...
首页> 外文期刊>電子情報通信学会技術研究報告. 医用画像. Medical Imaging >A segmentation method for CT images of livers based on entropy minimization of pixel density distribution
【24h】

A segmentation method for CT images of livers based on entropy minimization of pixel density distribution

机译:基于像素密度分布熵最小化的肝脏CT图像分割方法

获取原文
获取原文并翻译 | 示例
           

摘要

We propose an image segmentation method based on gradient of pixel intensity in CT images of livers and show some experimental results. Image segmentation for tumors in CT images of libers based on edge detection is difficult, because difference of pixel intensity between tumors and other regions is small compared with cases in other organs, and because tumors in liver contains mosaic structure. In order to improves the traditional segmentation method based on minimization of entropy CT pixel intensity, we define a three-dimensional density distribution of pixels composed of x, y-axis and axis of CT intensity. By minimizing this density distribution, we can obtain segments whose thresholds are determined based on gradient of boundary of tumors in various positions.
机译:我们提出了一种基于像素强度梯度的肝脏CT图像图像分割方法,并显示了一些实验结果。由于边缘与其他器官相比,肿瘤与其他区域之间的像素强度差异较小,并且肝脏中的肿瘤包含镶嵌结构,因此基于边缘检测的解放者CT图像中的肿瘤图像很难分割。为了改进基于最小熵CT像素强度的传统分割方法,我们定义了由x,y轴和CT强度轴组成的三维像素密度分布。通过最小化这种密度分布,我们可以获得基于各种位置的肿瘤边界梯度确定其阈值的片段。

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