Mammographic mass classification using filter response patches. Issue 8 (13th August 2018)

• Record Type: Journal Article
• Authors: Suhail, Zobia; Hamidinekoo, Azam; Zwiggelaar, Reyer
• Is Part Of: IET computer vision. Volume 12:Issue 8(2018)
• Page Start: 1060
• Page End: 1066
• Publication Date: 2018-08-13
• Subjects: Bayes methods -- image texture -- channel bank filters -- cancer -- object detection -- image classification -- medical image processing -- mammography; receiver operating characteristic curve -- naive Bayes classifier -- Digital Database-for-Screening Mammography database -- texton dictionary generation -- filter bank responses -- texture-based mass classification -- mammograms -- mass abnormalities classification -- supervised patch-wise texton-based approach -- early breast cancer diagnosis -- filter response patches -- automatic mammographic mass classification; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2018.5244
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : Considering the importance of early diagnosis of breast cancer, a supervised patch‐wise texton‐based approach has been developed for the classification of mass abnormalities in mammograms. The proposed method is based on texture‐based classification of masses in mammograms and does not require segmentation of the mass region. In this approach, patches from filter bank responses are utilised for generating the texton dictionary. The methodology is evaluated on the publicly available Digital Database for Screening Mammography database. Using a naive Bayes classifier, a classification accuracy of 83% with an area under the receiver operating characteristic curve of 0.89 was obtained. Experimental results demonstrated that the patch‐wise texton‐based approach in conjunction with the naive Bayes classifier constructs an efficient and alternative approach for automatic mammographic mass classification.