Medical image fusion focuses to fuse complementary diagnostic details for better visualization of comprehensive information and interpretation of various diseases and its treatment planning. In this paper, a multistage multimodal fusion model is presented based on nonsubsampled shearlet transform (NSST), stationary wavelet transform (SWT), and feature‐adaptive pulse coupled neural network. Firstly, NSST is employed to decompose the source images into optimally sparse multi‐resolution components followed by SWT. Secondly, structural features are extracted by a weighted sum‐modified Laplacian and applied to an adaptive model to map feature weights for low‐band SWT component fusion, and texture feature‐based fusion rule is applied to fuse high‐band SWT components. High‐frequency NSST components are fused using the absolute maximum and sum of absolute difference based rule to retain complex directional details. Experimental results show that the proposed method obtains significantly better fused medical images compared to others with excellent visual quality and improved computational measures.

中文翻译：

---

基于特征自适应脉冲耦合神经网络的多阶段多峰医学图像融合模型

医学图像融合的重点是融合互补的诊断细节，以便更好地可视化综合信息并解释各种疾病及其治疗计划。本文提出了一种基于非下采样的小波变换（NSST），平稳小波变换（SWT）和特征自适应脉冲耦合神经网络的多阶段多峰融合模型。首先，使用NSST将源图像分解为最佳稀疏的多分辨率分量，然后再进行SWT。其次，通过加权和修正的拉普拉斯算子提取结构特征，并将其应用于自适应模型，以映射特征权重以进行低频段SWT组件融合，而基于纹理特征的融合规则则应用于融合高频段SWT组件。高频NSST分量使用基于绝对最大值和绝对差之和的规则进行融合，以保留复杂的方向细节。实验结果表明，与其他方法相比，该方法获得了明显更好的融合医学图像，并具有出色的视觉质量和改进的计算手段。