Search

In recent years, extensive multimodal medical image fusion algorithms have been proposed. However, existing methods are primarily based on specific transformation theories. There are many problems with existing algorithms, such as poor adaptability, low efficiency and blurry details. To address these problems, this paper proposes a generative adversarial network based on dual-stream attention mechanism (DSAGAN) for anatomical and functional image fusion. The dual-stream architecture and multiscale convolutions are utilized to extract deep features. In addition, the attention mechanism is utilized to further enhance the fused features. Then, the fusion images and multimodal input images are put into the discriminator . In the update stage of the discriminator, we expect to judge the multimodal images as real, and to judge the fusion images as fake. Furthermore, the fusion images are expected to be judged as real in the update stage of the generator, forcing the generator to improve the fusion quality. The training process continues until the generator and discriminator reach a Nash equilibrium . After training, the fusion images can be obtained directly after inputting anatomical and functional images. Compared with the reference algorithms , DSAGAN consumes less fusion time and achieves better objective metrics in terms of Q AG, QEN and QNIQE.

Secret sharing has a number of practical applications in network-based scenarios, such as key transfer protocols, attribute-based encryption and secure multiparty computation. However, existing secret sharing schemes cannot efficiently achieve fairness. They either rely on a trusted third party or require multiple rounds of communication. In this paper, we propose the first decentralized and fair hierarchical threshold secret sharing (HTSS) scheme using blockchain. In the scheme, secret shares are distributed to different levels of parties, and any authorized subset of parties can obtain the secret. We leverage a smart contract to force all participants to commit to the secret shares; otherwise, the committer either reveals his secret share within a certain time frame or pays a fine. Thus, unlike previous HTSS schemes, the participants can reconstruct the secret fairly using Birkhoff interpolation without a trusted party and complete the computation in one round. We formally prove that our scheme is secure. We evaluate the performance of the scheme by implementing our scheme on Ethereum’s official test network. Our experiments show that our scheme can run reasonably fast and is practical.

Large-scale group decision-making (LSGDM) has been widely studied to address increasingly complex decision-making problems. The consensus-reaching process is usually designed to reduce differences between decision-makers and achieve high-consensus decision results. Opinion adjustment is a good solution for promoting consensus, but there are always some decision-makers who refuse to adjust or make small compromises. Many noncooperative behaviors may exist in the consensus-reaching process. Traditional consensus-reaching models dealing with noncooperative behaviors focus on situations where only one decision-maker modifies his or her opinion in each consensus iteration. However, some, or even all, decision-makers may adjust their opinions in one iteration, especially at the beginning. In this study, a mixed consensus-reaching model for managing noncooperative behaviors is proposed. We first develop a novel method to calculate the weights of decision-makers in LSGDM environments. An independent consensus-reaching model is then put forward to address situations where multiple decision-makers modify their opinions in each iteration. By combining this independent consensus model with traditional consensus models, a mixed consensus model is constructed. Finally, a case study is used to show the feasibility and applicability of the proposed model, and a comparative analysis illustrates its advantages for managing noncooperative behaviors in LSGDM situations.

Replacing Computed tomography (CT) with magnetic resonance image (MRI), MRI- positron electron tomography (PET) or MRI- single photon emission computed tomography (SPECT) imaging might have further advantages due to higher soft-tissue contrast of brain structure and lower dose absorbed by the patient. In this paper, a new three-layer (intensity, detail, and base layers) medical image fusion method with differential features for gray and pseudo-color images is proposed. The proposed method includes three steps. At the first step, differential feature by structure tensor is used to decompose the anatomical MRI medical image into its three-layer image representation. On the other side, differential feature by color tensor is adopted to decompose the functional PET or SPECT medical image into its three-layer image representation. At the second step, spatial frequency metric is proposed to combine the decomposed intensity layers and detail layers and absolute maximum is defined as the image fusion rule of the base layers. At the third step, the fused image is obtained by the addition of the fused intensity layer, the fused detail layer, and the fused base layer. The superiority of the proposed method is demonstrated by subjective and objective evaluation on experimental results.

Because of the complexity of real-world problems , large-scale group decision making has become a research topic of great interest in the field of decision science. Differences of opinion in a large group are highly likely. Sometimes, decision makers are unwilling to adjust their opinions to promote consensus. It is hence necessary to establish a consensus model for the effective management of opinion differences and non-cooperative behaviors. More importantly, the credibility of the adjustment information must be ensured. In this paper, we present a confidence consensus-based model for large-scale group decision making that provides a novel approach to addressing non-cooperative behaviors. First, some new concepts are proposed, including the collective adjustment suggestion and rationality degree. Then, we combine the rationality and non-cooperation of the adjustment information to construct the concept of a confidence level. This confidence level measures the impartiality and objectivity of the adjustment information and is the basis for managing non-cooperative behaviors. We then establish a mechanism for addressing non-cooperative behaviors. Finally, we present a case study that illustrates that the proposed model is feasible and effective. A comparative analysis reveals the features and advantages of this model for managing large-scale group decision making.

Finding and constructing Boolean functions with many cryptographic properties to resist a variety of existing attacks are challenging tasks in current cryptography and information security. The key idea in this paper consists of finding a general formula for computing the number of orbits with the same length and Hamming weight by utilizing prime factorization for any integer n greater than 1. Using the property of an orthogonal array to turn the construction of 1-resilient rotation symmetric Boolean functions (RSBFs) on n variables into the solution of a linear system of equations, a complete characterization and a general construction method of this class of functions are also presented. Moreover, a formula for counting the number of functions of this class is found. Not only are the structures of all 1-resilient RSBFs that are obtained more clear, such problems regarding their construction and count are completely and exhaustively solved. In addition, our methods are simpler than existing methods. We provide the exact numbers of 1-resilient RSBFs having ten and 11 variables, which are 162091449508441568747323063140 and 403305984734393392122612918710214418571734777982178890, respectively. Finally, we use three examples to illustrate the application of our methods.

An efficient method is proposed for fusion of anatomical and functional images by constructing the fused image through the combination of parallel saliency features in a multi-scale domain. First, the anatomical and functional images are decomposed into a series of smooth layers and detail layers at different scales by the average filter. Second, the parallel saliency features of both sharp edge and color detail are extracted to obtain the saliency maps. The edge saliency weighted map aims to preserve the high-spatial-resolution structural information using the Canny edge detection operator, while the color saliency weighted map extracts the high-intensity color detail using the context-aware operator. Finally, the fused image is reconstructed by the fused smooth layers and the fused detail layers using saliency maps. We demonstrate the application of the proposed method to a medical problem: Alzheimer's disease. Experimental results show that the proposed method for fusion of MRI-CBV and SPECT-Tc images and fusion of MRI-T1 and PET-FDG images successfully presents the pleasing fused medical images with high-spatial-resolution anatomical structural boundaries and high-intensity color detail.