A comparison of methods for three-class mammograms classification

BACKGROUND

Mammography is considered the gold standard for early breast cancer detection but it is very difficult to interpret mammograms for many reason. Computer aided diagnosis (CAD) is an important development that may help to improve the performance in breast cancer detection.

OBJECTIVE

We present a CAD system based on feature extraction techniques for detecting abnormal patterns in digital mammograms.

METHODS

Computed features based on gray-level co-occurrence matrices (GLCM) are used to evaluate the effectiveness of textural information possessed by mass regions. A total of 20 texture features are extracted from each mammogram. The ability of feature set in differentiating normal, benign and malign tissue is investigated using a Support Vector Machine (SVM) classifier, Naive Bayes classifier and K-Nearest Neighbor (k-NN) classifier. The efficiency of classification is provided using cross-validation technique. Support Vector Machine was originally designed for binary classification. We constructed a three-class SVM classifier by combining two binary classifiers and then compared his performance with classifiers intended for multi-class classification. To evaluate the classification performance, confusion matrix and Receiver Operating Characteristic (ROC) analysis were performed.

RESULTS

Obtained results indicate that SVM classification results are better than the k-NN and Naive Bayes classification results, with accuracy ratio of 65% according to 51.6% and 38.1%, respectively.The unbalanced classification that occurs in all three classification tests is reason for unsatisfactory accuracy.

CONCLUSIONS

Obtained experimental results indicate that the proposed three-class SVM classifier is more suitable for practical use than the other two methods.

Neighborhood Structural Similarity Mapping for the Classification of Masses in Mammograms

In this paper, two novel feature extraction methods, using neighborhood structural similarity (NSS), are proposed for the characterization of mammographic masses as benign or malignant. Since gray-level distribution of pixels is different in benign and malignant masses, more regular and homogeneous patterns are visible in benign masses compared to malignant masses; the proposed method exploits the similarity between neighboring regions of masses by designing two new features, namely, NSS-I and NSS-II, which capture global similarity at different scales. Complementary to these global features, uniform local binary patterns are computed to enhance the classification efficiency by combining with the proposed features. The performance of the features are evaluated using the images from the mini-mammographic image analysis society (mini-MIAS) and digital database for screening mammography (DDSM) databases, where a tenfold cross-validation technique is incorporated with Fisher linear discriminant analysis, after selecting the optimal set of features using stepwise logistic regression method. The best area under the receiver operating characteristic curve of 0.98 with an accuracy of is achieved with the mini-MIAS database, while the same for the DDSM database is 0.93 with accuracy .

Computer-aided classification of mammographic masses using visually sensitive image features

PURPOSE

To develop a new computer-aided diagnosis (CAD) scheme that computes visually sensitive image features routinely used by radiologists to develop a machine learning classifier and distinguish between the malignant and benign breast masses detected from digital mammograms.

METHODS

An image dataset including 301 breast masses was retrospectively selected. From each segmented mass region, we computed image features that mimic five categories of visually sensitive features routinely used by radiologists in reading mammograms. We then selected five optimal features in the five feature categories and applied logistic regression models for classification. A new CAD interface was also designed to show lesion segmentation, computed feature values and classification score.

RESULTS

Areas under ROC curves (AUC) were 0.786±0.026 and 0.758±0.027 when to classify mass regions depicting on two view images, respectively. By fusing classification scores computed from two regions, AUC increased to 0.806±0.025.

CONCLUSION

This study demonstrated a new approach to develop CAD scheme based on 5 visually sensitive image features. Combining with a "visual aid" interface, CAD results may be much more easily explainable to the observers and increase their confidence to consider CAD generated classification results than using other conventional CAD approaches, which involve many complicated and visually insensitive texture features.