Analysis of Structural Similarity in Mammograms for Detection of Bilateral Asymmetry

• Published in: IEEE transactions on medical imaging Vol. 34; no. 2; pp. 662 - 671
• Main Authors: Casti, Paola, Mencattini, Arianna, Salmeri, Marcello, Rangayyan, Rangaraj M.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-02-2015
• Subjects: Accuracy; Algorithms; Bayes Theorem; Bilateral asymmetry; Breast - pathology; Breast cancer; Breast Density; Breast Neoplasms; computer-aided diagnosis; Databases, Factual; Delta-sigma modulation; Female; Gabor filters; Humans; Image Processing, Computer-Assisted - methods; Indexes; Mammary Glands, Human - abnormalities; Mammography - methods; ROC Curve; spherical semivariogram; Strips; structural similarity indices; Tabár masking
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2014.2365436

We hypothesize that quantification of structural similarity or dissimilarity between paired mammographic regions can be effective in detecting asymmetric signs of breast cancer. Bilateral masking procedures are applied for this purpose by using automatically detected anatomical landmarks. Changes in structural information of the extracted regions are investigated using spherical semivariogram descriptors and correlation-based structural similarity indices in the spatial and complex wavelet domains. The spatial distribution of grayscale values as well as of the magnitude and phase responses of multidirectional Gabor filters are used to represent the structure of mammographic density and of the directional components of breast tissue patterns, respectively. A total of 188 mammograms from the DDSM and mini-MIAS databases, consisting of 47 asymmetric cases and 47 normal cases, were analyzed. For the combined dataset of mammograms, areas under the receiver operating characteristic curves of 0.83, 0.77, and 0.87 were obtained, respectively, with linear discriminant analysis, the Bayesian classifier, and an artificial neural network with radial basis functions, using the features selected by stepwise logistic regression and leave-one-patient-out cross-validation. Two-view analysis provided accuracy up to 0.94, with sensitivity and specificity of 1 and 0.88, respectively.