Brain CT and MRI medical image fusion scheme Using NSST And Dictionary Learning

Abstract

Medical image fusion offers an important approach by integrating complimentary features of different imaging modalities to acquire a high-quality image. For the fusion of medical images that it is very helpful to medical exploration and clinical diagnosis. An image fusion method for CT and MRI medical image using nonsubsampled shearlet transform (NSST) and dictionary learning which is based on sparse representation (SR) theory is presented. NSST and dictionary learning are two most extensively used image representation theories. Firstly, the source image is decomposed by NSST to get low frequency coefficients and the high frequency coefficients. Secondly, the high frequency coefficients are merged using the absolute-maximum rule while the low frequency coefficients are fused with a SR-based fusion approach. Finally, the fused image is obtained by inverse NSST. The results show that the proposed method achieves the best performance in both subjective and objective evaluation.