False-positive reduction in mammography using multiscale spatial Weber law descriptor and support vector machines

Abstract

In a CAD system for the detection of masses, segmentation of mammograms yields regions of interest (ROIs), which are not only true masses but also suspicious normal tissues that result in false positives. We introduce a new method for false-positive reduction in this paper. The key idea of our approach is to exploit the textural properties of mammograms and for texture description, to use Weber law descriptor (WLD), which outperforms state-of-the-art best texture descriptors. The basic WLD is a holistic descriptor by its construction because it integrates the local information content into a single histogram, which does not take into account the spatial locality of micropatterns. We extend it into a multiscale spatial WLD (MSWLD) that better characterizes the texture micro structures of masses by incorporating the spatial locality and scale of microstructures. The dimension of the feature space generated by MSWLD becomes high; it is reduced by selecting features based on their significance. Finally, support vector machines are employed to classify ROIs as true masses or normal parenchyma. The proposed approach is evaluated using 1024 ROIs taken from digital database for screening mammography and an accuracy of Az = 0.99 ± 0.003 (area under receiver operating characteristic curve) is obtained. A comparison reveals that the proposed method has significant improvement over the state-of-the-art best methods for false-positive reduction problem.

Keywords: False-positive reduction; Mammograms; Mass detection; Support vector machines; WLD.

Fig. 1

a Central pixel and its neighbors in case P = 8. b (8, 1) neighborhood of the central pixel, c and d (16, 2) and (24, 3) neighborhoods, respectively, of the central pixel [22]

Fig. 2

a Basic WLDr, b spatial WLD

Fig. 3

Graph showing the effect of the parameters (σ, λ) on classification accuracy

Fig. 4

SVM classifies by finding the optimal hyperplane that has maximum margin

Fig. 5

Mass detection system

Fig. 6

Annotated mammogram images from DDSM database. Contours mark the boundaries of the mass regions. Squares represent the mass and suspicious normal ROIs extracted for the validation of the proposed method

Fig. 7

Sample mass ROIs (top row) and suspicious normal ROIs (bottom row)

Fig. 8

The effect of the combinations (4, 4, 5) and (12, 4, 20), and different number of blocks with MSWLD_24,3 (T, M, S, n) operator at scale (24, 3). In each case, the dimension of the feature space is shown on bars

Fig. 9

The effect of scale-1: (8, 1), scale-2: (16, 2), scale-3: (27, 3), and their fusion on the recognition rate before feature selection

Fig. 10

The effect of scale-1: (8, 1), scale-2: (16, 2), scale-3: (24, 3), and their fusion on the recognition rate after feature selection. The numbers on two bars show the number of features (after/before) selection