...
首页> 外文期刊>Multidimensional systems and signal processing >A tool supported approach for brightness preserving contrast enhancement and mass segmentation of mammogram images using histogram modified grey relational analysis
【24h】

A tool supported approach for brightness preserving contrast enhancement and mass segmentation of mammogram images using histogram modified grey relational analysis

机译:使用直方图修改灰色关系分析,支持亮度保留对比度增强和乳房X线图像图像质量分割方法的工具

获取原文
获取原文并翻译 | 示例
           

摘要

Mammography is a tool that uses X-rays to create mammograms. This tool is mainly used to find early signs of breast cancer. Usually, mammogram image contains region with low contrast and complicated structured background. This may cause difficulties in detection of infected cells in their early stage. Using contrast enhancement of mammogram image we can increase the detection rate of early breast cancer. In this paper we propose a tool supported method named histogram modified grey relational analysis, based on HE with local contrast enhancement for mammogram images. This method enhances local as well as global contrast of given mammogram image and segments breast region in order to obtain better visual interpretation, analysis, and classification of mammogram masses to assist radiologists in making more accurate decisions. The main contribution of this work is to show that better breast-region segmentation results can be achieved from simple breast-region segmentation method if the input image has sufficient contrast with good interpretation of local details. We tested proposed method for MIAS mammogram images. To evaluate effectiveness of proposed method we choose three widely used metrics absolute mean brightness error, structural similarity index measure and peak signal to noise ratio for all 322 images of MIAS mammogram images database.
机译:乳房X线照相术是一种使用X射线来创建乳房X线照片的工具。该工具主要用于寻找乳腺癌的早期迹象。通常,乳房X线图图像包含具有低对比度和复杂结构背景的区域。这可能导致在早期检测感染细胞的困难。使用乳房X线照片的对比度增强我们可以提高早期乳腺癌的检出率。在本文中,我们提出了一种名为直方图修改灰色关系分析的工具支持的方法,基于乳房X线图图像的局部对比度增强。该方法增强了当地的乳房X线照片图像和区段乳房区域的全局对比,以获得乳房X线照片群众的更好的视觉解释,分析和分类,以帮助放射科医师制定更准确的决策。这项工作的主要贡献是表明,如果输入图像具有足够的对照局部细节,则可以从简单的乳房区域分割方法实现更好的乳房区域分割结果。我们测试了用于MIS乳房X光图的提出方法。为了评估所提出的方法的有效性,我们选择三个广泛使用的度量绝对平均亮度误差,结构相似性指标测量和峰值信号对MIS乳房XMMICK图像数据库的所有322个图像的噪声比。

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