Article: Effect of BIRADS shape descriptors on breast cancer analysis Journal: International Journal of Medical Engineering and Informatics (IJMEI) 2015 Vol.7 No.1 pp.65 - 79 Abstract: This paper focuses on an approach for characterising the spatial structure of mammogram masses using various multimodal features. Experiments have been conducted on benchmark digital database for screening mammography (DDSM) database with 300 mammograms. According to Breast Imaging Reporting and Data System (BIRADS) spatial structure of mammogram masses can be discriminated using its shape, size and density properties. Various new geometrical shape, margin and texture features and DDSM descriptors are used to characterise the morphology of masses as either benign or malignant. The effect of DDSM descriptors on classification accuracy is analysed. The experimental results shows that all 20 features including DDSM descriptors produce better accuracy of 93.3& compared to 86.7& without using DDSM descriptors. The overall Wilk's lambda value is reduced when all 20 features are used for classification. The proposed features set using shape, texture and DDSM descriptors provide better (c/v) ratio compared to wavelet, Gabor and other features reported in the literature. Inderscience Publishers - linking academia, business and industry through research

Title: Effect of BIRADS shape descriptors on breast cancer analysis

Authors: B. Surendiran; P. Ramanathan; A. Vadivel

Addresses: Department of Information Technology, Info Institute of Engineering, Coimbatore, Tamil Nadu, India ' Department of ECE, Info Institute of Engineering, Coimbatore, Tamil Nadu, India ' National Institute of Technology, Trichy, Tamil Nadu, India

Abstract: This paper focuses on an approach for characterising the spatial structure of mammogram masses using various multimodal features. Experiments have been conducted on benchmark digital database for screening mammography (DDSM) database with 300 mammograms. According to Breast Imaging Reporting and Data System (BIRADS) spatial structure of mammogram masses can be discriminated using its shape, size and density properties. Various new geometrical shape, margin and texture features and DDSM descriptors are used to characterise the morphology of masses as either benign or malignant. The effect of DDSM descriptors on classification accuracy is analysed. The experimental results shows that all 20 features including DDSM descriptors produce better accuracy of 93.3& compared to 86.7& without using DDSM descriptors. The overall Wilk's lambda value is reduced when all 20 features are used for classification. The proposed features set using shape, texture and DDSM descriptors provide better (c/v) ratio compared to wavelet, Gabor and other features reported in the literature.

Keywords: discriminant analysis; digital mammograms; shape features; texture features; density features; DDSM descriptors; cases to variable ratio; multimodal features; BIRADS characteristics; breast cancer analysis; mammography; classification accuracy; breast imaging; breast screening.

DOI: 10.1504/IJMEI.2015.066244

International Journal of Medical Engineering and Informatics, 2015 Vol.7 No.1, pp.65 - 79

Received: 10 Feb 2014
Accepted: 16 Apr 2014
Published online: 09 Dec 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Effect of BIRADS shape descriptors on breast cancer analysis

Keep up-to-date