http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
복부 컴퓨터 단층촬영영상에서 다중 확률 아틀라스 기반 형상제한 그래프-컷을 사용한 신실질 자동 분할
이재선(Jaeseon Lee),홍헬렌(Helen Hong),나군호(Koon Ho Rha) 한국컴퓨터그래픽스학회 2016 컴퓨터그래픽스학회논문지 Vol.22 No.4
본 논문에서는 복부 CT 영상에서 다중 확률 아틀라스 기반 형상제한 그래프-컷을 사용한 신실질 자동 분할 방법을 제안한다. 제안 방법은 다음의 세 단계로 구성된다. 첫째 신실질의 다양한 형상정보를 이용하기 위해 피질기반 유사정합을 통한 다중 확률 아틀라스를 생성한다. 둘째, 최대사후확률 추정을 통해 그래프-컷의 초기 씨앗을 추출하고, 형상제한 그래프-컷을 통해 신실질을 분할한다. 셋째, 확률 아틀라스의 정합 오차를 줄이고 분할 정확도를 높이기 위해, 정합 및 분할을 반복적으로 수행한다. 제안방법의 성능을 평가하기 위해 정성적 평가 및 정량적 평가를 수행하였다. 실험결과 제안방법이 신실질과 유사한 밝기값을 갖는 주변 영역으로의 누출을 방지하여 개선된 분할 정확도를 보여준다. In this paper, we propose an automatic segmentation method of renal parenchyma on abdominal CT image using graph-cuts with shape constraint based on multi-probabilistic atlas. The proposed method consists of following three steps. First, to use the various shape information of renal parenchyma, multi-probabilistic atlas is generated by cortex-based similarity registration. Second, initial seeds for graph-cuts are extracted by maximum a posteriori (MAP) estimation and renal parenchyma is segmented by graph-cuts with shape constraint. Third, to reduce alignment error of probabilistic atlas and increase segmentation accuracy, registration and segmentation are iteratively performed. To evaluate the performance of proposed method, qualitative and quantitative evaluation are performed. Experimental results show that the proposed method avoids a leakage into neighbor regions with similar intensity of renal parenchyma and shows improved segmentation accuracy.
복부 CT 영상에서 다중 아틀라스 기반 형상 및 밝기값 정보를 사용한 신실질 자동 분할
김현진(Hyeonjin Kim),홍헬렌(Helen Hong),장기돈(Kidon Chang),나군호(Koon Ho Rha) Korean Institute of Information Scientists and Eng 2018 정보과학회논문지 Vol.45 No.9
Renal parenchyma segmentation is necessary to predict contralateral hypertrophy after renal partial nephrectomy. In this paper, we propose an automatic segmentation method of renal parenchyma using shape and intensity information based on the multi-atlas in abdominal CT images. First, similar atlases are selected using volume-based similarity registration and intensity-similarity measure. Second, renal parenchyma is segmented using two-stage registration and constrained intensity-based locally-weighted voting. Finally, renal parenchyma is refined using a Gaussian mixture model-based multi-thresholds and shape-prediction map in under- and over-segmented data. The average dice similarity coefficient of renal parenchyma was 91.34%, which was 18.19%, 1.35% higher than the segmentation method using majority voting and locally-weighted voting in dice similarity coefficient, respectively.
Jee Soo Park(박지수),Won Sik Jang(장원식),Sung Joon Hong(홍성준),Young Deuk Choi(최영득),Koon Ho Rha(나군호),Won Sik Ham(함원식) 대한비뇨기종양학회 2020 대한비뇨기종양학회지 Vol.18 No.1
Purpose: To report an association between prostate cancer and vitamin D levels among different races in a single population in the United States. Materials and Methods: We investigated whether there was an association between vitamin D level and prostate cancer in different races in the United States. We used data collected from 1,363 men during the National Health and Nutrition Examination Survey 2007–2008. Multivariate logistic regression analysis was used to evaluate the independent associations between vitamin D levels (not only 25-hydroxyvitamin D [25(OH)D], but also 25(OH)D2 and D3) and prostate cancer. Association between vitamin D levels and prostate specific antigen level was also analyzed in non-Hispanic white males without prostate cancer. Results: Older age was significantly associated with prostate cancer in all races (p<0.05), whereas vitamin D (p=0.024), especially 25(OH)D2 (p=0.027) was significantly higher only in non-Hispanic white males. There was no difference in vitamin D levels between non-Hispanic white males with a prostate specific antigen concentration >3 ng/mL and ≤3 ng/mL. Conclusions: This study revealed a positive association between vitamin D, especially 25(OH)D2, and prostate cancer only in non-Hispanic white males. And vitamin D was not associated with prostate specific antigen level causing detection bias.