Microcalcification clusters processing in mammograms based on relevance vector machine with adaptive kernel learning

Abstract

Using the method of adaptive kernel learning based relevance vector machine (ARVM) and combining the morphological filtering and the clustering criterion recommended by Kallergi, a new algorithm for microcalcification (MC) clusters processing in mammograms is investigated. Firstly, the detection of MC is formulated as a supervised-learning problem. Then the ARVM is used as a classifier to determine whether an MC object is present at each location in the mammogram and a morphological processing is used to remove the isolated spurious pixels. Finally, the identified MC clusters are obtained by Kallergi criterion. To improve the computational speed, a fast processing method based on ARVM is developed, in which the whole image is decomposed first into sub-image blocks for parallel operation. Experimental results indicate that the ARVM method outperforms the RVM method and, in particular, the fast processing method could greatly reduce the testing time.