• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.268-270
• /
• 2006

본 논문에서는 3차원 볼륨영상에서 객체를 빠르게 분할하고 동시에 대화식으로 분할과정을 가시화하기 위하여 그래픽 하드웨어를 사용한 레벨-셋 방법을 제안한다. 이를 위하여 첫째, GPU 내에서 효율적 연산을 수행하기 위해 메모리 관리방법을 제안한다. 이는 GPU 내 텍스쳐 메모리 형식에 적합하게 데이터를 패킹하고, CPU의 주메모리와 GPU의 텍스쳐 메모리를 관리하는 방법을 제시한다. 둘째, GPU 내에서 레벨-셋 값을 갱신하는 과정을 9가지 경우로 나누어 연산을 수행하게 함으로써 연산의 효율성을 높힌다. 셋째, front의 변화를 대화식으로 확인하고, 파라미터 변경에 따른 분할 과정을 효과적으로 측정하기 위하여 그래픽 하드웨어 기반 빠른 가시화 방법을 제안한다. 본 논문에서는 제안방법을 평가하기 위하여 3차원 폐 CT 영상데이터를 사용하여 육안평가를 수행하고, 기존 소프트웨어 기반 레벨-셋 방법과 수행시간 측면에서 비교 분석한다. 본 제안방법은 소프트웨어 기반 레벨-셋 방법보다 빠르게 영상을 분할하고 동시에 가시화함으로써 데이터 량이 많은 의료응용에 효율적으로 적용이 가능하다.

• Journal of Biomedical Engineering Research
• /
• v.18 no.4
• /
• pp.349-356
• /
• 1997

In this paper, we propose the lossless coding: scheme for progressive transmission of medical images. The input image is decomposed by the proposed fast adaptive subband decomposition method which is suited for a lossless coding. The decomposed images are coded by an arithmetic coder with two conditioning pixels, and the conditioning pixels are selected differently according to the property of the subbands. The conditioning contexts are usually quantized to reduce the conditional state, and the optimization method of quantization is proposed For the purpose of improving compression ratio in this paper. The proposed lossless coding scheme provides the asymmetric structure of cosec and results in better compression ability than the JPEC lossless coding[ 1 ].

• Journal of Biomedical Engineering Research
• /
• v.20 no.2
• /
• pp.149-154
• /
• 1999

In anatomical aspects, magnetic resonance image offers more accurate information than other medical images such as X ray, ultrasonic and CT images. This paper introduces a method that segments and detects lesion for 2 dimensional axial MR brain images automatically. Image segmentation process consists of 2 stages. First stage extracts cerebrum region using thresholding and morphology. In the second stage, white matter, gray matter and cerebrospinal fluid in the cerebrum are extracted using FCM, We could improve processing time as removing uninterested region. Finally symmetry measure and anatomical Knowledge are used to detect lesion.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.705-707
• /
• 2022

인체의 흉부 X-ray 영상으로부터 척추질환과 관련된 의료 진단지표를 자동으로 추출하는 과정을 위하여 흉추조직의 정확한 분할이 필요하다. 본 연구에서는 HRNet 기반의 학습을 통하여 흉추조직을 분할하는 방법을 고찰한다. 분할 과정에서 영상 내의 상대적인 위치 정보가 효과적으로 반영될 수 있도록, 계층별로 영상의 고해상도의 표현이 그대로 유지되는 구조와 저해상도의 특징 지도로 변환되는 구조가 병렬적으로 연결되는 형태의 심층 신경망 모델을 채택하였다. 흉부 X-ray 영상에서 콥각도(Cobb's angle)를 산출하는 문제를 대상으로 흉추 분할을 위한 학습 방법, 진단지표 추출 방법 등을 소개하며, 부수적으로 피사체의 위치 변화 및 크기 변화 등에 강인한 성능을 제공하기 위하여 학습 데이터를 증강하는 방법론을 제시하였다. 총 145개의 영상을 사용한 실험을 통하여 제안된 이론의 타당성을 평가하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.4
• /
• pp.567-574
• /
• 2006

This paper focuses on lossy medical image compression methods for medical images that operate on three-dimensional(3-D) irreversible integer wavelet transform. We offer an application of unbalanced tree structure algorithm to medical images, using a 3-D unbalanced wavelet decomposition and a 3-D unbalanced spatial dependence tree. The wavelet decomposition is accomplished with integer wavelet filters implemented with the lifting method. We have tested our encoder on volumetric medical images using different integer filters and 16 coding unit size. The coding unit sizes of 16 slices save considerable dynamic memory(RAM) and coding delay from full sequence coding units used in previous works. If we allow the formation of trees of different lengths, then we can accomodate more transaxial scales than three. Then the encoder and decoder can then keep track of the length of the tree in which each pixel resides through the sequence of decompositions. Results show that, even with these small coding units, our algorithm with I(5,3)filter performs as well and better in lossy coding than previous coding systems using 3-D integer unbalanced wavelet transforms on volumetric medical images.

• Journal of Biomedical Engineering Research
• /
• v.19 no.2
• /
• pp.189-198
• /
• 1998

3D medical image reconstruction techniques are useful to figure out complex 3D structures from the set of 2D sections. In the paper, 3D medical image reconstruction system is constructed under PC environment and programmed based on modular programming by using Visual C++ 4.2. The whole procedures are composed of data preparation, gradient estimation, classification, shading, transformation and ray-casting & compositing. Three speed optimization techniques are used for accelerating 3D medical image reconstruction technique. One is to reduce the rays when cast rays to reconstruct 3D medical image, another is to reduce the voxels to be calculated and the other is to apply early ray termination. To implement 3D medical image reconstruction system based on PC, speed optimization techniques are experimented and applied.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.8
• /
• pp.1765-1772
• /
• 2012

Success rate of transplantation of body organs improved due to development of medical equipment and diagnostic technology. In particular, a liver transplant due to liver dysfunction has increased. With the development of image processing and analysis to obtain the volume for liver transplantation have increased the accuracy and efficiency. In this thesis, we try to reconstruct the regions of the liver within three dimensional images using the mevislab tool, which is effective in quick comparison and analysis of various algorithms, and in expedient development of prototypes. Liver is divided by applying threshold values and region growing method to the original image, and by removing noise and unnecessary entities through morphology and region filling, and setting of areas of interest. It is deemed that high temporal efficiency, and presentation of diverse range of comparison and analysis module application methods through usage of MeVisLab would make contribution towards expanding of baseline of medical image processing researches.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.51-58
• /
• 2023

In this paper, we propose an organ segmentation technique for the automatic extraction of medical diagnostic indicators from X-ray images. In order to calculate diagnostic indicators of heart disease and spinal disease such as VHS(vertebral heart scale) and Cobb angle, it is necessary to accurately segment the thoracic spine, carina, and heart in a chest X-ray image. A deep neural network model in which the high-resolution representation of the image for each layer and the structure converted into a low-resolution feature map are connected in parallel was adopted. This structure enables the relative position information in the image to be effectively reflected in the segmentation process. It is shown that learning performance can be improved by combining the OCR module, in which pixel information and object information are mutually interacted in a multi-step process, and the channel attention module, which allows each channel of the network to be reflected as different weight values. In addition, a method of augmenting learning data is presented in order to provide robust performance against changes in the position, shape, and size of the subject in the X-ray image. The effectiveness of the proposed theory was evaluated through an experiment using 145 human chest X-ray images and 118 animal X-ray images.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.7
• /
• pp.487-494
• /
• 2013

Medical image watermarking has received extensive attention as wide security services in the healthcare information system. This paper proposes a blind medical image watermarking approach on the segmented gray-matter (GM) images by utilizing discrete wavelet transform (DWT) and discrete cosine transform (DCT) along with enhanced suppressed fuzzy C-means (EnSFCM) for the optimal selection of sub-blocks position to insert a watermark. Experimental results show that the proposed approach outperforms other methods in terms of peak signal to noise ratio (PSNR) and M-SVD. In addition, the proposed approach shows better robustness than other methods in normalized correlation (NC) values against several attacks, such as noise addition, filtering, JPEG compression, blurring, histogram equalization, and cropping.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.460-463
• /
• 2003

의료영상에서의 혈관의 분할은 심혈관계질환의 진단 및 시술을 위한 3차원 가시화 및 가상내시경을 하기위한 필수 선행 단계로 이에 대한 연구가 많이 이루어 지고 있다. 조영제를 투여한 환자의 CT데이터에서 혈관분할의 가장 큰 문제점은 혈관의 밝기값이 뼈의 밝기값과 비슷하기 때문에 기존의 3차원 SRG방법으로 분할하는 경우 새나감의 문제를 가지고 있었다. 본 논문에서는 Cubic SRG라는 방법을 통해 기존의 3차원 SRG가 가지는 깔끔한 분할결과와 적응적인 특성등의 여러 장점을 그대로 취하며 Cubic이라는 구조적 특징을 이용하여 혈관을 빠르고 강인하게 분할하는 방법을 제안한다. Cubic SRG는 SRG가 픽셀단위의 성장을 통해 동질 영역을 분할하는 방법을 사용함에 반해 Cubic이라는 부피 단위를 지정하여 이를 SRG의 픽셀과 같이 퍼트리는 방식으로 기존의 3차원 SRG에 비해 2$\sim$5배 정도의 빠른 수행속도를 보이며 3차원 SRG의 장점인 적응적인 특성을 그대로 가질수 있도륵 구현되었다. 또한 복셀들을 Cubic이라는 단위로 묶음으로서 혈관의 구조적인 분석을 수행하여 혈관을 트리형태의 구조로 그룹화가 가능하기 때문에 혈관을 가지별로 분할하기에 용이한 특징을 가지도록 하였으며, 이를 통해 새나감이 시작된 가지를 찾아서 잘라내는 방법을 통하여 SRG의 가장 큰 문제인 새나감 방법을 효과적으로 해결하는 방법을 제시한다. 최종적으로 위의 방법을 기본으로 하여 적응형 임계값 기반의 분할 방법을 혼합하여 사용자가 지정한 두 지점사이의 혈관을 강인하게 분할할수 있도록 구현하였고, 제안한 방법으로 여러 환자의 CT데이터에 실험하여 좋은 결과를 얻을 수 있었다.