华东师范大学学报(自然科学版)
華東師範大學學報(自然科學版)
화동사범대학학보(자연과학판)
2008年
1期
60-67
,共8页
CT图像%结节分割%实质性结节%亚实质性结节%CI特征%均值平移算法
CT圖像%結節分割%實質性結節%亞實質性結節%CI特徵%均值平移算法
CT도상%결절분할%실질성결절%아실질성결절%CI특정%균치평이산법
CT images%nodule segmentation%solid nodule%sub-solid nodule%CI feature%mean shift algorithm
提出了一种有效的分割CT图像中肺结节的新算法.该算法采用均值平移(mean shift)算法和基于CI(Convergence Index, CI)特征,共由三个步骤组成:(1)计算感兴趣区内的所有像素的CI特征;(2)把CI特征与像素的灰度值和空间位置信息结合在一起,形成3-域特征向量集;(3)利用均值平移聚类算法对特征向量集进行聚类.由于该算法能有效分析多高斯模型描述的包括实质性结节和亚实质性结节在内的所有结节,因此,可应用于CT图像中任何含有结节的用户感兴趣区域.实验结果证明,该方法能更精确地分割出不同类型的结节.
提齣瞭一種有效的分割CT圖像中肺結節的新算法.該算法採用均值平移(mean shift)算法和基于CI(Convergence Index, CI)特徵,共由三箇步驟組成:(1)計算感興趣區內的所有像素的CI特徵;(2)把CI特徵與像素的灰度值和空間位置信息結閤在一起,形成3-域特徵嚮量集;(3)利用均值平移聚類算法對特徵嚮量集進行聚類.由于該算法能有效分析多高斯模型描述的包括實質性結節和亞實質性結節在內的所有結節,因此,可應用于CT圖像中任何含有結節的用戶感興趣區域.實驗結果證明,該方法能更精確地分割齣不同類型的結節.
제출료일충유효적분할CT도상중폐결절적신산법.해산법채용균치평이(mean shift)산법화기우CI(Convergence Index, CI)특정,공유삼개보취조성:(1)계산감흥취구내적소유상소적CI특정;(2)파CI특정여상소적회도치화공간위치신식결합재일기,형성3-역특정향량집;(3)이용균치평이취류산법대특정향량집진행취류.유우해산법능유효분석다고사모형묘술적포괄실질성결절화아실질성결절재내적소유결절,인차,가응용우CT도상중임하함유결절적용호감흥취구역.실험결과증명,해방법능경정학지분할출불동류형적결절.
A novel and more effective algorithm used for segmenting pulmonary nodules in CT images was presented. The algorithm is based on mean shift clustering method and CI (Convergence Index) features, which can represent the multiple Gaussian model of pulmonary nodules both for solid and sub-solid, substantially. The algorithm has three steps: (1) calculating the CI feature of every pixel in the region of interest (ROI); (2) combining the CI feature with the intensity range and the spatial position of each pixel to form a feature vector set; (3) grouping all feature vector sets into different cluster with mean shift clustering algorithm. Owing to our algorithm can represents the multiple Gaussian model both for solid and sub-solid nodules, it can be used in any interesting nodule regions, especially suitable for the segmentation of sub-solid nodules. Experiments demonstrated that our algorithm can figure out the outline of pulmonary nodules of different forms more precisely.
