Usefulness of texture analysis for computerized classification of breast lesions on mammograms

Abstract

This work presents the usefulness of texture features in the classification of breast lesions in 5,518 images of regions of interest, which were obtained from the Digital Database for Screening Mammography that included microcalcifications, masses, and normal cases. Sixteen texture features were used, i.e., 13 were based on the spatial gray-level dependence matrix and 3 on the wavelet transform. The nonparametric K-NN classifier was used in the classification stage. The results obtained from receiver operating characteristic analysis indicated that the texture features can be used for separating normal regions and lesions with masses and microcalcifications, yielding the area under the curve (AUC) values of 0.957 and 0.859, respectively. However, the texture features were not very effective for distinguishing between malignant and benign lesions because the AUC was 0.617 for masses and 0.607 for microcalcifications. The study showed that the texture features can be used for the detection of suspicious regions in mammograms.

Fig 1

Digitized image of a calibration phantom with 21 different optical density levels used.

Fig 2

Relationship between optical density and gray-level values for a Howtek scanner obtained with 21 different levels shown in Figure 1. Straight line of regression for data generated by Equation (1).

Fig 3

Orientations used in the co-occurrence matrix calculation.

Fig 4

Jeffries–Matusita distance value for each number of features used in the case of classification between normal and abnormal regions.

Fig 5

Jeffries–Matusita distance value for each number of features used in the case of classification between regions with masses and microcalcifications.

Fig 6

ROC curve for classification between normal and abnormal regions.

Fig 7

ROC curve for classification between masses and microcalcifications.

Fig 8

ROC curve for classification between benign and malignant microcalcifications.

Fig 9

ROC curve for classification between benign and malignant masses.