BMCS-Net: A Bi-directional multi-scale cascaded segmentation network based on transformer-guided feature Aggregation for medical images.

convolutional neural networks (CNNs) show great potential in medical image segmentation tasks, and can provide reliable basis for disease diagnosis and clinical research. However, CNNs exhibit general limitations on modeling explicit long-range relation, and existing cures, resorting to building deep encoders along with aggressive downsampling operations, leads to loss of localized details. Transformer has naturally excellent ability to model the global features and long-range correlations of the input information, which is strongly complementary to the inductive bias of CNNs. In this paper, a novel Bi-directional Multi-scale Cascaded Segmentation Network, BMCS-Net, is proposed to improve the performance of medical segmentation tasks by aggregating these features obtained from Transformers and CNNs branches. Specifically, a novel feature integration technique, termed as Two-stream Cascaded Feature Aggregation (TCFA) module, is designed to fuse features in two-stream branches, and solve the problem of gradual dilution of global information in the network. Besides, a Multi-Scale Expansion-Aware (MSEA) module based on the convolution of feature perception and expansion is introduced to capture context information, and further compensate for the loss of details. Extensive experiments demonstrated that BMCS-Net has an excellent performance on both skin and Polyp segmentation datasets.

HyperTDP-Net: A Hyper-densely Connected Compression-and-Decomposition Network Based on Trident Dilated Perception for PET and MRI Image Fusion.

Objective. Since medical images generated by medical devices have low spatial resolution and quality, fusion approaches on medical images can generate a fused image containing a more comprehensive range of different modal features to help physicians accurately diagnose diseases. Conventional methods based on deep learning for medical image fusion usually extract only local features without considering their global features, which often leads to the problem of unclear detail information in the final fused image. Therefore, medical image fusion is a challenging task of great relevance.Approach.This paper proposes a novel end-to-end medical image fusion model for PET and MRI images to achieve information interaction between different pathways, termed as hyper-densely connected compression-and-decomposition network based on trident dilated perception for PET and MRI image fusion (HyperTDP-Net). In particular, in the compression network, a dual residual hyper densely module is constructed to take full advantage of middle layer information. Moreover, we establish the trident dilated perception module to precisely determine the location information of features, and improve the feature representation capability of the network. In addition, we abandon the ordinary mean square error as the content loss function and propose a new content-aware loss consisting of structural similarity loss and gradient loss, so that the fused image not only contains rich texture details but also maintains sufficient structural similarity with the source images.Main results. The experimental dataset used in this paper is derived from multimodal medical images published by Harvard Medical School. Extensive experiments illustrate that our model contains more edge information and texture detail information in the fusion result than the 12 state-of-the-art fusion models and ablation study results demonstrate the effectiveness of three technical innovations.Significance. As medical images continue to be used in clinical diagnosis, our method is expected to be a tool that can effectively improve the accuracy of physician diagnosis and automatic machine detection.

Nonrigid Medical Image Registration Using an Information Theoretic Measure Based on Arimoto Entropy with Gradient Distributions.

This paper introduces a new nonrigid registration approach for medical images applying an information theoretic measure based on Arimoto entropy with gradient distributions. A normalized dissimilarity measure based on Arimoto entropy is presented, which is employed to measure the independence between two images. In addition, a regularization term is integrated into the cost function to obtain the smooth elastic deformation. To take the spatial information between voxels into account, the distance of gradient distributions is constructed. The goal of nonrigid alignment is to find the optimal solution of a cost function including a dissimilarity measure, a regularization term, and a distance term between the gradient distributions of two images to be registered, which would achieve a minimum value when two misaligned images are perfectly registered using limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) optimization scheme. To evaluate the test results of our presented algorithm in non-rigid medical image registration, experiments on simulated three-dimension (3D) brain magnetic resonance imaging (MR) images, real 3D thoracic computed tomography (CT) volumes and 3D cardiac CT volumes were carried out on elastix package. Comparison studies including mutual information (MI) and the approach without considering spatial information were conducted. These results demonstrate a slight improvement in accuracy of non-rigid registration.

Double color image encryption using iterative phase retrieval algorithm in quaternion gyrator domain.

This paper describes a novel algorithm to encrypt double color images into a single undistinguishable image in quaternion gyrator domain. By using an iterative phase retrieval algorithm, the phase masks used for encryption are obtained. Subsequently, the encrypted image is generated via cascaded quaternion gyrator transforms with different rotation angles. The parameters in quaternion gyrator transforms and phases serve as encryption keys. By knowing these keys, the original color images can be fully restituted. Numerical simulations have demonstrated the validity of the proposed encryption system as well as its robustness against loss of data and additive Gaussian noise.

Rac1 signaling stimulates N-cadherin expression, mesenchymal condensation, and chondrogenesis.

The molecular mechanisms controlling differentiation of mesenchymal precursor cells into chondrocytes (chondrogenesis) are not completely understood. We have recently shown that the small GTPase RhoA inhibits this process. Here we demonstrate that a different Rho GTPase family member, Rac1, promotes chondrogenesis. Pharmacological inhibition of Rac1 expression in micromass culture resulted in reduced mRNA levels of the chondrogenic markers collagen II and aggrecan, and decreased accumulation of glycosaminoglycans. Expression of the essential chondrogenic transcription factors Sox9, Sox5, and Sox6 was also reduced upon inhibition of Rac1 signaling. In contrast, overexpression of Rac1 in the chondrogenic ATDC5 cell line increased mRNA transcripts of Sox9, 5, and 6, collagen II, and aggrecan. Inhibition of Rac1 resulted in a reduction in the number, size, and organization of cellular condensations and decreased expression of N-cadherin. Overexpression of Rac1 resulted in an increase in N-cadherin expression levels. Furthermore, genetic ablation of Rac1 in primary micromass cultures resulted in reduced expression of chondrogenic markers. Additionally, we provide evidence that Cdc42 also promotes chondrogenesis. Overexpression of Cdc42 in ATDC5 cells resulted in increased expression of Sox5, Sox9, and collagen II but not Sox6, aggrecan, or N-cadherin. Therefore, we demonstrate that Rac1 and Cdc42 are positive regulators of chondrogenesis, but act at least in part through different cellular and molecular mechanisms.

Myxoma virus M063R is a host range gene essential for virus replication in rabbit cells.

The myxoma virus M063R gene product exhibits some sequence similarity to the poxvirus host range gene, C7L, of vaccinia virus. To address the potential host range function of the M063R gene product in rabbits, a deletion mutant of myxoma virus (vMyx63KO) was generated and characterized. vMyx63KO replicated to normal titre levels and produced foci that were indistinguishable from those produced by MV in vitro in a monkey kidney cell line (BGMK) that are permissive for wild type MV. However, vMyx63KO failed to replicate in all rabbit cell lines tested, including both primary and established cells lines, as well as cells derived from a variety of tissues. M063R expression was not required for myxoma virus binding, entry or early gene expression, whereas DNA replication was aborted and late genes were not expressed in vMyx63KO infected rabbit cells. Thus, the replication block for vMyx63KO in rabbit cells preceded the stage of late gene expression and DNA replication. Finally, an in vivo pathogenesis study indicated that vMyx63KO failed to cause any signs of classic myxomatosis in infected rabbits, but functioned as a non-replicating vaccine and provided protection for subsequent challenge by wild type myxoma virus. Altogether, these observations demonstrate that M063R plays a critical role in determining the host specificity of myxoma virus in rabbit cells.

M135R is a novel cell surface virulence factor of myxoma virus.

Myxoma virus (MV) encodes a cell surface protein (M135R) that is predicted to mimic the host alpha/beta interferon receptor (IFN-alpha/beta-R) and thus prevent IFN-alpha/beta from triggering a host antiviral response. This prediction is based on sequence similarity to B18R, the viral IFN-alpha/beta-R from vaccinia virus (VV), which has been demonstrated to bind and inhibit type I interferons. However, M135R is only half the size of VV B18R. All other poxvirus-encoded IFN-alpha/beta-R homologs align only to the amino-terminal half of M135R. Peptide antibodies raised against M135R were used for immunoblotting and immunofluorescence and indicate that M135R is expressed as an early gene and that the product is a cell surface N-linked glycoprotein that is not secreted. In contrast to the predicted properties of M135R as an inhibitor of type I interferon, all binding and inhibition assays designed to demonstrate whether M135R can interact with IFN-alpha/beta have been negative. However, pathogenesis studies with a targeted M135-knockout MV construct (vMyx135KO) indicate that the deletion of M135R severely attenuates MV pathogenesis in the European rabbit. We propose that M135R is an important immunomodulatory virulence factor for myxomatosis but that the target immune ligand is not from the predicted type I interferon family and remains to be identified.