• Journal of Biomedical Engineering Research
• /
• v.22 no.2
• /
• pp.127-132
• /
• 2001

의료 영상에서 관심 있는 부위를 3차원으로 재구성하여 보는 것은, 정확한 진단을 위해서 매우 중요하다. 이러한 3차원 재구성을 위해서는 관심 있는 영역의 분할이 필수적인 선행작업이다. 본 논문에서는 관도계 기관의 분할을 위해서 슬라이스 영상의 정보를 이용한 3차원 영역 성장법을 제안한다. 제안된 방법은 2차원 슬라이스 영상에서 영역 성장법에 의해 영역을 확장시키고, 그 이웃한 슬라이스들에 씨앗점을 전달하여 재귀적으로 3차원 체적을 확장하여 영상을 분할한다. 이때, 이웃한 슬라이스간의 영역의 크기의 제약을 이용하여 새나감을 방지한다. 제안된 방법을 기관지의 분할에 적용한 결과, 새나감 없이 뾰족한 가지들까지도 성공적으로 분할했으며, 튜브의 중심 축이 고차원 곡선인 경우에도 성공적으로 분할했다.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.267-274
• /
• 2023

There is a problem that the size of the dataset is insufficient due to the limitation of the collection of the medical image public data, so there is a possibility that the existing studies are overfitted to the public dataset. In this paper, we compare the performance of eight (Unet, X-Net, HarDNet, SegNet, PSPNet, SwinUnet, 3D-ResU-Net, UNETR) medical image semantic segmentation models to revalidate the superiority of existing models. Anatomical Tracings of Lesions After Stroke (ATLAS) V1.2, a public dataset for stroke diagnosis, is used to compare the performance of the models and the performance of the models in ATLAS V2.0. Experimental results show that most models have similar performance in V1.2 and V2.0, but X-net and 3D-ResU-Net have higher performance in V1.2 datasets. These results can be interpreted that the models may be overfitted to V1.2.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.123-131
• /
• 2019

In this study, we modified CT images of femoral head in consideration of anatomically meaningful structure, proposing the method to augment the training data of convolution Neural network for segmentation of femur mesh model. First, the femur mesh model is obtained from the CT image. Then divide the mesh model into meaningful parts by using cluster analysis on geometric characteristic of mesh surface. Finally, transform the segments by using an appropriate mesh deformation algorithm, then create new CT images by warping CT images accordingly. Deep learning models using the data enhancement methods of this study show better image division performance compared to data augmentation methods which have been commonly used, such as geometric conversion or color conversion.

• 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.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.643-646
• /
• 2000

의료 영상에서 관심 있는 부위를 3차원으로 재구성 하여 보는 것은, 정확한 진단을 위해서 매우 중요하다. 이러한 3차원 재구성을 위해서는 관심 있는 영역의 분할이 필수적인 선행작업이다. 본 논문에서는 3차원적 정보를 이용한 영상 분할 방법으로 슬라이스 기반의 3차원 영역 확장법을 제안한다. 제안된 방법은 2차원 슬라이스 영상에서 영역 성장법에 의해 영역을 확장시키고, 그 이웃한 슬라이스들에 씨앗을 전달하여 재귀적으로 3차원 영역을 확장하여 영상을 분할한다. 이때, 이웃한 슬라이스 간의 영역의 크기를 이용하여 새나감을 방지한다. 제안된 방법을 튜브 형태의 기관의 분할에 적용한 결과, 새나감 없이 뽀족한 가지들까지도 성공적으로 분할 했으며, 튜브의 중심 축이 고차원 곡선인 경우에도 성공적으로 분할했다.

• The KIPS Transactions:PartA
• /
• v.13A no.5 s.102
• /
• pp.465-472
• /
• 2006

Recently, many suggestions have been made in image segmentation methods for extracting human organs or disease affected area from huge amounts of medical image datasets. However, images from some areas, such as brain, which have multiple structures with ambiruous structural borders, have limitations in their structural segmentation. To address this problem, clustering technique which classifies voxels into finite number of clusters is often employed. This, however, has its drawback, the influence from noise, which is caused from voxel by voxel operations. Therefore, applying image enhancing method to minimize the influence from noise and to make clearer image borders would allow more robust structural segmentation. This research proposes an efficient structural segmentation method by filtering based clustering to extract detail structures such as white matter, gray matter and cerebrospinal fluid from brain MR. First, coherence enhancing diffusion filtering is adopted to make clearer borders between structures and to reduce the noises in them. To the enhanced images from this process, fuzzy c-means clustering method was applied, conducting structural segmentation by assigning corresponding cluster index to the structure containing each voxel. The suggested structural segmentation method, in comparison with existing ones with clustering using Gaussian or general anisotropic diffusion filtering, showed enhanced accuracy which was determined by how much it agreed with the manual segmentation results. Moreover, by suggesting fine segmentation method on the border area with reproducible results and minimized manual task, it provides efficient diagnostic support for morphological abnormalities in brain.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.119-126
• /
• 2023

Sarcopenia is not well known enough to be classified as a disease in 2021 in Korea, but it is recognized as a social problem in developed countries that have entered an aging society. The diagnosis of sarcopenia follows the international standard guidelines presented by the European Working Group for Sarcopenia in Older People (EWGSOP) and the d Asian Working Group for Sarcopenia (AWGS). Recently, it is recommended to evaluate muscle function by using physical performance evaluation, walking speed measurement, and standing test in addition to absolute muscle mass as a diagnostic method. As a representative method for measuring muscle mass, the body composition analysis method using DEXA has been formally implemented in clinical practice. In addition, various studies for measuring muscle mass using abdominal images of MRI or CT are being actively conducted. In this paper, we develop an AI image segmentation model based on abdominal images of CT with a relatively short imaging time for the diagnosis of sarcopenia and describe the multicenter validation. We developed an artificial intelligence model using U-Net that can automatically segment muscle, subcutaneous fat, and visceral fat by selecting the L3 region from the CT image. Also, to evaluate the performance of the model, internal verification was performed by calculating the intersection over union (IOU) of the partitioned area, and the results of external verification using data from other hospitals are shown. Based on the verification results, we tried to review and supplement the problems and solutions.

• 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.

• The Journal of the Korea Contents Association
• /
• v.14 no.3
• /
• pp.11-21
• /
• 2014

Multi-scale image segmentation is important in many applications such as image stylization and medical diagnosis. This paper proposes a novel segmentation algorithm based on MSER(maximally stable extremal region) which captures multi-scale structure and is stable and efficient. The algorithm collects MSERs and then partitions the image plane by redrawing MSERs in specific order. To denoise and smooth the region boundaries, hierarchical morphological operations are developed. To illustrate effectiveness of the algorithm's multi-scale structure, effects of various types of LOD control are shown for image stylization. The proposed technique achieves this without time-consuming multi-level Gaussian smoothing. The comparisons of segmentation quality and timing efficiency with mean shift-based Edison system are presented.

• Journal of Korea Multimedia Society
• /
• v.3 no.4
• /
• pp.339-346
• /
• 2000

Medical image is analyzed to get an anatomical information for diagnostics. Segmentation must be preceded to recognize and determine the lesion more accurately. In this paper, we propose automatic segmentation algorithm for MR brain images using T1-weighted, T2-weighted and PD images complementarily. The proposed segmentation algorithm is first, extracts cerebrum images from 3 input images using cerebrum mask which is made from PD image. And next, find 3D clusters corresponded to cerebrum tissues using scale filtering and 3D clustering in 3D space which is consisted of T1, T2, and PD axis. Cerebrum images are segmented using FCM algorithm with its initial centroid as the 3D cluster's centroid. The proposed algorithm improved segmentation results using accurate cluster centroid as initial value of FCM algorithm and also can get better segmentation results using multi spectral analysis than single spectral analysis.