- 期刊
- OpenAccess
Micro Calcification Clusters Detection by Using Gaussian Markov Random Fields Representation
並列摘要
In order to develop an accurate computer-aided diagnosis system for the automatic detection of microcalcification clusters in mammograms. In this study, we presented a new microcalcification clusters detection method by using Gaussian Markov Random Fields (GMRFs) representation. The design and evaluation of the algorithm involved three main phases. In the first phase of the algorithm, a training dataset is employed to train and get the GMRF texture features of each image block and then the cluster center and bias are obtained. In the second phase of the algorithm, we use GMRFs to get it texture feature with a given image block. And finally, the distance between the given image block GMRFs features and the cluster center to make a decision whether it contains a microcalcification cluster or not.