|
|
|
| Edge based differentiation between the malignant and the benign breast tumor in ultrasound images |
| CHEN Qiu-xia1, MA Bu-yun2, PENG Yu-lan2, LIU Qi1 |
| 1.Medical Information Engineering, College of Electrical Engineering and Information, Sichuan University, Chengdu 610065, China; 2.Department of Ultrasonography, West China Hospital, Sichuan University, Chengdu 610041, China |
|
|
|
|
Abstract Objective: Extracting the edge of breast tumor in ultrasonic images and distinguishing malignant from benign lesions. Method: This paper proposes an improved anisotropic diffusion filtering method which chooses diffusion equation with different diffusion coefficient according to the gradient of the image, and this method can smooth the image as well as finely preserve the boundary. Then presenting a new variational formulation in Level Set method which can avoid the step of re-initialization and make the formation of the initial Level Set function flexible, and applying a semiautomatic segmentation procedure with the rough contour is sketched first. This procedure improves not only the accuracy, but also the efficiency of the segmentation algorithm. Result: Computing the texture features of breast tumor by integrated GLCM and distinguishing the malignant from the benign by fuzzy C-means method, and the accuracy rate is 72.64%. Conclusion: The experiments show that the proposed algorithms could extract the contour of the breast tumor effectively and accurately, providing reliable foundation for differentiation of the malignant and the benign breast tumor.
|
|
Received: 05 June 2009
|
|
|
|
Corresponding Authors:
四川大学电气信息学院，610065
|
|
|
|
|
|
|
2010, Vol. 21 
