http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
오늘 본 자료
-
寒熱虛實 辨證 診斷 설문지의 개발에 대한 연구
-
Anatomical knowledge of zygomatico-buccal plexus in a cadaveric study
-
Environmental transformations in developing countries
-
회원사 소식
-
신선식품 유통 사이트에서 제품 정보품질과 정보원천 신뢰성이 제품환기에 미치는 영향
-
Bitter taste receptors protect against skin aging by inhibiting cellular senescence and enhancing wound healing
- 검색키워드
- 저자 : Heungkook Choi (검색결과 4 건)
- 무료
- 기관 내 무료
- 유료
-
SURFACE TEXTURE ANALYSIS FOR 3D SHAPE ESTIMATION OF CELL NUCLEI IN NUCLEAR GRADING
Hyunju Choi,Taeyun Kim,Uno Tak,Haegil Hwang,Heungkook Choi 한국멀티미디어학회 2007 한국멀티미디어학회 국제학술대회 Vol.2007 No.-
Objective: To find surface texture descriptors for estimating 3D shape of cell nuclei in nuclear grading of renal cell carcinoma and evaluate the feasibility of such quantitative analysis. Methods: After surface rendering, the surfaces of 3D cell nuclei consist of triangle meshes. Our method is based on the relationship between the normal vectors of adjacent triangles. In order to derive the relationship of them, we computed angles between adjacent normal vectors and made an angle feature histogram. Based on this feature histogram, we defined surface texture descriptors and evaluated their significance in nuclear grading. Results and Conclusion: We found a statistically significant correlation between nuclear grade and surface texture descriptors of cell nuclei. It means that surface texture descriptors can be important diagnostic factors to improve the accuracy of grading renal cell carcinoma.
-
COMPUTERIZED QUANTIFICATION OF TISSUE VASCULARIZATION
HyunJu Choi,TaeYun Kim,HaeGil Hwang,HeungKook Choi 한국멀티미디어학회 2006 한국멀티미디어학회 국제학술대회 Vol.2006 No.-
This paper presents a computerized image analysis method for quantifying tissue vascularization. The segmentation task was based on a supervised learning scheme. First, 12 color features (RGB, HSI, I₁I₂I₃, and L<SUP>*</SUP>a<SUP>*</SUP>b<SUP>*</SUP>) were extracted from a training set. The feature selection procedure selected I₂L<SUP>*</SUP>S features as the best color feature vector. Then, we segmented microvessels using the discriminant function made using the minimum error rate classification rule of Bayesian decision theory. In the quantification step, after applying a connected component-labeling algorithm, microvessels with discontinuities were connected and touching microvessels were separated. We tested the proposed method on 23 images. The result was evaluated by comparing it with manual quantification of the same images. The comparison revealed that our computerized microvessel counting was highly correlated with manual counting by an expert (r = 0.95754). The association between the number of microvessels after the initial segmentation and manual quantification was also assessed using Pearson's correlation coefficient (r = 0.71187). The results indicate that our method is better than the conventional computerized image analysis methods.
-
Slice 정보에 기반한 3차원 볼륨 데이타의 레이블링 알고리즘
최익환(Ikhwan Choi),최현주(Hyunju Choi),이병일(Byeongil Lee),최흥국(Heungkook Choi) 한국정보과학회 2004 정보과학회논문지 : 소프트웨어 및 응용 Vol.31 No.7
본 논문에서는 볼륨데이타에서의 레이블링(labeling)을 위한 알고리즘을 제안하고자한다. 3차원 볼륨은 2차원 슬라이스 데이타의 연속으로 보고 각 슬라이스의 레이블링 정보를 바탕으로 하는 SIL(Slice Information based Labeling)방법을 제안한다. 이는 기존의 알고리즘에 비해 효율적인 메모리 사용이 가능하고 분석하고자 하는 데이타의 특성에 맞는 2차원 레이블링과의 조합이 가능한 장점이 있다. 기존 알고리즘과 제안하는 방법을 3차원 세포영상에서 비교하여 보았으며, SIL을 2차원 레이블링 CCCL(Contour based Connected Component Labeling)과 함께 볼륨데이타에 적용하여 본 결과 기존의 알고리즘 보다 약 2배 빠른 성능을 보였다. 다양한 3차원 레이블링 방법 중 적용되는 영상에 따라 각기 다른 결과를 얻었지만, 3차원 세포영상의 분석에서는 SIL 방법이 우수하다는 결론을 얻었다. We propose a new 3 dimensional labeling method based on slice information for the volume data. This method is named SIL (Slice Information based Labeling). Compare to the conventional algorithms, it has advantages that the use of memory is efficient and it is possible to combine with a variety of 2 dimensional labeling algorithms for finding an appropriate labeling algorithm to its application. In this study, we applied SIL to confocal microscopy images of cervix cancer cell and compared the results of labeling. According to the measurement, we found that the speed of SIL combined with CCCL (Contour based Connected Component Labeling) is almost 2 times higher than that of other methods. In conclusion, considering that the performance of labeling depends on a kind of image, we obtained that the proposed method provide better result for the confocal microscopy cell volume data.
-
Surface Texture Analysis of Cell Nuclei using 3D Reconstruction
Tak, YoonO,Choi, HyunJu,Kim, TaeYun,Choi, HeungKook 인제대학교 2008 仁濟論叢 Vol.23 No.1
To find surface texture descriptors for estimating 3D shape of cell nuclei in nuclear grading of renal cell carcinoma and evaluate the feasibility of such quantitative analysis. Mehods: After surface rendering. the surfaces of 3D cell nuclei consist of triangle meshes. Our method is based on the relationship between the normal vectors of adjacent triangles. In order to derive the relationship of them, we computed angles between adjacent normal vectors and made an angle feature histogram. Based on this feature histogram, we defined surface texture descriptors and evaluated their significance in nuclear grading. Results and Conclusion: We found a statistically significant correlation between nuclear grade and surface texture descriptors of cell nuclei. It means that surface texture descriptors can be important diagnostic factors to improve the accuracy of grading renal cell carcimma.
ScienceON연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
