Abstract
Clustered microcalcifications (MCs) in mammograms are an important early sign of breast cancer in women. Their accurate detection is important in computer-aided detection (CADe). In this paper, we integrated the possibilistic fuzzy c-means (PFCM) clustering algorithm and weighted support vector machine (WSVM) for the detection of MC clusters in full-field digital mammograms (FFDM). For each image, suspicious MC regions are extracted with region growing and active contour segmentation. Then geometry and texture features are extracted for each suspicious MC, a mutual information-based supervised criterion is used to select important features, and PFCM is applied to cluster the samples into two clusters. Weights of the samples are calculated based on possibilities and typicality values from the PFCM, and the ground truth labels. A weighted nonlinear SVM is trained. During the test process, when an unknown image is presented, suspicious regions are located with the segmentation step, selected features are extracted, and the suspicious MC regions are classified as containing MC or not by the trained weighted nonlinear SVM. Finally, the MC regions are analyzed with spatial information to locate MC clusters. The proposed method is evaluated using a database of 410 clinical mammograms and compared with a standard unweighted support vector machine (SVM) classifier. The detection performance is evaluated using response receiver operating (ROC) curves and free-response receiver operating characteristic (FROC) curves. The proposed method obtained an area under the ROC curve of 0.8676, while the standard SVM obtained an area of 0.8268 for MC detection. For MC cluster detection, the proposed method obtained a high sensitivity of 92 % with a false-positive rate of 2.3 clusters/image, and it is also better than standard SVM with 4.7 false-positive clusters/image at the same sensitivity.
Highlights
Breast cancer is the most frequent form of cancer in women and is the leading cause of mortality in women each year
We proposed a novel weighted support vector machine-based microcalcification cluster detection method for full-field digital mammograms (FFDM) images
Geometry and texture features are extracted for each suspicious MC, a mutual information-based supervised criterion is used to select important features, and possibilistic fuzzy c-means (PFCM) is applied to cluster the samples into two clusters
Summary
Breast cancer is the most frequent form of cancer in women and is the leading cause of mortality in women each year. In our previous work [11], a new wavelet-based image enhanced method is proposed. El-Naqa et al [13] investigated the support vector machine (SVM) classifier for MC cluster detection, and a successive enhancement learning scheme was proposed to improve the performance. On a set of 76 mammogram images containing 1120 MCs, their method obtained a sensitivity of 94 % with an error rate of one false-positive cluster per image. Tiedeu et al [15] detected microcalcifications by integrating image enhancement and the threshold-based segmentation method. Several features were extracted for each region from the enhanced image, and by embedding feature clustering in the segmentation, their method obtained much less false positives than other methods. We proposed a novel weighted support vector machine-based microcalcification cluster detection method for FFDM images. Several features used here have been used in our previous work [7] for mass diagnosis
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
