基于小波统计特性的CT/MR医学影像优化融合方法

Optimum Fusion for CT/MR Image Based on the Statistical Property of Wavelet Decomposition

多模医学影像融合技术服务于临床诊断具有十分重要的意义。计算机断层摄像CT(ComputerTomography)仅能清晰显示人体骨骼组织,而磁共振成像MR(MagneticResonance)具有软组织对比分辨率高的特点。论文提出了一种基于小波统计特性的CT、MR医学颅脑部影像优化融合方法,采用信息熵和边缘保持度两项指标作为优化融合依据,获得的融合影像有效地综合CT与MR影像信息,可同时清晰地显示脑部骨组织和软组织信息。

The fusion technology of multi-modality biomedical images is important for clinic diagnoses.For structure of bone can only be clearly display on CT,while normal and pathological soft tissue are better visualised by MR.This paper describes a new optimum fusion scheme to combine information from different modalities which is based on the statistical properties of coefficient after wavelet decomposition.Entropy and edge preservation are used to adjust the fusion rule and achieve the optimum weight.The optimum fused images synthesize the information of CT and MR, especially in displaying of bone and soft tissue.