Characterization of mammographic masses based on level set segmentation with new image features and patient information

Abstract

Computer-aided diagnosis (CAD) for characterization of mammographic masses as malignant or benign has the potential to assist radiologists in reducing the biopsy rate without increasing false negatives. The purpose of this study was to develop an automated method for mammographic mass segmentation and explore new image based features in combination with patient information in order to improve the performance of mass characterization. The authors' previous CAD system, which used the active contour segmentation, and morphological, textural, and spiculation features, has achieved promising results in mass characterization. The new CAD system is based on the level set method and includes two new types of image features related to the presence of microcalcifications with the mass and abruptness of the mass margin, and patient age. A linear discriminant analysis (LDA) classifier with stepwise feature selection was used to merge the extracted features into a classification score. The classification accuracy was evaluated using the area under the receiver operating characteristic curve. The authors' primary data set consisted of 427 biopsy-proven masses (200 malignant and 227 benign) in 909 regions of interest (ROIs) (451 malignant and 458 benign) from multiple mammographic views. Leave-one-case-out resampling was used for training and testing. The new CAD system based on the level set segmentation and the new mammographic feature space achieved a view-based Az value of 0.83 +/- 0.01. The improvement compared to the previous CAD system was statistically significant (p = 0.02). When patient age was included in the new CAD system, view-based and case-based Az values were 0.85 +/- 0.01 and 0.87 +/- 0.02, respectively. The study also demonstrated the consistency of the newly developed CAD system by evaluating the statistics of the weights of the LDA classifiers in leave-one-case-out classification. Finally, an independent test on the publicly available digital database for screening mammography with 132 benign and 197 malignant ROIs containing masses achieved a view-based Az value of 0.84 +/- 0.02.

Figure 1

The flowchart of the newly developed CAD system for mammographic mass classification.

Figure 2

Characteristics of the data set included in this study. (a) The distribution of the likelihood of malignancy (LM) rating of the masses by the radiologist. (b) The distributions of mass size. To show the size for the majority of the masses in detail, 16 masses with sizes over 50 mm were grouped to the bar representing mass size=50 mm. (c) The distributions of ages for patients with malignant or benign masses.

Figure 3

An example of mammographic mass segmentation using the LS method. (a) Original ROI. (b) Initial boundary obtained by the K-means clustering and morphological opening. (c) LS boundary.

Figure 4

Extraction of the margin abruptness feature. (a) RBST image from the margin of the mass in Figure 3(c). (b) The gradient image of (a) in the vertical direction. (c) The HLE-RBST image. (d) The segment that contains the longest line in terms of the DFS algorithm.

Figure 5

Classification performances of the LS system in the new mammographic feature space and the AC system in the previous mammographic feature space. (a) View-based analysis. (b) Case-based analysis.

Figure 6

Classification performances of the LS system and the radiologist (RAD). (a) View-based analysis. (b) Case-based analysis.