Scheme Based on Multi-Level Patch Attention and Lesion Localization for Diabetic Retinopathy Grading

Early screening of diabetes retinopathy(DR)plays an important role in preventing irreversible blindness.Existing research has failed to fully explore effective DR lesion information in fundus maps.Besides,traditional attention schemes have not considered the impact of lesion type differences on grading,resulting in unreasonable extraction of important lesion features.Therefore,this paper proposes a DR diagnosis scheme that integrates a multi-level patch attention generator(MPAG)and a lesion localization module(LLM).Firstly,MPAGis used to predict patches of different sizes and generate a weighted attention map based on the prediction score and the types of lesions contained in the patches,fully considering the impact of lesion type differences on grading,solving the problem that the attention maps of lesions cannot be further refined and then adapted to the final DR diagnosis task.Secondly,the LLM generates a global attention map based on localization.Finally,the weighted attention map and global attention map are weighted with the fundus map to fully explore effective DR lesion information and increase the attention of the classification network to lesion details.This paper demonstrates the effectiveness of the proposed method through extensive experiments on the public DDR dataset,obtaining an accuracy of 0.8064.

DoS Attack Detection Based on Deep Factorization Machine in SDN

Software-Defined Network(SDN)decouples the control plane of network devices from the data plane.While alleviating the problems presented in traditional network architectures,it also brings potential security risks,particularly network Denial-of-Service(DoS)attacks.While many research efforts have been devoted to identifying new features for DoS attack detection,detection methods are less accurate in detecting DoS attacks against client hosts due to the high stealth of such attacks.To solve this problem,a new method of DoS attack detection based on Deep Factorization Machine(DeepFM)is proposed in SDN.Firstly,we select the Growth Rate of Max Matched Packets(GRMMP)in SDN as detection feature.Then,the DeepFM algorithm is used to extract features from flow rules and classify them into dense and discrete features to detect DoS attacks.After training,the model can be used to infer whether SDN is under DoS attacks,and a DeepFM-based detection method for DoS attacks against client host is implemented.Simulation results show that our method can effectively detect DoS attacks in SDN.Compared with the K-Nearest Neighbor(K-NN),Artificial Neural Network(ANN)models,Support Vector Machine(SVM)and Random Forest models,our proposed method outperforms in accuracy,precision and F1 values.

Oxidative stress: A critical hint in ionizing radiation induced pyroptosis

Reactive oxygen species(ROS)are a group of oxygen-containing free radicals and peroxygenic compounds,which are important substances in the maintenance of normal physiological functions of the body.Excessive ROS destroy the REDOX balance of the body and cause oxidative damage.Ionizing radiation(IR)is an important source of exogenous ROS and an important pathway for endogenous ROS production in the body.The continuous activation and increase in endogenous and exogenous ROS destroys the body’s antioxidant system and stimulates the production of more ROS to form a cascade of amplified inflammatory responses,which ultimately lead to cell death.Pyroptosis is a programmed death process involved in natural immunity,and closely related to the ROS level of the body.Whether pyroptosis is related to IR is still unknown.The present paper reported the effects of IR and pyroptosis on the production and development of ROS to clarify the relationship between ROS,IR and pyroptosis and provide novel ideas for radiation damage,a potential direction for pyroptosis,and an updated connotation for oxidative stress.

Add-on plasmonic patch as a universal fluorescence enhancer

Fluorescence-based techniques are the cornerstone of modern biomedical optics,with applications ranging from bioimaging at various scales(organelle to organism)to detection and quantification of a wide variety of biological species of interest.However,the weakness of the fluorescence signal remains a persistent challenge in meeting the ever-increasing demand to image,detect,and quantify biological species with low abundance.Here,we report a simple and universal method based on a flexible and conformal elastomeric film with adsorbed plasmonic nanostructures,which we term a“plasmonic patch,”that provides large(up to 100-fold)and uniform fluorescence enhancement on a variety of surfaces through simple transfer of the plasmonic patch to the surface.We demonstrate the applications of the plasmonic patch in improving the sensitivity and limit of detection(by more than 100 times)of fluorescence-based immunoassays implemented in microtiter plates and in microarray format.The novel fluorescence enhancement approach presented here represents a disease,biomarker,and application agnostic ubiquitously applicable fundamental and enabling technology to immediately improve the sensitivity of existing analytical methodologies in an easy-to-handle and cost-effective manner,without changing the original procedures of the existing techniques.