【摘要】 目的:研究一种新的算法用于PET/CT图像的异机融合。方法:在小波域上运用变分的方法,结合小波和变分的优点,首先对PET和CT图像进行小波分解,然后运用提出的两个假设分别对分解后的近似和细节分量进行融合,最后进行小波逆变换得到融合图像。结果:根据具体的融合算法实例,并与MATLAB的小波融合工具箱的融合结果进行了比较,发现新算法对图像中病变区域的解剖定位更加的准确。结论:实验证明在小波域上运用变分法进行图像的融合可以得到很好的效果,能够更好地满足临床治疗的需要。更多还原

【Abstract】 Objective To find a new algorithm for PET/CT image fusion.Methods A variational model was used based on the wavelet transform.Firstly,PET and CT images were decomposed using wavelet transform.Then,images in approximate channel and detail channel were fused according to the two proposed assumption.Finally,decomposed images were synthesized to form fused image.Results Compared with the results form MATLAB wavelet fusion toolbox,the experimental results showed that the new variational image fusion model could provide more accurate result for target location in radiotherapy planning.Conclusion According to experiments,the new algorithm can reach good results and meet requirement of clinical demands.更多还原