Feature Extraction

Features are extracted to characterise a segmented region in the mammogram. Feature vectors from masses are assumed to be considered different from normal tissue, and based on a collection of their examples from several subjects, a system can be trained to differentiate between them. The main aim is that features should be sensitive and accurate for reducing false positives. Typically a set or vector of features is extracted for a given segmented region.

From the pixels that comprise each suspicious ROI passing the prefiltering size test described above, a subset of gray scale, textural, and morphological features used in previous mammographic studies are extracted. The features extracted are summarized in Table 11.14.

Table 11.14: Summary of features extracted by feature grouping giving 316 features in total

Grouping

Type

Description

Number

Gray scale

Histogram

Mean, variance, skewness, kurtosis, and entropy.

5

Textural

SGLD

From SGLD matrices constructed in 5 different directions and 3 different distances 15 features [38, 39] are extracted.

15 x 15

Laws

Texture energy [6] extracted from 25 mask convolutions.

5 x 5

DWT

From DWT coefficients of 4 subbands at 3 scales the following statistical features are extracted: mean, standard deviation, skewness, kurtosis.

4 x 12

Fourier

Spectral energy from 10 Fourier rings.

10

Fractal

Fractal dimension feature.

1

Morphological

Region

Circularity [4] area.

2

0 0

Post a comment