Contour and region characterisation of breast tumour masses with fractal and statistical attributes. (2018)

• Record Type: Journal Article
• Authors: Khemis, Kamila; Lazzouni, Sihem Amel; Messadi, Mahammed; Bessaid, Abdelhafid
• Is Part Of: International journal of biomedical engineering and technology. Volume 26:Number 2(2018)
• Page Start: 186
• Page End: 196
• Publication Date: 2018
• Subjects: mammography -- fractal -- texture -- grey-level co-occurrence matrix -- contour -- watershed line -- characterisation -- classification -- SVM; Biomedical engineering -- Periodicals; 610.28
• Languages: English
• ISSNs: 1752-6418

Abstract

Breast cancer continues to rank at the forefront of public health problems. Characterisation of breast tissue is a step in computer-aided diagnosis, so we focus on it considering in particular texture and contour analysis of tumour masses with fractal and statistical approaches. Fist we extracted the mammographic mass with the mathematical morphology segmentation tool Watershed Line algorithm. Then we calculated fractal dimension of the mass contour using box counting algorithm. In addition to that we measured textural attributes from the grey-level co-occurrence matrix of the segmented image (region). Finally, we used Support Vector Machine classifier evaluated in K -fold cross-validation mode with OneVsOne strategy considering multiclass classification: Benin masses/Malignant masses. As a result we obtained a classification rate of 98%.