The Research Of Multimodality Medical Image Fusion Technology And The Establishment Of Evaluation System

With the devolopment of medical imaging and computer technology, various kind of advanced medical imaging equipments supply multi-modality medical images. Medical images in different modality display different characteristic information of human viscera and pathological changed tissue. Multi-modality medical image fusion is that using image fuse technology in medical images, in order to supply more abundant pathology information for clinic diagnoses.In this paper, the medical image fusion method based on multi-resolution is discussed. The principle of image decomposition and reconstruction based on Gauss-pyramid, Laplacian-pyramid, contrast-pyramid and wavelet-pyramid is emphatically analyzed, it is mainly discussed the image fusion method based on wavelet-transform, as well as the new fusion algorithm-region-based selection and weighted fusion operators which based on traditional fusion operators. In the experiment of medical image fusion, we fused two groups of CT and MRI images, gained ideal results. Further more, image registration is the basis of image fusion. Pixel level image fusion requires image registration with precision of sub-pixel level. In order to satisfy the demand of pixel level image fusion, the method of image registration based on mutual information is adopted.In addition, it is founded a set of medical image fusion evaluation system. Entropy,Cross entropy,Mutual Information,Equal value and Standard Error are adopted as the evaluate parameters.We developed a system called "Multi-modality medical image fusion System", based on VC++ 6.0, for the medical image registration and fusion in this paper.