首页> 外文会议>ICCE 2011;International Conference on informatics, cybernetics, and computer engineering >A Novel Segmentation Method for Breast Cancer Ultrasound CAD System
【24h】

A Novel Segmentation Method for Breast Cancer Ultrasound CAD System

机译:乳腺癌超声CAD系统分割的新方法

获取原文

摘要

Ultrasound is one of the most often used methods for breast cancer detection because it's harmless and low cost. However, tumor segmentation is very difficult in ultrasound images due to their specular nature and low quality of ultrasound images. In this paper, we employ a novel method for breast ultrasound (BUS) image segmentation using fuzzy logic. An US image is transformed into fuzzy domain by using s-function and maximum fuzzy entropy principle, and enhanced by fuzzy intensifying function. An iterative method is used to find threshold, then US image is converted to binary image on which a segmentation method is applied to get the final tumor boundary. The experiments show that our approach can process low quality ultrasound image very well.
机译:超声是乳腺癌检测最常用的方法之一,因为它是无害的和低成本。然而,由于其镜面性质和低质量的超声图像,肿瘤分割非常困难。在本文中,我们采用了一种使用模糊逻辑的乳房超声(总线)图像分割的新方法。通过使用S函数和最大模糊熵原理,通过模糊强化功能来转换为模糊域的模糊域。使用迭代方法来查找阈值,然后将US图像转换为施加分段方法以获得最终肿瘤边界的二进制图像。实验表明,我们的方法可以很好地处理低质量的超声图像。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号