Novel Stochastic Framework for Accurate Segmentation of Prostate in Dynamic Contrast Enhanced MRI

机译：用于动态对比增强MRI的前列腺精确分割的新型随机框架

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Prostate segmentation is an essential step in developing any non-invasive Computer-Assisted Diagnostic (CAD) system for the eaxly diagnosis of prostate cancer using Dynamic Contrast Enhancement Magnetic Resonance Images (DCE-MRI). In this paper we propose a novel approach for segmenting the prostate region from DCE-MRI based on using a graph cut framework to optimize a new energy function consists of three descriptors: (i) 1st-order visual appearance descriptors of the DCE-MRI; (ii) a spatially invariant 2nd-order homogeneity descriptor, and (iii) a prostate shape descriptor. The shape prior is learned from a subset of co-aligned training images. The visual appearances are described with marginal gray level distributions obtained by separat ing their mixture over the image. The spatial interactions between the prostate pixels are modeled by a 2nd-order translation and rotation invariant Markov-Gibbs random field of object / background labels with analytically estimated potentials. Experiments with prostate DCE-MR images confirm robustness and accuracy of the proposed approach.

机译：前列腺分割术是开发使用动态对比增强磁共振图像（DCE-MRI）进行前列腺癌的早期诊断的任何非侵入性计算机辅助诊断（CAD）系统的重要步骤。在本文中，我们提出了一种新的方法，该方法基于图切割框架来优化新的能量函数，从而从DCE-MRI分割前列腺区域，该方法包括三个描述符：（i）DCE-MRI的一阶视觉外观描述符；（ii）空间不变的2阶均匀性描述子，以及（iii）前列腺形状描述子。从共同对准的训练图像的子集中学习形状先验。通过将边缘混合在图像上分离获得的边缘灰度分布来描述视觉外观。前列腺像素之间的空间相互作用通过对象/背景标签的具有分析估计电位的二阶平移和旋转不变马尔可夫-吉布斯随机场进行建模。前列腺DCE-MR图像的实验证实了该方法的鲁棒性和准确性。

著录项

来源
《Prostate cancer imaging : Computer-aided diagnosis, prognosis, and intervention》|2010年|p.121-130|共10页
会议地点 Beijing(CN);Beijing(CN)
作者
Ahmad Firjany; Ahmed Elnakib; Ayman El-Baz; Georgy Gimelfarb; Mohamed Abo El-Ghar; Adel Elmaghraby;
展开▼
作者单位

Bioimaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY, USA,Department of Computer Engineering Computer Science,University of Louisville, Louisville, KY, USA;

Bioimaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY, USA;

Bioimaging Laboratory, Bioengineering Department, University of Louisville, Louisville, KY, USA;

Department of Computer Science, University of Auckland, Auckland, New Zealand;

Urology and Nrphrology Department, University of Mansoura, Mansoura, Egypt;

Department of Computer Engineering Computer Science,University of Louisville, Louisville, KY, USA;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类医用物理学;计算技术、计算机技术;
关键词

相似文献

外文文献
中文文献
专利

1. Model-free prostate cancer segmentation from dynamic contrast-enhanced MRI with recurrent convolutional networks: A feasibility study [J] . Peter Q. Lee, Alessro Guida, Steve Patterson, Computerized Medical Imaging and Graphics: The Official Jounal of the Computerized Medical Imaging Society . 2019,第期

机译：动态对比增强MRI的无模型前列腺癌细分与经常性卷积网络：可行性研究
2. Accurate estimation of pharmacokinetic contrast-enhanced dynamic MRI parameters of the prostate. [J] . Huisman HJ, Engelbrecht MR, Barentsz JO Journal of magnetic resonance imaging: JMRI . 2001,第4期

机译：前列腺的药代动力学对比增强动态MRI参数的准确估算。
3. Comparison of arterial input functions measured from ultra-fast dynamic contrast enhanced MRI and dynamic contrast enhanced computed tomography in prostate cancer patients [J] . Wang Shiyang, Lu Zhengfeng, Fan Xiaobing, Physics in medicine and biology. . 2018,第3期

机译：从超快速动态对比度测量的动脉输入函数的比较增强的MRI和动态对比增强了前列腺癌患者的计算断层扫描
4. Novel Stochastic Framework for Accurate Segmentation of Prostate in Dynamic Contrast Enhanced MRI [C] . Ahmad Firjany, Ahmed Elnakib, Ayman El-Baz, International Workshop on Prostate Cancer Imaging . 2010

机译：新型随机框架，用于动态对比增强MRI中前列腺前列腺分割
5. A computerized image analysis framework for dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) with applications to breast cancer. [D] . Agner, Shannon Christine. 2011

机译：动态对比增强磁共振成像（DCE-MRI）的计算机图像分析框架，并应用于乳腺癌。
6. Automatic Prostate Cancer Segmentation Using Kinetic Analysis in Dynamic Contrast-Enhanced MRI [O] . S. Navaei Lavasani, A. Mostaar, M. Ashtiyani 2018

机译：动态对比增强MRI中使用动力学分析的前列腺癌自动分割
7. Comparison of arterial input functions measured from ultra-fast dynamic contrast enhanced MRI and dynamic contrast enhanced computed tomography in prostate cancer patients [O] . Shiyang Wang, Zhengfeng Lu, Xiaobing Fan, 2018

机译：从超快速动态对比度测量的动脉输入函数的比较增强的MRI和动态对比增强了前列腺癌患者的计算断层扫描
8. Interventional MRI Technique for the Molecular Characterization of Heterogeneous Intra-Prostatic Dynamic Contrast Enhancement [R] . Menard, C., Susil, R. C., Choyke, P., 2004

机译：非均匀性前列腺动态对比增强的分子表征介入mRI技术

Novel Stochastic Framework for Accurate Segmentation of Prostate in Dynamic Contrast Enhanced MRI

摘要

著录项

相似文献

相关主题

期刊订阅