Welcome to the InfoSci Platform
Computer Aided Detection and Recognition of Lesions in Ultrasound Breast Images

Computer Aided Detection and Recognition of Lesions in Ultrasound Breast Images

Moi Hoon Yap, Eran Edirisinghe, Helmut Bez
Copyright: © 2010 |Volume: 1 |Issue: 2 |Pages: 29
ISSN: 1947-3133|EISSN: 1947-3141|EISBN13: 9781609604301|DOI: 10.4018/jcmam.2010040104
Cite Article Cite Article

MLA

Yap, Moi Hoon, et al. "Computer Aided Detection and Recognition of Lesions in Ultrasound Breast Images." IJCMAM vol.1, no.2 2010: pp.53-81. http://doi.org/10.4018/jcmam.2010040104

APA

Yap, M. H., Edirisinghe, E., & Bez, H. (2010). Computer Aided Detection and Recognition of Lesions in Ultrasound Breast Images. International Journal of Computational Models and Algorithms in Medicine (IJCMAM), 1(2), 53-81. http://doi.org/10.4018/jcmam.2010040104

Chicago

Yap, Moi Hoon, Eran Edirisinghe, and Helmut Bez. "Computer Aided Detection and Recognition of Lesions in Ultrasound Breast Images," International Journal of Computational Models and Algorithms in Medicine (IJCMAM) 1, no.2: 53-81. http://doi.org/10.4018/jcmam.2010040104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The authors extend their previous work on Ultrasound (US) image lesion detection and segmentation, to classification, proposing a complete end-to-end solution for automatic Ultrasound Computer Aided Detection (US CAD). Carried out is a comprehensive analysis to determine the best classifier-feature set combination that works optimally in US imaging. In particular the use of nineteen features categorised into three groups (shape, texture and edge), ten classifiers and 22 feature selection approaches are used in the analysis. From the overall performance, the classifier RBFNetworks defined by the WEKA pattern recognition tool set, with a feature set comprising of the area to perimeter ratio, solidity, elongation, roundness, standard deviation, two Fourier related and a fractal related texture measures out-performed other combinations of feature-classifiers, with an achievement of predicted Az value of 0.948. Next analyzed is the use of a number of different metrics in performance analysis and provide an insight to future improvements and extension.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.