软件学报
軟件學報
연건학보
JOURNAL OF SOFTWARE
2013年
8期
1927-1936
,共10页
解立志%周明全%田沄%武仲科%王醒策
解立誌%週明全%田沄%武仲科%王醒策
해립지%주명전%전운%무중과%왕성책
脑血管分割%二维OTSU%区域增长%局部自适应C-V模型
腦血管分割%二維OTSU%區域增長%跼部自適應C-V模型
뇌혈관분할%이유OTSU%구역증장%국부자괄응C-V모형
cerebrovascular segmentation%2D OTSU%region growing%local adaptive C-V model
提出了一种针对TOF MRA(time-of-flight magnetic resonance angiography)磁共振图像的双重分割脑血管提取方法。首先结合高斯滤波,采用二维OTSU算法,结合MIP(maximum intensity projection)图像获得三维血管种子点,定义全局与局部信息相结合的区域增长规则,通过区域增长算法对血管进行粗分割;然后,采用 Catt 扩散模型对体数据场进行各向异性滤波,提出了局部自适应C-V模型,将初步分割结果作为自适应活动轮廓模型的初始轮廓线进行二次分割。实验结果表明,该算法不仅能够有效分割脑血管粗大分支,而且还能精确提取脑血管的细小结构。
提齣瞭一種針對TOF MRA(time-of-flight magnetic resonance angiography)磁共振圖像的雙重分割腦血管提取方法。首先結閤高斯濾波,採用二維OTSU算法,結閤MIP(maximum intensity projection)圖像穫得三維血管種子點,定義全跼與跼部信息相結閤的區域增長規則,通過區域增長算法對血管進行粗分割;然後,採用 Catt 擴散模型對體數據場進行各嚮異性濾波,提齣瞭跼部自適應C-V模型,將初步分割結果作為自適應活動輪廓模型的初始輪廓線進行二次分割。實驗結果錶明,該算法不僅能夠有效分割腦血管粗大分支,而且還能精確提取腦血管的細小結構。
제출료일충침대TOF MRA(time-of-flight magnetic resonance angiography)자공진도상적쌍중분할뇌혈관제취방법。수선결합고사려파,채용이유OTSU산법,결합MIP(maximum intensity projection)도상획득삼유혈관충자점,정의전국여국부신식상결합적구역증장규칙,통과구역증장산법대혈관진행조분할;연후,채용 Catt 확산모형대체수거장진행각향이성려파,제출료국부자괄응C-V모형,장초보분할결과작위자괄응활동륜곽모형적초시륜곽선진행이차분할。실험결과표명,해산법불부능구유효분할뇌혈관조대분지,이차환능정학제취뇌혈관적세소결구。
This paper presents an effective approach to extract cerebrovascular tree from time-of-flight (TOF) magnetic resonance angiography (MRA) images. The approach consists of two segmentation stages. In the first stage, Gaussian filtering is implemented for the 3D volumetric field. By virtue of the maximum intensity projection (MIP) image segmented by the two dimensional OTSU algorithm, 3D vessel seeds are obtained. The region growing rule is defined by combining the global information with the local information, and then the rough segmentation is implemented by the region growing algorithm. In second stage, the original volume data is filtered by an anisotropic filtering based on Catt diffusion. A local adaptive C-V model is proposed, and the initial contour of the model is set by employing the first segmented vessels. Then the accurate segmentation is realized by the contour evolution. Experimental results show that the proposed algorithm is not only able to effectively segment the thick vessel, but also able to accurately extract the thinner vessels with weak boundaries.