At present, multimodal medical image fusion technology has become an essential means for researchers and doctors to predict diseases and study pathology. Nevertheless, how to reserve more unique features from different modal source images on the premise of ensuring time efficiency is a tricky problem. To handle this issue, we propose a flexible semantic-guided architecture with a mask-optimized framework in an end-to-end manner, termed as GeSeNet. Specifically, a region mask module is devised to deepen the learning of important information while pruning redundant computation for reducing the runtime. An edge enhancement module and a global refinement module are presented to modify the extracted features for boosting the edge textures and adjusting overall visual performance. In addition, we introduce a semantic module that is cascaded with the proposed fusion network to deliver semantic information into our generated results. Sufficient qualitative and quantitative comparative experiments (i.e., MRI-CT, MRI-PET, and MRI-SPECT) are deployed between our proposed method and ten state-of-the-art methods, which shows our generated images lead the way. Moreover, we also conduct operational efficiency comparisons and ablation experiments to prove that our proposed method can perform excellently in the field of multimodal medical image fusion. The code is available at https://github.com/lok-18/GeSeNet.

This paper presents a dynamic deoxyribonucleic acid (DNA) image encryption based on Secure Hash Algorithm-512 (SHA-512), having the structure of two rounds of permutation–diffusion, by employing two chaotic systems, dynamic DNA coding, DNA sequencing operations, and conditional shifting. We employed the SHA-512 algorithm to generate a 512-bit hash value and later utilized this value with the natural DNA sequence to calculate the initial values for the chaotic systems and the eight intermittent parameters. We implemented a two-dimensional rectangular transform (2D-RT) on the permutation. We used four-wing chaotic systems and Lorentz systems to generate chaotic sequences and recombined three channel matrices and chaotic matrices with intermittent parameters. We calculated hamming distances of DNA matrices, updated the initial values of two chaotic systems, and generated the corresponding chaotic matrices to complete the diffusion operation. After diffusion, we decoded and decomposed the DNA matrices, and then scrambled and merged these matrices into an encrypted image. According to experiments, the encryption method in this paper not only was able to withstand statistical attacks, plaintext attacks, brute-force attacks, and a host of other attacks, but also could reduce the complexity of the algorithm because it adopted DNA sequencing operations that were different from traditional DNA sequencing operations.

Nowadays, deep learning has made rapid progress in the field of multi-exposure image fusion. However, it is still challenging to extract available features while retaining texture details and color. To address this difficult issue, in this paper, we propose a coordinated learning network for detail-refinement in an end-to-end manner. Firstly, we obtain shallow feature maps from extreme over/under-exposed source images by a collaborative extraction module. Secondly, smooth attention weight maps are generated under the guidance of a self-attention module, which can draw a global connection to correlate patches in different locations. With the cooperation of the two aforementioned used modules, our proposed network can obtain a coarse fused image. Moreover, by assisting with an edge revision module, edge details of fused results are refined and noise is suppressed effectively. We conduct subjective qualitative and objective quantitative comparisons between the proposed method and twelve state-of-the-art methods on two available public datasets, respectively. The results show that our fused images significantly outperform others in visual effects and evaluation metrics. In addition, we also perform ablation experiments to verify the function and effectiveness of each module in our proposed method. The source code can be achieved at https://github.com/lok-18/LCNDR.

The image is one of the most important means to store information, and is widely used in every aspect of life. However, the characteristics of images enable them to be easily stolen, tampered with, and copied. Researchers have proposed many encryption methods, with most applying only to traditional digital images. There are few encryption methods for quantum images, and quantum image-oriented encryption technology has begun to attract researchers’ attention. This study proposes a quantum image encryption method based on DNA Controlled-Not (DNACNot). Based on the quantum image information, encryption parameters are obtained and transferred as part of a chaotic initial key. Two natural DNA sequences are amplified to obtain the DNA coordinate sequence, and a modified chaos game representation is used to modify the DNA coordinate sequence, which is then used to correct the sequence generated by chaos. The resulting sequence is converted to an integer sequence to obtain DNACNot. A controlled-not operation is performed between DNACNot and the quantum image is scrambled by bit-plane to obtain the encrypted image. The encryption method has high security, a good encryption effect, and a large key space. The method can effectively resist exhaustive, statistical, and differential attacks. The algorithm is easy to implement at a low cost. The encryption time of our proposed method is satisfactory, and the method is suitable for real-time encryption. Moreover, the encryption results can be transmitted over the internet and stored in the cloud.