• Journal of Biomedical Engineering Research
• /
• v.8 no.1
• /
• pp.81-86
• /
• 1987

An image feature extraction method for the low contrast fluoresceln angiogram in dlabetes was studied. To obtain effective image segmentation, an adaptive local difference image is generated and relaxation process are applied to this difference Image. By the use of distance transformed data with segmented image, shape and location of feature regions were obtained. It was shown that the location and shape descriptions of Impaired blood vessel networks and retinal regions are can he utilized for the diagnosis of diabetes and other disease.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.7
• /
• pp.536-546
• /
• 2003

We propose an object extraction technique adequate for the radial shape's radar signal structure for the purpose of implementing ARPA(Automatic Radar Plotting Aid) installed in the vessel. The radar signal data are processed by interpolation and accumulation to acquire a qualified image. The objects of the radar image have characteristics of having different shape and size as it gets far from the center, and it is not adequate for clustering generally. Therefore, this study designs a new vigilance distance model of elliptical shape and adopts this model in the ART2 neural network. We prove that the proposed clustering method makes it possible to extract objects adaptively and to separate the connected objects effectively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.04a
• /
• pp.414-416
• /
• 2012

본 논문에서는 X-선 혈관 조영 영상 내 심혈관의 추출 방법을 제안한다. 본 방법은 불균일 조명 보정 필터를 사용함으로써 X-선 영상 내에서 나타나는 일정하지 않은 contrast, 낮은 명암도 및 불균일 조명 문제를 해결한다. 또한 영상의 지역적인 밝기 값의 변화의 특징을 고려하면서 분할 대상영역의 각 픽셀들의 2 차 미분((second partial derivation)을 행렬의 요소(element)로 갖는 Hessian 행렬의 고유치 (eigenvalue)를 영역확장의 문턱치 결정에 이용하여 전역적인 밝기값(intensity)만을 사용하는 분할의 단점을보완하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.397-398
• /
• 2019

망막혈관 영상에서(retinal image) 혈관의 모양 또는 생성변화를 효과적으로 검진하기 위해서 망막혈관을 자동적으로 분리하는 영상분할 기법의 개발은 매우 중요한 사안이다. 이를 위해서 주로 망막혈관영상의 잡음을 억제하고 또한 혈관의 명암대비도(contrast)를 증가시키는 전처리 과정을 거쳐서 혈관의 국부적인 화소값의 변화, 방향성을 판별하여 혈관을 자동적으로 검출하는 방법들이 제시되어왔으며 최근에는 합성곱 신경망(CNN) 딥러닝 학습모델을 활용한 망막혈관 분리 알고리즘들이 제시되고 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.819-822
• /
• 2005

본 연구는 MDCT 영상을 이용하여 인체의 장기인 간을 추출하고 그 간 내부의 혈관을 추출하는 알고리즘을 제안하였다. 간에는 2개의 주요혈관이 있는데 생체 간 이식 수술시 필수적인 간의 절개 비율 및 간 내의 혈관 모습들을 제공하여 의료진에게 수술 전 혈관 형태에 대한 정확히 정보를 파악하도록 함으로써 혈관의 손상을 최대한으로 줄일 수 있도록 하여 수술 성공률을 높이는데 중요한 역할을 할 수 있다. 간을 이식 할 때 기증자와 수혜자가 동시에 생존하기 위해서는 기증자의 간으 크기가 중요하며 둘다 생존하기 위해서는 기증자는 자신의 간의 35% 이상을 남겨야 하며 수혜자 또한 생존을 위해 자신의 간의 40% 이상에 해당하는 간을 이식 받아야 하는데 간 이식에 있어서 절단 부분을 결정하는데 중요한 중간 정맥을 찾아내어 보여 줌으로써 중간 정맥을 중심으로 3가닥의 굵은 혈관과 주변혈관의 손상을 최소화하고 비율을 잘 맞추어 절단 할 수 있도록 수술하는데 도움을 줄 수 있다. 각 혈관은 원형성과 다양한 각도를 갖는 막대형의 형태를 가지고 있다는 특징을 이용해 morphological filtering을 통해 추출한 후 조합하여 재구성을 하여 혈관의 모습으로 생성해 낼 수 있었다.

• Journal of the Korean Society of Radiology
• /
• v.12 no.3
• /
• pp.435-441
• /
• 2018

In this study, we performed to design an image guiding algorithm to improve the efficiency and safety of treatment of varicose vein by focused ultrasound. The algorithm was suggested by different guiding images according to the location of varicose veins. In the case of deep-seated varicose veins, the target area was marked on the surface of the blood vessel in the obtained cross-sectional blood vessel ultrasound image. In the case of the superficial varicose vein, A guiding system based on image segmentation algorithm of the vascular region was suggested and designed two different algorithms according to varicose veins progression degree. as a results, the algorithm based on ultrasound image show a small error with $830{\mu}m$ at maximum. However, the algorithm based on charge coupled device image has a maximum error of 8.3 mm in some data. Therefore, it is expected that additional study is needed for superficial varicose vein image guiding algorithm, and it is expected that the accuracy of blood vessel tracking should be evaluated by constructing simple system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.423-430
• /
• 2013

Recently, the personal identification technologies using vein pattern of back of the hand, palm, and finger have been developed actively because it has the advantage that the vein blood vessel in the body is impossible to damage, make a replication and forge. However, it is difficult to extract clearly the vein region from captured vein images through common image prcessing based region segmentation method, because of the light scattering and non-uniform internal tissue by skin layer and inside layer skeleton, etc. Especially, it takes a long time for processing time and makes a discontinuity of blood vessel just in a image because it has non-uniform illumination due to use a locally different adaptive threshold for the binarization of acquired finger-vein image. To solve this problem, we propose illumination normalization based fast method for extracting the finger-vein region. The proposed method has advantages compared to the previous methods as follows. Firstly, for remove a non-uniform illumination of the captured vein image, we obtain a illumination component of the captured vein image by using a low-pass filter. Secondly, by extracting the finger-vein path using one time binarization of a single threshold selection, we were able to reduce the processing time. Through experimental results, we confirmed that the accuracy of extracting the finger-vein region was increased and the processing time was shortened than prior methods.

• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.700-707
• /
• 2013

In this paper, we propose a non-rigid registration method of lung parenchyma in temporal chest CT scans using region binarization modeling and locally deformable model. To cope with intensity differences between CT scans, we segment the lung vessel and parenchyma in each scan and perform binarization modeling. Then, we match them without referring any intensity information. We globally align two lung surfaces. Then, locally deformable transformation model is developed for the subsequent non-rigid registration. Subtracted quantification results after non-rigid registration are visualized by pre-defined color map. Experimental results showed that proposed registration method correctly aligned lung parenchyma in the full inspiration and expiration CT images for ten patients. Our non-rigid lung registration method may be useful for the assessment of various lung diseases by providing intuitive color-coded information of quantification results about lung parenchyma.

• Journal of radiological science and technology
• /
• v.39 no.4
• /
• pp.543-547
• /
• 2016

Acute stroke is a one of common disease that require fast diagnosis and treatment to save patients life. however, the acute stroke may cause lifelong disability due to brain damage with no prompt surgical procedure. In order to diagnose the Stroke, brain perfusion CT examination and possible rapid implementation of 3D angiography has been widely used. However, a low-dose technique should be applied for the examination since a lot of radiation exposure to the patient may cause secondary damage for the patients. Therefore, the degradation of the measured CT images may interferes with a clinical check in that blood vessel shapes on the CT image are significantly affected by gaussian noise. In this study, we employed the spatio-temporal technique to analyze dynamic (brain perfusion) CT data to improve an image quality for successful clinical diagnosis. As a results, proposed technique could remove gaussian noise successfully, demonstrated a possibility of new image segmentation technique for CT angiography. Qualitative evaluation was conducted by skilled radiological technologists, indicated significant quality improvement of dynamic CT images. the proposed technique will be useful tools as a clinical application for brain perfusion CT examination.