Sparse Representation for Detection of Microcalcification Clusters

We present an approach to detect MCs in mammograms by casting the detection problem as finding sparse representations of test samples with respect to training samples. The ground truth training samples of MCs in mammograms are assumed to be known as a priori. From these samples of the interest object class, a vocabulary of information-rich object parts is automatically constructed. The sparse representation is computed by the l1-regularized least square approach using the interior-point method. The method based on sparse representation expresses each testing sample as a linear combination of all the training samplesfrom the vocabulary. The sparse coefficient vector is obtained by l1-regularized least square through learning. MCs detectionis achieved by defining discriminatefunctions from the sparse coefficient vector for each category. To investigate its performance, the proposed method is applied to DDSM datasets and compared with support vector machines (SVMs) and twin support vector machines (TWSVMs). The experimental results have shown that the performance of the proposed method is comparable with or better than those methods. In addition, the proposed method is more efficient than SVMs and TWSVMs based methods as it has no need of model selection and parameter optimization.