Title :
Selection of optimal texture descriptors for retrieving ultrasound medical images
Author :
Sohail, Abu Sayeed Md ; Bhattacharya, Prabir ; Mudur, Sudhir P. ; Krishnamurthy, Srinivasan
Author_Institution :
Dept. of Comput. Sci. & Software Eng., Concordia Univ., Montreal, QC, Canada
fDate :
March 30 2011-April 2 2011
Abstract :
Although feature selection has been proven to be very effective in machine learning and pattern classification applications, it has not been widely practiced in the area of image annotation and retrieval. This paper presents a method of selecting a near optimal to optimal subset of statistical texture descriptors in efficient representation and retrieval of ultrasound medical images. An objective function combining the concept of between-class distance and within-class divergence among the training dataset has been proposed as the evaluation criteria of optimality. Searching for the selection of optimal subset of image descriptors has been performed using Multi-Objective Genetic Algorithm (MOGA). The proposed feature selection based approach of image annotation and retrieval has been tested using a database of 679 ultrasound ovarian images and satisfactory retrieval performance has been achieved. Besides, performance of ultrasound medical image retrieval with and without applying feature selection based image annotation technique has also been compared.
Keywords :
biomedical ultrasonics; data analysis; feature extraction; genetic algorithms; image classification; image representation; image retrieval; image texture; medical image processing; statistical analysis; feature selection; image annotation; image representation; machine learning; multiobjective genetic algorithm; pattern classification; statistical texture descriptors; training dataset; ultrasound medical image retrieval; ultrasound ovarian images; Biological cells; Biomedical imaging; Entropy; Feature extraction; Genetic algorithms; Image retrieval; Ultrasonic imaging; feature selection; medical image retrieval; multi-objective optimization; texture descriptors;
Conference_Titel :
Biomedical Imaging: From Nano to Macro, 2011 IEEE International Symposium on
Conference_Location :
Chicago, IL
Print_ISBN :
978-1-4244-4127-3
Electronic_ISBN :
1945-7928
DOI :
10.1109/ISBI.2011.5872343