利用自适应纹理分布的活动形状分割前列腺磁共振图像

汪源源; 原宗良; 唐三

doi:10.3788/OPE.20132109.2371

您当前的位置：

首页 >

文章列表页 >

利用自适应纹理分布的活动形状分割前列腺磁共振图像

信息科学 | 更新时间：2020-08-12

- 利用自适应纹理分布的活动形状分割前列腺磁共振图像
- Segmentation of prostate magnetic resonance image with active shape of adaptive texture distribution
- 光学精密工程 2013年21卷第9期页码：2371-2380
- 作者机构：
  
  复旦大学电子工程系，上海 200433
- 作者简介：
- 基金信息：
  
  高等学校博士学科点专项科研基金(20136101110019)
- DOI：10.3788/OPE.20132109.2371
  中图分类号： Q-334;TP391.4
- 收稿日期：2013-03-12，
  
  修回日期：2013-04-25，
  
  网络出版日期：2013-09-30，
  
  纸质出版日期：2013-09-15
- 稿件说明：
移动端阅览
汪源源原宗良唐三. 利用自适应纹理分布的活动形状分割前列腺磁共振图像[J]. 光学精密工程, 2013,21(9): 2371-2380

WANG Yuan-yuan YUAN Zong-liang TANG San. Segmentation of prostate magnetic resonance image with active shape of adaptive texture distribution[J]. Editorial Office of Optics and Precision Engineering, 2013,21(9): 2371-2380
汪源源原宗良唐三. 利用自适应纹理分布的活动形状分割前列腺磁共振图像[J]. 光学精密工程, 2013,21(9): 2371-2380 DOI： 10.3788/OPE.20132109.2371.

WANG Yuan-yuan YUAN Zong-liang TANG San. Segmentation of prostate magnetic resonance image with active shape of adaptive texture distribution[J]. Editorial Office of Optics and Precision Engineering, 2013,21(9): 2371-2380 DOI： 10.3788/OPE.20132109.2371.

摘要

基于前列腺磁共振图像性质，提出利用自适应纹理分布的活动形状图像分割方法来自动分割前列腺磁共振图像。该方法首先通过图像的分类与拟合确定感兴趣的腺体区域，同时估计若干形状参数用于分割过程中调整形状；然后融入多重纹理信息，建立纹理一致测度，将传统的活动形状按照自适应的纹理判别步骤细分为纹理分布形状与补充形状，提高活动形状的搜索匹配能力。在搜索匹配部分，利用已估计参数优化活动形状搜索的初始估计，并根据纹理分布形状和补充形状调整迭代过程。实验结果表明，该方法分割出来的前列腺轮廓与金标准的Hausdorff距离为6.00 pixel，分割精度为93%。该方法对活动形状的改进是有效的，利用自适应纹理分布的活动形状能够自动、准确地将前列腺从磁共振图像中分割出来。

Abstract

On the basis of properties of magnetic resonance images for the prostate

an active shape image segmentation method making use of adaptive texture distribution was introduced to segment a prostate magnetic resonance image. Firstly

a prostate region of interest was determined through image classification and image fitting

and several shape parameters were estimated and used in the segmentation. Then

multi-features were fused to build a texture coincidence measure. In order to improve the searching and matching ability of an active shape

the active shape was divided into two portions

the texture distribution shape and the supplementary shape. In search

the estimated parameters were used to optimize the initial estimation of the active shape searching and adjust the iterative process based on the texture distribution shape and the supplementary shape. Experimental results indicate that the Hausdorff Distance is 6.00 pixels between the true prostate contour and that extracted by the proposed method and the segmentation accuracy of the method is 93%. The proposed method can modify the active shape effectively

and can automatically segment the prostate magnetic resonance images with high enough accuracy.

关键词

Keywords

references

Prostate cancer incidence statistics[EB/OL].(2013-01-22) [2013-03-05]http://www.cancerresearchuk.org/cancer-info/cancerstats/types/prostate/incidence/. [2]HALPERN E J, COCHLIN D L, GOLDBERG B B. Imaging of the Prostate[M]. 1st ed.UK: Informa Healthcare, 2002.[3]PUECH P, BETROUNI N, MAKNI N, et al.. Computer-assisted diagnosis of prostate cancer using DCE-MRI data: design, implementation and preliminary results[J]. International Journal of Computer Assisted Radiology and Surgery, 2009, 4(1): 1-10.[4]GHOSE S, OLIVE A, MARTI R, et al.. A survey of prostate segmentation methodologies in ultrasound, magnetic resonance and computed tomography images[J]. Computer Methods and Programs in Biomedicine, 2012, 108(1): 262-287.[5]JOLESZ F, NABAVI A, KIKINIS R. Integration of interventional MRI with computer-assisted surgery[J]. Journal of Magnetic Resonance Imaging, 2001, 13(1): 69-77.[6]SAMIEE M, THOMAS G, FAZEL-REZAI R. Semi-automatic prostate segmentation of MR images based on flow orientation [C]. IEEE International Symposium on Signal Processing and Information Technology, USA, 2008: 203-207.[7]FLORES-TAPIA D, THOMAS G, VENUGOPAL N, et al.. Semi automatic MRI prostate segmentation based on wavelet multiscale products [C]. 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, USA, 2008: 3020-3023.[8]VIKAL S, HAKER S, TEMPANY C, et al.. Prostate contouring in MRI guided biopsy[C]. Proceedings of SPIE Medical Imaging, USA, 2009: 7259-7266.[9]KLEIN S, HEIDE U A, LIPPS IM, et al.. Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information[J]. Medical Physics, 2008, 35(4): 1407-1417.[10]DOWLING J, FRIPP J, CHANDRA S, et al.. Fast automatic multi-atlas segmentation of the prostate from 3D MR images [J]. IEEE Transactions on Medical Imaging, 2010, 29(12): 2000-1008.[11]ALLEN P D, GRAHAM J, WILLIAMSON D C, et al.. Differential segmentation of the prostate in MR images using combined 3D shape modeling and voxel classification[C]. 3rd IEEE International Symposium on Biomedical Imaging, USA, 2006: 410-413.[12]ZHANG Y, MATUSZEWSKI B J, HISTANCE F, et al.. Boundary delineation in prostate imaging using active contour segmentation method with interactively defined object regions [J]. Prostate Cancer Imaging, 2010, 6367: 131-142.[13]TSAI A, YEZZI J A, WELLS W, et al.. A shape-based approach to the segmentation of medical imagery using level sets [J]. IEEE Transactions on Medical Imaging, 2003, 22(2): 137-154.[14]TOTH R, TIWARI P, ROSEN M, et al.. A magnetic resonance spectroscopy driven initialization scheme for active shape model based prostate segmentaion [J]. Medical Image Analysis, 2011, 15(1):214-255.[15]张麒, 汪源源, 王威琪, 等. 活动轮廓模型和Contourlet多分辨率分析分割血管内超声图像[J]. 光学精密工程, 2008, 16(11): 2303-2313.ZHANG Q, WANG Y Y, WANG W Q, et al.. Intravascular ultrasound image segmentation based on active contour model and Contourlet multiresolution analysis[J]. Opt. Precision Eng., 2008, 16(11): 2303-2313. (in Chinese)[16]张广才, 付宜利, 王树国, 等. T2加权人脑MR体数据的脑提取[J]. 光学精密工程, 2011, 19(7): 1635-1644.ZHANG G C, FU Y L, WANG S G, et al.. Human brain extraction from T2 weighted volumetric magnetic resonance images[J]. Opt. Precision Eng., 2011, 19(7): 1635-1644. (in Chinese)[17]COOTES T F, HILL A, TAYLOR C J, et al.. The use of active shape model for locating structures in medical images[J]. Image and Vision Computing, 1994, 12(6):355-366.[18]LAWS K I. Textured image segmentation [R]. University of Southern California Los Angeles Image Processing INST, 1980.[19]OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Trans. on Systems, Man and Cybernetic, 1979, 9(1): 62-66.[20]金炜, 俞建定, 符冉迪, 等. 双树轮廓波变换域的磁共振图像降噪[J]. 光学精密工程, 2010, 18(3): 756-765.JIN W, YU J D, FU R D, et al.. Magnetic resonance image denoising in dual-tree Contourlet transform domain[J]. Opt. Precision Eng., 2010, 18(3): 756-765. (in Chinese)[21]WALTER G, GOLUB G H, ROLF S. Least-squares fitting of circles and ellipses[J]. BIT Numerical Mathematics, 1994, 34(4): 558-578.

浏览量

110

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合条形注意力机制的电芯极片计算机断层图像分割

增强型金枪鱼群优化指数熵的砂粒显微图像分割

语义流引导采样结合注意力机制的脑肿瘤图像分割

混沌SSA优化多重熵阈值的骨料图像自动分割

基于高分辨率复合网络的皮肤病变分割