Underwater image super-resolution using multi-stage information distillation networks

Recently, single image super-resolution (SISR) has been widely applied in the fields of underwater robot vision and obtained remarkable performance. However, most current methods generally suffered from the problem of a heavy burden on computational resources with large model sizes, which limited their real-world underwater robotic applications. In this paper, we introduce and tackle the super resolution (SR) problem for underwater robot vision and provide an efficient solution for near real-time applications. We present a novel lightweight multi-stage information distillation network, named MSIDN, for better balancing performance against applicability, which aggregates the local distilled features from different stages for more powerful feature representation. Moreover, a novel recursive residual feature distillation (RRFD) module is constructed to progressively extract useful features with a modest number of parameters in each stage. We also propose a channel interaction & distillation (CI&D) module that employs channel split operation on the preceding features to produce two-part features and utilizes the inter channel-wise interaction information between them to generate the distilled features, which can effectively extract the useful information of current stage without extra parameters. Besides, we present USR-2K dataset, a collection of over 1.6K samples for large-scale underwater image SR training, and a testset with an additional 400 samples for benchmark evaluation. Extensive experiments on several standard benchmark datasets show that the proposed MSIDN can provide state-of-the-art or even better performance in both quantitative and qualitative measurements.     

WavNet — Visual saliency detection using Discrete Wavelet Convolutional Neural Network

In the recent advancements in image and video analysis, the detection of salient regions in the image becomes the initial step. This plays a crucial role in deciding the performance of such algorithms. In this work, a Multi-Resolution Feature Extraction (MRFE) technique that makes use of Discrete Wavelet Convolutional Neural Network (DWCNN) for generating features is employed. An Enhanced Feature Extraction (EFE) module extracts additional features from the high level features of the DWCNN, which are used to frame both channel as well as spatial attention models for yielding contextual attention maps. A new hybrid loss function is also proposed, which is a combination of Balanced Cross Entropy (BCE) loss and Edge based Structural Similarity (ESSIM) loss that effectively identifies and segments the salient regions with clear boundaries. The method is tested exhaustively with five different benchmark datasets and is proved superior to the existing state-of-the-art methods with a minimum Mean Absolute error (MAE) of 0.03 and F-measure of 0.956.     

Preparation and Evaluation of a Self-Nanoemulsifying Drug Delivery System Loaded with Heparin Phospholipid Complex

A self-nanoemulsifying drug delivery system (SNEDDS) was developed to enhance the absorption of heparin after oral administration, in which heparin was compounded with phospholipids to achieve better fat solubility in the form of heparin-phospholipid (HEP-Pc) complex. HEP-Pc complex was prepared using the solvent evaporation method, which increased the solubility of heparin in n-octanol. The successful preparation of HEP-Pc complex was confirmed by differential scanning calorimetry (DSC), Fourier-transform infrared (FT-IR) spectroscopy, NMR, and SEM. A heparin lipid microemulsion (HEP-LM) was prepared by high-pressure homogenization and characterized. HEP-LM can enhance the absorption of heparin after oral administration, significantly prolong activated partial thromboplastin time (APTT) and thrombin time (TT) in mice, and reduce fibrinogen (FIB) content. All these outcomes indicate that HEP-LM has great potential as an oral heparin formulation.     

Portrait of Cancer Stem Cells on Colorectal Cancer: Molecular Biomarkers,Signaling Pathways and miRNAome

Colorectal cancer (CRC) is a leading cause of cancer death worldwide, and about 20% is metastatic at diagnosis and untreatable. Increasing evidence suggests that the heterogeneous nature of CRC is related to colorectal cancer stem cells (CCSCs), a small cells population with stemness behaviors and responsible for tumor progression, recurrence, and therapy resistance. Growing knowledge of stem cells (SCs) biology has rapidly improved uncovering the molecular mechanisms and possible crosstalk/feedback loops between signaling pathways that directly influence intestinal homeostasis and tumorigenesis. The generation of CCSCs is probably connected to genetic changes in members of signaling pathways, which control self-renewal and pluripotency in SCs and then establish function and phenotype of CCSCs. Particularly, various deregulated CCSC-related miRNAs have been reported to modulate stemness features, controlling CCSCs functions such as regulation of cell cycle genes expression, epithelial-mesenchymal transition, metastasization, and drug-resistance mechanisms. Primarily, CCSC-related miRNAs work by regulating mainly signal pathways known to be involved in CCSCs biology. This review intends to summarize the epigenetic findings linked to miRNAome in the maintenance and regulation of CCSCs, including their relationships with different signaling pathways, which should help to identify specific diagnostic, prognostic, and predictive biomarkers for CRC, but also develop innovative CCSCs-targeted therapies.     

基于卷积神经网络的安全防御模式研究

云计算、大数据、5G通信等技术的快速发展，有力的促进了计算机网络在多个领域的普及和使用，人们已经进入到了“互联网+”时代，实现了工作、生活和学习的数字化、智能化和共享化。计算机网络在为人们提供各种便利服务的同时也面临着许多的安全威胁，比如木马、病毒等，不法分子攻击网络数据中心，破坏用户服务终端及服务器，为人们带来严重的威胁。网络安全学者或企业机构也提出了许多安全防御技术，比如入侵检测技术、深度包过滤技术、防火墙技术、数据加密技术等，一定程度上提高了网络安全防御的能力，但是随着互联网数据流量的增多，需要引入更加先进的人工智能技术，以便能够快速的采集、分析网络数据流，确定数据流中是否存在病毒或木马，以便及时的对其进行查杀，进一步提高网络安全防御的主动性、积极性     

Recent Advances in Design of Functional Biocompatible Hydrogels for Bone Tissue Engineering

Bone related diseases have caused serious threats to human health owing to their complexity and specificity. Fortunately, owing to the unique 3D network structure with high aqueous content and functional properties, emerging hydrogels are regarded as one of the most promising candidates for bone tissue engineering, such as repairing cartilage injury, skull defect, and arthritis. Herein, various design strategies and synthesis methods (e.g., 3D-printing technology and nanoparticle composite strategy) are introduced to prepare implanted hydrogel scaffolds with tunable mechanical strength, favorable biocompatibility, and excellent bioactivity for applying in bone regeneration. Injectable hydrogels based on biocompatible materials (e.g., collagen, hyaluronic acid, chitosan, polyethylene glycol, etc.) possess many advantages in minimally invasive surgery, including adjustable physicochemical properties, filling irregular shapes of defect sites, and on-demand release drugs or growth factors in response to different stimuli (e.g., pH, temperature, redox, enzyme, light, magnetic, etc.). In addition, drug delivery systems based on micro/nanogels are discussed, and its numerous promising designs used in the application of bone diseases (e.g., rheumatoid arthritis, osteoarthritis, cartilage defect) are also briefed in this review. Particularly, several key factors of hydrogel scaffolds (e.g., mechanical property, pore size, and release behavior of active factors) that can induce bone tissue regeneration are also summarized in this review. It is anticipated that advanced approaches and innovative ideas of bioactive hydrogels will be exploited in the clinical field and increase the life quality of patients with the bone injury.     

Enzyme-Activated Prodrug-Based Smart Liposomes Specifically Enhance Tumor Hemoperfusion with Efficient Drug Delivery to Pancreatic Cancer Cells and Stellate Cells

Tumor-specific enhanced delivery of chemotherapeutics and modulators to tumor cells and activated pancreatic stellate cells (aPSCs), respectively, represents safer and more effective therapy for pancreatic cancer. Herein, a membrane type 1-matrix metalloproteinase (MT1-MMP)-cleavable spacer is used to assemble low-density cRGDfK onto thermosensitive liposomes loaded with phosphorylated calcipotriol (PCAL) and doxorubicin (DOX), yielding MR-T-PD. The liposome-linked cRGDfK prodrug on MR-T-PD surface is first activated by MT1-MMP, which is selectively expressed on tumor endothelial cells, to release cRGDfK. The free cRGDfK specifically promotes tumor angiogenesis, leading to 3.4-fold higher accumulation and a wider distribution of MR-T-PD in tumors. Furthermore, MR-T-PD rapidly releases PCAL and DOX into the interstitium under heat treatment. The released DOX enters tumor cells to induce apoptosis, whereas the PCAL prodrug is converted to CAL by alkaline phosphatase on the surface of aPSCs; CAL can then enter aPSCs to induce quiescence and promote the antitumor effect of DOX. Finally, by enhancing the exposure of DOX and CAL to tumor cells and aPSCs, respectively, in a tumor-specific manner, MR-T-PD exerts superior efficacy (a 5.9-fold decrease in tumor weight) without causing additional side effects. Overall, this prodrug-based smart liposome system represents a promising paradigm for pancreatic cancer therapy.     

Targeted Delivery of Anesthetic Agents to Bone Tissues using Conductive Microneedles Enhanced Iontophoresis for Painless Dental Anesthesia

Pain management during dental procedures is a cornerstone for successful daily practice. In current practice, the traditional needle and syringe injection is used to administer local anesthesia. However, the appearance of long needles and the pain associated with it often leads to dental anxiety deterring timely interventions. Microneedles (MNs) have emerged as a minimally invasive alternative to hypodermic needles and shown to be effective in transdermal drug delivery applications. In this article, the potential use of MNs for local anesthesia delivery in dentistry is explored. The development of a novel conductive MN array that can be used in combination with iontophoresis technique to achieve drug penetration through the oral mucosa and the underlying bone tissue is presented. The conductive MN array plays a dual-role, creating micro-conduits and lowering the resistance of the oral mucosa. The reduced tissue resistance further enhances the application of a low-voltage current that is able to direct and accelerate the drug molecules to target the sensory nerves supplying teeth. The successful delivery of lidocaine using this new strategy in a clinically relevant rabbit incisor model is shown to be as effective as the current gold standard.     

Investigation on thermal conductivity and mechanical properties of Si3N4 ceramics via one-step sintering

High thermal conductivity Si₃N₄ ceramics were fabricated using a one-step method consisting of reaction-bonded Si₃N₄ (RBSN) and post-sintering. The influence of Si content on nitridation rate, β/(α+β) phase rate, thermal conductivity and mechanical properties was investigated in this work. It is of special interest to note that the thermal conductivity showed a tendency to increase first and then decrease with increasing Si content. This experimental result shows that the optimal thermal conductivity and fracture toughness were obtained to be 66 W (m K)^-1 and 12.0 MPa m^1/2, respectively. As a comparison, the nitridation rate and β/(α+β) phase rate in a static pressure nitriding system, i.e., 97% (MS10), 97% (MS15), 97% (MS20) and 8.3% (MS10), 8.3% (MS15), 8.9% (MS20), respectively, have obvious advantages over those in a flowing nitriding system, i.e., 91% (MS10), 91% (MS15), 93% (MS20) and 3.1% (MS10), 3.3% (MS15), 3.3% (MS20), respectively. Moreover, high lattice integrity of the β-Si₃N₄ phase was observed, which can effectively confine O atoms into the β-Si₃N₄ lattice using MgO as a sintering additive. This result indicates that one-step sintering can provide a new route to prepare Si₃N₄ ceramics with a good combination of thermal conductivity and mechanical properties.