기 분할에 비해 뼈분할은 주위의 영역들과 모호한 경계를 지니고 있어 컬러영상만을 가지고 구분해 내기가 쉽지 않다. 이러한 문제점을 해결하기 위해 본 논문에서는 Visible human CT영상을 가지고 뼈 영역을 분할하고 분할 된 뼈 영역의 경계를 추출하여 그 경계를 컬러영상의 최적화된 위치로 변환해 최종적인 뼈 영역 분할을 시도한다. 제안된 방법은 Visible human 단면영상의 머리부분에 적용하여 좋은 결과를 얻음을 실험을 통해 효율성을 검증하였다.

• Journal of KIISE:Software and Applications
• /
• v.30 no.7_8
• /
• pp.719-726
• /
• 2003

This paper proposes a multimodal registration method for segmentation of the Visible Human color images, in which color characteristics of bones are very similar to those of its surrounding fat areas. Bones are initially segmented in CT images, and then registered into color images to lineate their boundaries in the color images. For the segmentation of bones in CT images, a thresholding method is developed. The registration method registers boundaries of bodies in CT and color images using a cross-correlation approach, in which the boundaries of bodies are extracted by thresholding segmentation methods. The proposed method has been applied to segmentation of bones in a head and legs whose boundary is ambiguous due to surrounding fat areas with similar color characteristics, and produced promising results.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.19 no.6
• /
• pp.1483-1490
• /
• 2005

This study was written in order to help understanding of visible diagnosis of appearance(形). Visible diagnosis of appearance(形) is a very important factor of diagnosis and a first step of visible diagnosis. appearance(形) is closely connection with spirit(神), so is house of spirit(神). If we make a visible diagnosis of appearance(形), we know the prosperousness of energy and the relative seriousness of an illness. Spirit(神) is understood by appearances and movements of patient, and influenced by seasons, lands, human's relationship and the grade of age. By visible diagnosis of appearance(形), we can conclude existence or nonexistence of spirit(神), As comparing spirit(神) with appearance(形), we can decide good or bad prognoses. One man's own appearance(形) is determined by the five human type(五形人). There are very various points of changing form. As divided into principal groups, there are three main groups, that is, sky(天), earth(地) and man(人). The age and sex belong 治 the factor of sky(天), a direction and configuration of the ground(地形) belong to the factor of earth(地), the five human type(五形人) and white fatness(肥白) and black emaciation(黑瘦) belong to the factor of man(人).

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.308-315
• /
• 2003

This paper proposes an approach integrating multiple segmentation methods in a systematic way, which can improve overall accuracy without deteriorating accuracy of highly confident segments of boundaries generated by constituent methods. A segmentation method produces boundary segments, which are then evaluated with an evaluation function considering pros/cons of the current and next methods to apply. Boundary segments with low confidence are replaced by a next method while the other segments are kept. These steps are repeated until all segmentation methods are applied. The proposed approach is implemented for the segmentation of muscles in the Visible Human color images. A Balloon method, a minimum cost path finding method, and a Seeded Region Growing method are integrated. The final segmentation results showed improvements in both overall evaluation and segment-based evaluation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.268-270
• /
• 2003

국내에서의 의료영상에 관한 관심도가 높아짐에 따라 Visible Korean Human Project가 시작되었다. 이를 통해 얻어진 해부영상들의 다양한 응용을 위해 분할작업은 필수적 단계로 이를 분할하기 위한 도구가 필요하다. 그러나 분할해야할 기관들의 종류가 많고 그 특성이 다양해서 기존의 분할도구로 적용하기에 많은 문제점이 나타나 새로운 분할도구개발의 필요성이 나타났다. 새로운 분할도구에서는 각 기관의 특성 에 알맞은 다양한 방법의 분할 방범을 제공하여 분할방법에 따라 다른 분할결과를 통합적으로 표현하여 보다 용이한 처리를 가능하도록 설계되었다. 구현된 분할 도구는 반자동 분할 방법과 슬라이스간 전달 방법을 사용하여 보다 적은 사용자의 입력으로도 빠른 시간에 많은 양의 데이터를 분할 할 수 있도록 자동화 설계되었으며, 자동적으로 분할된 결과가 사용자의 의도와 다른 경우 설계 편집할 수 있는 기능도 제공하도록 구현했다. 구현된 분할도구를 통해 Visible Korean Human Dataset의 분할 실험을 했으며 기존의 분할 도구에 비해 이르고 정확한 결과를 얻어 낼 수 있었다.

• Proceedings of the Korea Contents Association Conference
• /
• 2008.05a
• /
• pp.819-822
• /
• 2008

As the IT and computer network technology is developed very rapidly, the quantity of digital contents is increased and disseminated more widely. The digital contents is generally expressed in 2 or 3 dimensional multimedia format and the visible human image that is taken from human body is very important because of its variety of usefulness. The KISTI(Korea Institute of Science and Technology Information) is now constructing various Korean human informations such as visible Korean, digital Korean, human bone property and human models. These informations are accessable through the internet. However, these human images are not easily understandable for general users because they are specialized in medical image field and there is no detailed explanation data. In this study, we designed the annotation database and searching interface for KISTI's visible Korean database. This annotation database involved the detailed explanation and special note of visible Korean data and it can connect the image and text data of visible Korean with each other. By studying this database and interface design, the KISTI's visible Korean database is more easily accessable and understandable to general users and it can promote the usage of visible Korean data more widely.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.265-267
• /
• 2003

해부학적 구조의 변형이 존재하는 신체 부위를 정합하기 위하여 연구되는 non-rigid 정합 방법은 현재 의료 영상 분야에서 매우 중요한 주제이고 많은 연구가 이루어지고 있다. 본 논문에서는 Visible Human Color 단면 영상과 CT영상 사이에 존재하는 다리 모양의 변형을 정합 하기 위하여 계층적인 non-rigid 정합 방법을 제안하였다. 제안한 계층적 정합 방법은 영역 경계를 이용한 global rigid 정합으로 초기 변형 벡터를 찾고. 정합 할 영역을 sampling하여 local non-rigid 정합을 수행 한 후 결과를 interpolation하여 전체 영역에 대한 최종 정합 벡터를 계산하였다. 결과적으로 더욱 효율적이고 강력한 non-rigid 정합 결과를 얻을 수 있었다.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.18 no.4
• /
• pp.976-981
• /
• 2004

This study was written in order to help understanding of visible diagnosis of spirit(神). Visible diagnosis of spirit(神) is a very important factor of diagnosis and a first step of visible diagnosis. Spirit(神) is closely connection with appearance(形), so is revealed by appearance(형). If we make a visible diagnosis of spirit(神), we know the prosperousness of energy and the relative seriousness of an illness. Spirit(神) is understood by appearances and movements of patient, and influenced by seasons, lands, human's relationship and the grade of age. Visible diagnosis of spirit(神) is practiced by the observation of movements, appearances, languages, voices, mental condition, color, eye, etc. By visible diagnosis of spirit(神), we can conclude existence or nonexistence of spirit(神), discriminate true spirit(神) from false spirit(神), and diagnose mental diseases. As comparing spirit(神) with appearance(形), we can decide good or bad prognoses.

• Journal of KIISE:Software and Applications
• /
• v.27 no.3
• /
• pp.266-274
• /
• 2000

Medical image segmentation, which is essential in diagnosis and 3D reconstruction, is performed manually in most applications to produce accurate results. However, manual segmentation requires lots of time to segment, and is difficult even for the same operator to reproduce the same segmentation results for a region. To overcome such limitations, we propose a convenient and accurate semiautomatic segmentation method. The proposed method initially receives several control points of an ROI(Region of Interest Region) from a human operator, and then finds a boundary composed of a minimum cost path connecting the control points, which is the Live-wire method. Next, the boundary is modified to overcome limitations of the Live-wire, such as a zig-zag boundary and erosion of an ROI. Finally, the region is segmented by SRG(Seeded Region Growing), where the modified boundary acts as a blockage to prevent leakage. The proposed User-steered balloon method can overcome not only the limitations of the Live-wire but also the leakage problem of the SRG. Segmentation results of thigh muscles of the Visible Human are presented.