基于提升小波变换与自适应PCNN的医学图像融合方法

为了更好地满足临床辅助诊断和治疗的需要,提出一种基于提升小波变换的CT与MRI图像的融合方法.该方法在低频子带采用基于区域能量的融合规则；高频子带采用自适应脉冲耦合神经网络(PCNN)的融合规则,通过应用PCNN简化模型把图像逐像素的梯度能量作为PCNN的链接强度,使得PCNN能根据像素梯度能量的变化来自适应地调整链接强度的大小,并根据点火次数确定高频子带融合系数.实验结果表明,文中方法与传统融合方法相比性能优越,丰富了融合图像的边缘及细节信息,可取得更好的融合效果.

A Medical Image Fusion Method Based on Lifting Wavelet Transform and Adaptive PCNN

To better meet the demands of clinical diagnosis and treatment,this paper proposes a CT and MRI image fusion method based on lifting wavelet transform,with different fusion rules employed in low and high frequency sub-bands separately.A fusion rule based on region energy is adopted in low frequency sub-band.Adaptive PCNN fusion rule is adopted in high frequency sub-band,through the application of a simplified PCNN model.The adaptive PCNN uses gradient energy of each pixel as the linking strength of PCNN,so that the linking strength of each pixel can be chosen adaptively according to the change of pixel gradient energy,The high frequency sub-band coefficients are determined by times of firing.The experimental results show that the proposed approach of image fusion achieve better fusion quality with rich information and abundant edge details.