基于边缘流的改进梯度矢量流算法及其在淋巴结超声图像分割中的应用.pdfVIP

第19 卷 第3 期 航天医学与医学工程 Vol. 19 No. 3 2006 年 6 月 Space Medicine Medical Engineering Jun. 2006 基于边缘流的改进梯度矢量流算法及其在淋巴结超声图像 分割中的应用* 1，2 1 2 3 3 张俊华 ，汪源源 ，施心陵 ，董 怡 ，王 怡 （1. 复旦大学电子工程系，上海 200433 ；2 . 云南大学电子工程系，云南昆明650091；3 . 复旦大学附属华山医院，上海 200040 ） 摘要：目的提出一种基于边缘流的梯度矢量流（gradient vector flow ，GV F ）形变模型的图像分割方 法，并用于淋巴结超声图像的分割。方法 综合图像灰度和纹理特征构造边缘流，使每点的边缘流矢量 指向最近的边缘，再由边缘流扩散得到GV F 场作为形变模型的外部势力，引导模型形变实现图像分割。 结果 在给定4 个标记点的条件下，实现了对淋巴结超声图像的半自动分割。结论 将边缘流引入GV F 将明显改善对低对比度超声图像的分割效果。 关键词：梯度矢量流；边缘流；医学超声图像；图像分割 TP391；R319 文献标识码：A 文章编号：1002-0837 （2006 ）03-0212-05 中图分类号： An Imp roved Gradient Vector Flow （GVF ）Snake Model f or Lymp hatic Ultrasonic Image Segmentation Based on Edge Flow. ZHANG Jun- hua ，Wang Yuan-yuan，SHI Xin- ling ，DONG Yi，WANG Yi. Space Medicine Medical Engineering ，2006 ，19 （3 ）：212 ~ 216 Abstract ：Objective To put forward an improved gradient vector flow （GV F）snake model based on the edge flow for segmentation of medical ultrasonic images of the lymph node. Method An edge flow vector was constructed at each pixel location basing on the integration of image intensity and texture characteristics to make the edge flow vector point to the direction of potential boundary pix- els. The GV F field obtained by the diffusion of the edge flow vector was regarded as the external potential force of the snake model. Then the curve propagation was guided by the improved GV F snake model. Result A semi- automatic segmentation of ultrasonic images of the lymph node was accomplished under the condition that the four marks were provided by an expert . Conclusion By the integration of the edge flow into the GV F snake model，the segmentation Ouality is obviously im- proved for low contrast ultrasonic images. Key words ：gradient vector flow