Decomposition and recompilation of mammograms for breast tumour detection. Issue 2 (26th January 2018)

• Record Type: Journal Article
• Authors: Yeh, Jinn‐Yi; Chan, Si‐Wa
• Other Names: GarcÍa‐RodrÍguez José guestEditor.; Escalera Sergio guestEditor.; Psarrou Alexandra guestEditor.; Guyon Isabelle guestEditor.; Lewis Andrew guestEditor.; Leitner Juxi guestEditor.
• Is Part Of: Expert systems. Volume 35:Issue 2(2018)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2018-01-26
• Subjects: computer‐aided detection -- mammograms -- multiband generation processes -- principal‐component analysis -- tumour detection; Expert systems (Computer science); 006.33
• DOI: 10.1111/exsy.12243
• Languages: English
• ISSNs: 0266-4720

Abstract

Abstract: Breast tumours are the leading cause of cancer death among female adults. Early diagnosis, discovery and treatment are currently the optimal approach to reducing mortality rates and increasing the length of cancer patients' lives. Presently, mammography is the most effective screening method for early breast tumour detection. This paper proposes a decomposition and recompilation approach for the analysis of mammograms. The decomposition stage is based on multiband generation processes (MBGP), which are used to expand the dimensionality of a mammogram. Recompilation uses principal‐component analysis (PCA) to generate different views of the mammogram based on the orthonormal basis vectors. Using Otsu's thresholding method, the abnormal parts of mammographic images can be easily detected. In experiments, the average Jaccard values determined using the Bayes, Markov, Windows, and proposed method were 0.253, 0.228, 0.201, and 0.441, respectively, for images from the mini–MIAS; averages were 0.132, 0.186, 0.158, and 0.261 for images from the Digital Database for Screening Mammography. Thus, the proposed method outperformed the other methods. The main contributions of the current paper are as follows: A novel methodology consisting of multiband generation processes and principal‐component analysis for analyzing abnormities in mammograms is proposed. Two practical data sets were used to develop and evaluate the proposed approach.