基于多尺度系数分解框架的医学图像融合

Title Medical Image Fusion Based on Multi-scale Coefficient Decomposition Framework

为了获得高分辨率图像细节从而辅助疾病诊断,针对磁共振(MR)和计算机断层扫描(CT)的互补特征,提出了一种基于多尺度系数分解框架的融合MR和CT医学图像的新方法。利用离散小波变换(DWT)和非下采样剪切波变换(NSST)对源图像进行多尺度分解,根据不同的局部活性度量将多尺度分解系数进行两次融合,通过对NSST域的近似系数和DWT域的融合近似系数及融合细节系数进行逆变换重建融合图像。实验结果表明,该方法能够得到更高质量的融合图像并且计算开销不大,可以有助于更好的医疗诊断。

The main purpose of medical image fusion is to obtain a high resolution image with as much details as possible for diagnosis. Magnetic resonance(MR) and computed tomography(CT) medical images has special sophisticated and complementary characteristics which are required for accurate diagnosis of disease. Based on this, a new medical fusion approach for MR and CT images based on multi-scale coefficient decomposition framework was proposed. The proposed approach used a combination of discrete wavelet and non-subsampled shearlet transforms for the initial multi-scale decompositions firstly. The decomposition multi-scale coefficients were fused twice using various local activity measures. The fused image was reconstructed by inverse transform of the approximation coefficients in the NSST domain and inverse wavelet transform of fused approximation and fused detail coefficients. The simulation results show that, compared with the state-of-the-art method, the fusion image with higher quality and less computation overhead which can be helpful for better medical diagnosis is obtained in the proposed method.