Digital Library

cab1

 
Title:      ESTIMATION OF A LOG-COMPRESSED NAKAGAMI DISTRIBUTION AND APPLICATION TO BREAST TUMOR DISCRIMINATION IN ULTRASONIC IMAGES
Author(s):      Atsushi Takemura
ISBN:      978-972-8924-97-3
Editors:      Hans Weghorn and Pedro IsaĆ­as
Year:      2009
Edition:      V II, 2
Keywords:      Ultrasonic image, breast tumor, log-compressed Nakagami distribution, geodesic active contour, AdaBoost
Type:      Short Paper
First Page:      191
Last Page:      196
Language:      English
Cover:      cover          
Full Contents:      click to dowload Download
Paper Abstract:      This paper proposes a new method for estimation of a Nakagami distribution parameter from a log-compressed ultrasonic image. This paper also describes effective features and classifiers for accurate discrimination of breast tumors in ultrasonic images. Total 127 features were defined corresponding to diagnostic observations used by physicians, such as internal echo, shape, and boundary echo. These features included novel features based on the estimated parameter of the log-compressed Nakagami distribution. Furthermore, this paper proposes a method for discrimination of breast tumors using a geodesic active contour model, and an ensemble classifier trained by the multi-class AdaBoost learning algorithm combined with a sequential feature selection process. Validation testing using 200 carcinomas, 50 fibroadenomas, and 50 cysts showed the high performance of the proposed method of segmentation and discrimination.
   

Social Media Links

Search

Login