Texture analysis of tissue surrounding microcalcifications on mammograms for breast cancer diagnosis

Abstract

Diagnosis of microcalcifications (MCs) is challenged by the presence of dense breast parenchyma, resulting in low specificity values and thus in unnecessary biopsies. The current study investigates whether texture properties of the tissue surrounding MCs can contribute to breast cancer diagnosis. A case sample of 100 biopsy-proved MC clusters (46 benign, 54 malignant) from 85 dense mammographic images, included in the Digital Database for Screening Mammography, was analysed. Regions of interest (ROIs) containing the MCs were pre-processed using a wavelet-based contrast enhancement method, followed by local thresholding to segment MCs; the segmented MCs were excluded from original image ROIs, and the remaining area (surrounding tissue) was subjected to texture analysis. Four categories of textural features (first order statistics, co-occurrence matrices features, run length matrices features and Laws' texture energy measures) were extracted from the surrounding tissue. The ability of each feature category in discriminating malignant from benign tissue was investigated using a k-nearest neighbour (kNN) classifier. An additional classification scheme was performed by combining classification outputs of three textural feature categories (the most discriminating ones) with a majority voting rule. Receiver operating characteristic (ROC) analysis was conducted for classifier performance evaluation of the individual textural feature categories and of the combined classification scheme. The best performance was achieved by the combined classification scheme yielding an area under the ROC curve (A(z)) of 0.96 (sensitivity 94.4%, specificity 80.0%). Texture analysis of tissue surrounding MCs shows promising results in computer-aided diagnosis of breast cancer and may contribute to the reduction of unnecessary biopsies.

Elm Based Cad System to Classify Mammograms by the Combination of CLBP and Contourlet

“…Finally, the abnormal regions are detected by the neural network. A system to detect microcalcification in mammograms is presented in [9] and is based on wavelets. The texture features of first order statistical, co-occurrence matrices, run length matrices and energy measures are calculated.…”

Computerized Image Analysis of Mammographic Microcalcifications: Diagnosis and Prognosis

“…The hypothesis was tested on a dataset of 54 cases (18 malignant/36 benign) exploiting GLCMs and fractal geometry based features and achieved a classification performance 85% (sensitivity 89%, specificity 83%) employing Linear and Logistic Discriminant analysis. Since its introduction on digital scout views, the feasibility of the MCs surrounding tissue analysis hypothesis has been further investigated on screening mammograms (Karahaliou et al, 2007a(Karahaliou et al, , 2007b). …”

Mammographic Parenchymal Texture Analysis for Estrogen-Receptor Subtype Specific Breast Cancer Risk Estimation

“…Structure Enhancing Diffusion acts as a denoising model that suppresses the noise as well as preserves the flow-like structure, which has special interest in mammography, since mammographic parenchymal pattern has flow-like, thin, linear structures within breast vasculature representing significant textural information [12]. It adapts its Eigenvalues to enhance the structure, hence the Eigenvalues are related to the anisotropy of the image represented by two conductivity terms β 1 and β 2 in the direction of gradient and isophote at a given scale respectively.…”