Probability density difference-based active contour for ultrasound image segmentation

被引:143
作者
Liu, Bo [1 ]
Cheng, H. D. [1 ,2 ]
Huang, Jianhua [1 ]
Tian, Jiawei [3 ]
Tang, Xianglong [1 ]
Liu, Jiafeng [1 ]
机构
[1] Harbin Inst Technol, Sch Comp Sci & Technol, Harbin 150001, Peoples R China
[2] Utah State Univ, Dept Comp Sci, Logan, UT 84322 USA
[3] Harbin Med Univ, Affiliated Hosp 2, Harbin, Peoples R China
基金
美国国家科学基金会;
关键词
Image segmentation; Active contour; Probability difference; Level set; Breast ultrasound (bus) imaging; BOUNDARY DETECTION; LEVEL; SPECKLE; ALGORITHM; MODEL;
D O I
10.1016/j.patcog.2010.01.002
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Because of its low signal/noise ratio, low contrast and blurry boundaries, ultrasound (US) image segmentation is a difficult task. In this paper, a novel level set-based active contour model is proposed for breast ultrasound (BUS) image segmentation. At first, an energy function is formulated according to the differences between the actual and estimated probability densities of the intensities in different regions. The actual probability densities are calculated directly. For calculating the estimated probability densities, the probability density estimation method and background knowledge are utilized. The energy function is formulated with level set approach, and a partial differential equation is derived for finding the minimum of the energy function. For performing numerical computation, the derived partial differential equation is approximated by the central difference and non-re-initialization approach. The proposed method was operated on both the synthetic images and clinical BUS images for studying its characteristics and evaluating its performance. The experimental results demonstrate that the proposed method can model the BUS images well, be robust to noise, and segment the BUS images accurately and reliably. (C) 2010 Elsevier Ltd. All rights reserved.
引用
收藏
页码:2028 / 2042
页数:15
相关论文
共 50 条
[1]   An interacting multiple model probabilistic data association filter for cavity boundary extraction from ultrasound images [J].
Abolmaesumi, P ;
Sirouspour, MR .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2004, 23 (06) :772-784
[2]   Novel Bayesian multiscale method for speckle removal in medical ultrasound images [J].
Achim, A ;
Bezerianos, A ;
Tsakalides, P .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2001, 20 (08) :772-783
[3]   Multiple resolution Bayesian segmentation of ultrasound images [J].
Ashton, EA ;
Parker, KJ .
ULTRASONIC IMAGING, 1995, 17 (04) :291-304
[4]   Segmentation of ultrasound images - multiresolution 2D and 3D algorithm based on global and local statistics [J].
Boukerroui, D ;
Baskurt, A ;
Noble, JA ;
Basset, O .
PATTERN RECOGNITION LETTERS, 2003, 24 (4-5) :779-790
[5]   A multiparametric and multiresolution segmentation algorithm of 3-D ultrasonic data [J].
Boukerroui, D ;
Basset, O ;
Baskurt, A ;
Gimenez, G .
IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL, 2001, 48 (01) :64-77
[6]  
Bouma CJ, 1996, LECT NOTES COMPUT SC, V1131, P203, DOI 10.1007/BFb0046955
[7]   SPECKLE IN ULTRASOUND B-MODE SCANS [J].
BURCKHARDT, CB .
IEEE TRANSACTIONS ON SONICS AND ULTRASONICS, 1978, 25 (01) :1-6
[8]   Intravascular ultrasound image segmentation:: A three-dimensional fast-marching method based on gray level distributions [J].
Cardinal, MHR ;
Meunier, J ;
Soulez, G ;
Maurice, RL ;
Therasse, É ;
Cloutier, G .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2006, 25 (05) :590-601
[9]   Geodesic active contours [J].
Caselles, V ;
Kimmel, R ;
Sapiro, G .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1997, 22 (01) :61-79
[10]   A methodology for evaluation of boundary detection algorithms on medical images [J].
Chalana, V ;
Kim, YM .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 1997, 16 (05) :642-652