首页> 外文会议>Image Processing pt.3; Progress in Biomedical Optics and Imaging; vol.6 no.24 >Automatic cropping of breast regions for registration in MR mammography
【24h】

Automatic cropping of breast regions for registration in MR mammography

机译:自动裁剪乳房区域以在MR乳腺摄影中进行配准

获取原文
获取原文并翻译 | 示例

摘要

In MR mammography, usually the complete upper part of the body is recorded although for most diagnostic examinations and therapeutic planning only the regions around the breasts are important. This can lead to some disadvantages for automatic processing of images, e.g. higher time consumption and lesser accuracy in image registration. In this paper, we present a straight-forward method for automatic cropping of breast regions for registration in MR mammography. The method starts with processing two-dimensional slices. The result of this first step is statistically analyzed and a cropping-region for three-dimensional volumes is calculated. For each two-dimensional slice, the boundary between breast and air is identified by applying a threshold operator. This boundary describes a bimodal curve; the peaks for the right and left breast and the breastbone are found by searching among the curve's extremal points. An heuristic method analyzes this curve and further yields an estimation of the chest wall boundary to the inner body. For image registration purpose, we compare our proposed automatic cropping method with a simple cropping mechanism that defines the regions of the left and right breasts by reducing the volume to 60 percent from the margin of each side. It is shown that the proposed method works reliably and gives advantages regarding the time-quality tradeoff for automatic image registration in MR mammography.
机译:在MR乳腺摄影中,通常记录整个身体的上部,尽管对于大多数诊断检查和治疗计划而言,仅乳房周围的区域很重要。这会导致自动处理图像的一些缺点,例如耗时较长,图像配准精度较低。在本文中,我们提出了一种自动裁剪乳房区域的简单方法,以便在MR乳腺摄影中进行配准。该方法开始于处理二维切片。对第一步的结果进行统计分析,并计算三维空间的裁剪区域。对于每个二维切片,通过应用阈值运算符来识别乳房和空气之间的边界。该边界描述了双峰曲线。通过在曲线的极点之间进行搜索,可以找到左右乳房和胸骨的峰值。启发式方法分析了该曲线,并进一步得出了到体内的胸壁边界的估计。出于图像配准的目的,我们将我们提出的自动裁剪方法与一种简单的裁剪机制进行了比较,该裁剪机制通过将每侧边缘的体积减小到60%来定义左右乳房的区域。结果表明,所提出的方法工作可靠,并且在MR乳腺摄影中自动图像配准的时间质量权衡方面具有优势。

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