Zhu Rui, Li Xiongfei, Huang Sa, Zhang Xiaoli
Key Laboratory of Symbolic Computation and Knowledge Engineering, Ministry of Education, Jilin University, Changchun 130012, China.
College of Computer Science and Technology, Jilin University, Changchun 130012, China.
Bioinformatics. 2022 Jan 12;38(3):818-826. doi: 10.1093/bioinformatics/btab721.
Medical image fusion has developed into an important technology, which can effectively merge the significant information of multiple source images into one image. Fused images with abundant and complementary information are desirable, which contributes to clinical diagnosis and surgical planning.
In this article, the concept of the skewness of pixel intensity (SPI) and a novel adaptive co-occurrence filter (ACOF)-based image decomposition optimization model are proposed to improve the quality of fused images. Experimental results demonstrate that the proposed method outperforms 22 state-of-the-art medical image fusion methods in terms of five objective indices and subjective evaluation, and it has higher computational efficiency.
First, the concept of SPI is applied to the co-occurrence filter to design ACOF. The initial base layers of source images are obtained using ACOF, which relies on the contents of images rather than fixed scale. Then, the widely used iterative filter framework is replaced with an optimization model to ensure that the base layer and detail layer are sufficiently separated and the image decomposition has higher computational efficiency. The optimization function is constructed based on the characteristics of the ideal base layer. Finally, the fused images are generated by designed fusion rules and linear addition. The code and data can be downloaded at https://github.com/zhunui/acof.
Supplementary data are available at Bioinformatics online.
医学图像融合已发展成为一项重要技术，它能够有效地将多源图像的重要信息合并到一幅图像中。具有丰富且互补信息的融合图像是理想的，这有助于临床诊断和手术规划。
在本文中，提出了像素强度偏度（SPI）的概念以及一种基于新型自适应共生滤波器（ACOF）的图像分解优化模型，以提高融合图像的质量。实验结果表明，所提方法在五个客观指标和主观评价方面优于22种先进的医学图像融合方法，并且具有更高的计算效率。
首先，将SPI的概念应用于共生滤波器以设计ACOF。使用ACOF获得源图像的初始基础层，这依赖于图像内容而非固定尺度。然后，用一个优化模型取代广泛使用的迭代滤波器框架，以确保基础层和细节层充分分离且图像分解具有更高的计算效率。基于理想基础层的特征构建优化函数。最后，通过设计的融合规则和线性相加生成融合图像。代码和数据可在https://github.com/zhunui/acof下载。
补充数据可在《生物信息学》在线获取。
