Detection of Breast Masses in Mammogram Images Using Growing Neural Gas Algorithm and Ripley’s K Function

Abstract

Breast cancer is a serious public health problem in several countries. Computer-aided detection/diagnosis systems (CAD/CADx) have been used with relative success in aid of health care professionals. The goal of such systems is not to replace the professionals, but to join forces in order to detect the different types of cancer at an early stage. The main contribution of this work is the presentation of a methodology for detecting masses in digitized mammograms using the growing neural gas algorithm for image segmentation and Ripley's K function to describe the texture of segmented structures. The classification of these structures is accomplished through support vector machines which separate them in two groups, using shape and texture measures: masses and non-masses. The methodology obtained 89.30% of accuracy and a rate of 0.93 false positives per image.

A novel computer aided breast mass detection scheme based on morphological enhancement and SLIC superpixel segmentation

“…The proposed method (with T = 1,2,3) is compared with existing methods in Table XI in terms of the sensitivity and FP rate. It is worth noting that the schemes proposed in the other relevant literatures 2,5,20 were also evaluated on the DDSM database. These results indicate that the proposed scheme has the potential to lower the FP rate of CAD without sacrificing sensitivity.…”

Detection of masses in mammograms with adaption to breast density using genetic algorithm, phylogenetic trees, LBP and SVM

“…These regional analyses are superior to the global analyses (entire ROI), according to (Sampaio et al, 2011), (Junior et al, 2009), (de Oliveira Martins et al, 2009.…”

Automatic Detection of Masses in Mammograms Using Quality Threshold Clustering, Correlogram Function, and SVM

“…Oliveira Martins et al [23] introduced a methodology that uses a growing neural gas (GNG) to segment the lesion candidates, and the SVM was pooled with Ripley's K-function for the detection of masses. In that methodology, they used 997 images from the Digital Database for Screening Mammography (DDSM), with 436 images used for testing and 561 used in the evaluation of the process of detecting the masses.…”