Wang Zhaobin, Cui Zijing, Zhu Ying
School of Information Science and Engineering, Lanzhou University, Lanzhou, 730000, China.
School of Information Science and Engineering, Lanzhou University, Lanzhou, 730000, China.
Comput Biol Med. 2020 Aug;123:103823. doi: 10.1016/j.compbiomed.2020.103823. Epub 2020 Jun 20.
Multi-modal medical image fusion refers to the fusion of two or more medical images obtained by different imaging methods into one image. Multi-modal medical images contain a lot of useful information that helps doctors to make a diagnosis. In this study, a multi-modal medical image fusion method is proposed based on Laplacian pyramid (LP) decomposition and adaptive sparse representation (ASR). ASR was used to reduce the noise of high-frequency information in the image fusion process and it did not need a high redundancy dictionary as traditional sparse representation (SR) methods. The proposed fusion method first used the LP decomposition to split medical images into four images of different sizes. Then ASR was performed to fuse the decomposed four layers, respectively. Finally, the fused image was obtained by the inverse Laplace pyramid transform. Experimental results showed that the proposed method could effectively fuse the medical images with the detailed information perfectly integrated, and could also reduce the influences of artifacts, noise and block effect. The research results are of great significance in the field of medical image fusion.
多模态医学图像融合是指将通过不同成像方法获得的两幅或多幅医学图像融合为一幅图像。多模态医学图像包含许多有助于医生进行诊断的有用信息。在本研究中，提出了一种基于拉普拉斯金字塔（LP）分解和自适应稀疏表示（ASR）的多模态医学图像融合方法。在图像融合过程中，ASR用于降低高频信息的噪声，并且它不需要像传统稀疏表示（SR）方法那样的高冗余字典。所提出的融合方法首先使用LP分解将医学图像分割成四个不同大小的图像。然后分别对分解后的四层进行ASR融合。最后，通过拉普拉斯金字塔逆变换获得融合图像。实验结果表明，该方法能够有效地融合医学图像，使详细信息完美整合，同时还能减少伪影、噪声和块效应的影响。研究结果在医学图像融合领域具有重要意义。
