Image fusion meets deep learning: A survey and perspective

An infrared and visible image fusion method based on multi-scale transformation and norm optimization

The fusion of multi-modal medical images makes a significant contribution to clinical diagnosis and analysis because it allows diagnostic imaging practitioners to make a more accurate diagnosis. According to our current knowledge, there are some limitations of current medical image fusion approaches. The first limitation is that the use of a weighted average rule for fusing low-frequency components. This limitation leads to a decrease in the intensity of the brightness of the fused image. The second limitation is that the utilizing of fusion rules for high-frequency components is not really optimal. This is likely to result in the loss of detailed information in the fused image. In this paper, a novel approach, including two algorithms, is proposed to address the above-mentioned limitations. The first algorithm is based on the Grasshopper optimization algorithm (GOA) to find optimal parameters with the aim of fusing low-frequency components. This allows the fused image to have good contrast. The second algorithm is based on the Kirsch compass operator to create an efficient rule for the fusion of high-frequency components. This allows the fused image to significantly preserve details transferred from input images. Experimental results show that the proposed approach not only effective in enhancing significantly the contrast of the fused image but also preserving edge information carried from input images to the composite image.

A novel approach based on Grasshopper optimization algorithm for medical image fusion

A novel approach based on Three-scale image decomposition and Marine predators algorithm for multi-modal medical image fusion

Multi-modal medical image fusion brings many benefits to clinical diagnosis and analysis because it creates favorable conditions for diagnostic imaging practitioners to make a more accurate diagnosis. According to our current knowledge, there are still some disadvantages to current image fusion approaches. The first one is that the fused images often have low contrast. The reason for this is several approaches use a weighted average rule for fusing low-frequency components. The second drawback is that the loss of detailed information in the fused image. This can be explained by the fact that the high-frequency components synthesized by the rules are not really effective. In this paper, two novel algorithms are proposed to tackle the above two disadvantages. The first algorithm is based on the Equilibrium optimizer algorithm (EOA) to find optimal parameters to fuse low-frequency components. This allows the fused image to have good contrast. The second algorithm is based on the sum of local energy functions using the Prewitt compass operator to create an efficient rule for the fusion of high-frequency components. This allows the fused image to significantly preserve details transferred from input images. Experimental results show that the proposed approach not only effective in significantly enhancing the quality of the fusion image but also preserving edge information carried from input images.

Multi-modal medical image fusion based on equilibrium optimizer algorithm and local energy functions

Multi-focus image fusion: A Survey of the state of the art

Multi-focus image fusion with deep residual learning and focus property detection

In deep learning (DL)-based multifocus image fusion, effective multiscale feature learning is a key issue to promote fusion performance. In this article, we propose a novel DL model named multiscale feature interactive network (MSFIN), which can segment the source images into focused and defocused regions accurately by sufficient interaction of multiscale features from layers of different depths in the network for multifocus image fusion. Specifically, based on the popular encoder–decoder framework, two functional modules, namely, multiscale feature fusion (MSFF) and coordinate attention upsample (CAU), are designed for interactive multiscale feature learning. Moreover, the weighted binary cross-entropy (WBCE) loss and the multilevel supervision (MLS) strategy are introduced to train the network more effectively. Qualitative and quantitative comparisons with 19 representative multifocus image fusion methods demonstrate that the proposed method can achieve state-of-the-art performance. The code of our method is available at https://github.com/yuliu316316/MSFIN-Fusion .

Multiscale Feature Interactive Network for Multifocus Image Fusion

In order to meet the needs of Model-Based Systems Engineering (MBSE) development for aerospace products, a flow-driven R&D resource management and sharing mode was explored based on the existing MBSE design environment of the enterprise. In this way, resource management and sharing system can be constructed to realize collaborative development based on design process and resource fusion and sharing, and improve product development efficiency and innovation ability.

The Study of Design Resource Management and Sharing System Construction in Aviation Product MBSE Environment

To promote the rational use of cabozantinib (CBZ), this paper studied the influence of several nutritional supplements on the interaction between CBZ and bovine serum albumin (BSA), an appropriate alternative model for human serum albumin (HSA) which is one of the important transporter proteins in plasma, by fluorescence spectroscopy and UV-vis spectroscopy. The results showed that CBZ could quench the fluorescence of BSA via a dynamic-static quenching process, and the six nutritional supplements did not change the quenching mode of BSA by CBZ. However, all of them could reduce the binding constant of the CBZ-BSA system at 293 K and increase the polarity around tryptophan residues. Among them, nicotinamide and VB12 had a greater effect on the binding constants of the CBZ-BSA system. In the meantime, the thermodynamic parameters of the CBZ-BSA system were examined, indicating that the interaction of CBZ with BSA was spontaneous and dominated by hydrophobic forces. Further research discovered that the combining of CBZ with BSA was primarily located within site I of BSA, and the binding distance r was 2.48 nm. Consequently, while taking CBZ, patients should use carefully the VB12 and nicotinamide which maybe interfere with the transport of drugs.

Lei Wang

Papers

Multi-focus image fusion: A Survey of the state of the art

Multi-focus image fusion with deep residual learning and focus property detection

Multiscale Feature Interactive Network for Multifocus Image Fusion

The Study of Design Resource Management and Sharing System Construction in Aviation Product MBSE Environment

The influence of several nutritional supplements on the rational use of cabozantinib.