A Cover-Independent Deep Image Hiding Method Based on Domain Attention Mechanism

Recently,deep image-hiding techniques have attracted considerable attention in covert communication and high-capacity information hiding.However,these approaches have some limitations.For example,a cover image lacks self-adaptability,information leakage,or weak concealment.To address these issues,this study proposes a universal and adaptable image-hiding method.First,a domain attention mechanism is designed by combining the Atrous convolution,which makes better use of the relationship between the secret image domain and the cover image domain.Second,to improve perceived human similarity,perceptual loss is incorporated into the training process.The experimental results are promising,with the proposed method achieving an average pixel discrepancy(APD)of 1.83 and a peak signal-to-noise ratio(PSNR)value of 40.72 dB between the cover and stego images,indicative of its high-quality output.Furthermore,the structural similarity index measure(SSIM)reaches 0.985 while the learned perceptual image patch similarity(LPIPS)remarkably registers at 0.0001.Moreover,self-testing and cross-experiments demonstrate the model’s adaptability and generalization in unknown hidden spaces,making it suitable for diverse computer vision tasks.

B^(2)C^(3)NetF^(2):Breast cancer classification using an end‐to‐end deep learning feature fusion and satin bowerbird optimization controlled Newton Raphson feature selection

Currently,the improvement in AI is mainly related to deep learning techniques that are employed for the classification,identification,and quantification of patterns in clinical images.The deep learning models show more remarkable performance than the traditional methods for medical image processing tasks,such as skin cancer,colorectal cancer,brain tumour,cardiac disease,Breast cancer(BrC),and a few more.The manual diagnosis of medical issues always requires an expert and is also expensive.Therefore,developing some computer diagnosis techniques based on deep learning is essential.Breast cancer is the most frequently diagnosed cancer in females with a rapidly growing percentage.It is estimated that patients with BrC will rise to 70%in the next 20 years.If diagnosed at a later stage,the survival rate of patients with BrC is shallow.Hence,early detection is essential,increasing the survival rate to 50%.A new framework for BrC classification is presented that utilises deep learning and feature optimization.The significant steps of the presented framework include(i)hybrid contrast enhancement of acquired images,(ii)data augmentation to facilitate better learning of the Convolutional Neural Network(CNN)model,(iii)a pre‐trained ResNet‐101 model is utilised and modified according to selected dataset classes,(iv)deep transfer learning based model training for feature extraction,(v)the fusion of features using the proposed highly corrected function‐controlled canonical correlation analysis approach,and(vi)optimal feature selection using the modified Satin Bowerbird Optimization controlled Newton Raphson algorithm that finally classified using 10 machine learning classifiers.The experiments of the proposed framework have been carried out using the most critical and publicly available dataset,such as CBISDDSM,and obtained the best accuracy of 94.5%along with improved computation time.The comparison depicts that the presented method surpasses the current state‐ofthe‐art approaches.

Design of axial flaps with color Doppler flow imaging technique for repairing deep wounds of heels

To report the methods and effect of axial pattern flap on lower limb in repairing deep wounds of heels by using color Doppler flow imaging (CDFI) technique so as to solve the ever before problems that the vessel can not be displayed in designing axial flap.Methods Suitable axial flaps on lower limbs were selected according to the character of the wounds.There were 25 flaps including 10 cases of the distal-based sural neurovascular flap,nine medial sole flap and six medial leg flap.All the axial pattern flaps were designed on the basis of traditional design ways before operation;then,CDFI appliance with high resolution was used to examine the starting spot,exterior diameter,trail and length of the flap’s major artery.The flaps were redesigned according to the results of CDFI and transferred to cover the wounds.In the meantime,both the results of operation and examination were compared.Results The major artery’s starting spot,exterior diameter,trail and anatomic layers were displayed clearly,in consistency with the results of operation.The flaps survived completely and recovered well,with perfect appearance,color and arthral function.Conclusion CDFI is a simple,macroscopic and atraumatic method for designing the axial pattern flap on lower limb,can provide more scientific and accurate evidence for preoperative determination of flap transplantation and is worthy of clinical application.10 refs,4 figs,2 tabs.

Classification of Domestic Refuse in Medical Institutions Based on Transfer Learning and Convolutional Neural Network

The problem of domestic refuse is becoming more and more serious with the use of all kinds of equipment in medical institutions.This matter arouses people’s attention.Traditional artificial waste classification is subjective and cannot be put accurately;moreover,the working environment of sorting is poor and the efficiency is low.Therefore,automated and effective sorting is needed.In view of the current development of deep learning,it can provide a good auxiliary role for classification and realize automatic classification.In this paper,the ResNet-50 convolutional neural network based on the transfer learning method is applied to design the image classifier to obtain the domestic refuse classification with high accuracy.By comparing the method designed in this paper with back propagation neural network and convolutional neural network,it is concluded that the CNN based on transfer learning method applied in this paper with higher accuracy rate and lower false detection rate.Further,under the shortage situation of data samples,the method with transfer learning and ResNet-50 training model is effective to improve the accuracy of image classification.

DSC based Dual-Resunet for radio frequency interference identification

Radio frequency interference(RFI)will pollute the weak astronomical signals received by radio telescopes,which in return will seriously affect the time-domain astronomical observation and research.In this paper,we use a deep learning method to identify RFI in frequency spectrum data,and propose a neural network based on Unet that combines the principles of depthwise separable convolution and residual,named DSC Based Dual-Resunet.Compared with the existing Unet network,DSC Based Dual-Resunet performs better in terms of accuracy,F1 score,and MIoU,and is also better in terms of computation cost where the model size and parameter amount are 12.5%of Unet and the amount of computation is 38%of Unet.The experimental results show that the proposed network is a high-performance and lightweight network,and it is hopeful to be applied to RFI identification of radio telescopes on a large scale.

Highly sensitive solar-blind deep ultraviolet photodetector based on graphene/PtSe_(2)/β-Ga_(2)O_(3)2D/3D Schottky junction with ultrafast speed

There is an emerging need for high-sensitivity solar-blind deep ultraviolet(DUV)photodetectors with an ultra-fast response speed.Although nanoscale devices based on Ga_(2)O_(3)nanostructures have been developed,their practical applications are greatly limited by their slow response speed as well as low specific detectivity.Here,the successful fabrication of two-/three-dimensional(2D/3D)graphene(Gr)/PtSe2/β-Ga_(2)O_(3)Schottky junction devices for high-sensitivity solar-blind DUV photodetectors is demonstrated.Benefitting from the high-quality 2D/3D Schottky junction,the vertically stacked structure,and the superior-quality transparent graphene electrode for effective carrier collection,the photodetector is highly sensitive to DUV light illumination and achieves a high responsivity of 76.2 mA/W,a large on/off current ratio of~105,along with an ultra-high ultraviolet(UV)/visible rejection ratio of 1.8×104.More importantly,it has an ultra-fast response time of 12µs and a remarkable specific detectivity of~1013 Jones.Finally,an excellent DUV imaging capability has been identified based on the Gr/PtSe2/β-Ga_(2)O_(3)Schottky junction photodetector,demonstrating its great potential application in DUV imaging systems.

Injectable and thermosensitive hydrogels mediating a universal macromolecular contrast agent with radiopacity for noninvasive imaging of deep tissues

It is very challenging to visualize implantable medical devices made of biodegradable polymers in deep tissues.Herein,we designed a novel macromolecular contrast agent with ultrahigh radiopacity(iodinate content>50%)via polymerizing an iodinated trimethylene carbonate monomer into the two ends of poly(ethylene glycol)(PEG).A set of thermosensitive and biodegradable polyester-PEG-polyester triblock copolymers with varied polyester compositions synthesized by us,which were soluble in water at room temperature and could spontaneously form hydrogels at body temperature,were selected as the demonstration materials.The addition of macromolecular contrast agent did not obviously compromise the injectability and thermogelation properties of polymeric hydrogels,but conferred them with excellent X-ray opacity,enabling visualization of the hydrogels at clinically relevant depths through X-ray fluoroscopy or Micro-CT.In a mouse model,the 3D morphology of the radiopaque hydrogels after injection into different target sites was visible using Micro-CT imaging,and their injection volume could be accurately obtained.Furthermore,the subcutaneous degradation process of a radiopaque hydrogel could be non-invasively monitored in a real-time and quantitative manner.In particular,the corrected degradation curve based on Micro-CT imaging well matched with the degradation profile of virgin polymer hydrogel determined by the gravimetric method.These findings indicate that the macromolecular contrast agent has good universality for the construction of various radiopaque polymer hydrogels,and can nondestructively trace and quantify their degradation in vivo.Meanwhile,the present methodology developed by us affords a platform technology for deep tissue imaging of polymeric materials.

Temperature-sensitive polymeric nanogels encapsulating withβ-cyclodextrin and ICG complex for high-resolution deep-tissue ultrasound-switchable fluorescence imaging

One of the thorny problems currently impeding the applications of the fluorescence imaging technique is the poor spatial resolution in deep tissue.Ultrasound-switchable fluorescence(USF)imaging is a novel imaging tool that has recently been explored to possibly surmount the above-mentioned bottleneck.Herein,αβ-cyclodextrin/indocyanine green(ICG)complex-encapsulated poly(N-isopropylacrylamide)(PNIPAM)nanogel was synthesized and studied for ex vivo/in vivo deep tissue/high-resolution near infrared USF(NIR-USF)imaging.To be specific,our results revealed that the average diameter of the as-prepared nanogels was significantly decreased to-32 nm from-335 nm compared to the reported ICG-PNIPAM nanoparticles.Additionally,the excitation/emission characteristics of the ICG itself in present nanogels were almost completely retained,and the resultant nanogel exhibited high physiological stability and positive biocompatibility.In particular,the signal-to-noise ratio of the USF image for the PNIPAM/P-cyclodextrin/ICG nanogel(33.01±2.42 dB)was prominently higher than that of the ICG-PNIPAM nanoparticles(18.73±0.33 dB)in 1.5-cm-thick chicken breast tissues.The NIR-USF imaging in 3.5-cm-thick chicken breast tissues was achieved using this new probe.The e x v iv o NIR-USF imaging of the mouse liver was also successfully obtained.Animal experiments showed that the present nanogels were able to be effectively accumulated into U87 tumor-bearing mice via enhanced permeability and retention effects,and the high-resolution NIR-USF imaging of in v ivo tumor was efficiently acquired.The metabolism and in vivo biodistribution of the nanogels were evaluated.Overall,the results suggest that the current nanogel is a highly promising NIR-USF probe for deep tissue and high-resolution USF imaging.

Reconstruction of 3D light distribution produced by cylindrical diffuser in deep tissues based on photoacoustic imaging

Measurement of light distribution in biological tissue contributes to selecting strategy and optimizing dose for biomedical application. In this letter, a photoacoustic method combined with Monte Carlo simulation was used to estimate the three-dimensional light distribution in biological tissue. The light distribution was produced by a cylindrical diffuser which interposed into tissues. The light profiles obtained by the method were compared to those detected by photo diodes. The experimental results demonstrate the feasibility of this method. The approach can play a significant role for photo-dosimetry in biomedical phototherapy.

Stimulated Raman scattering tomography for rapid three-dimensional chemical imaging of cells and tissue

Three-dimensional(3D)imaging is essential for understanding intricate biological and biomedical systems,yet live cell and tissue imaging applications still face challenges due to constrained imaging speed and strong scattering in turbid media.Here,we present a unique phase-modulated stimulated Raman scattering tomography(PM-SRST)technique to achieve rapid label-free 3D chemical imaging in cells and tissue.To accomplish PM-SRST,we utilize a spatial light modulator to electronically manipulate the focused Stokes beam along the needle Bessel pump beam for SRS tomography without the need for mechanical z scanning.We demonstrate the rapid 3D imaging capability of PM-SRST by real-time monitoring of 3D Brownian motion of polystyrene beads in water with 8.5 Hz volume rate,as well as the instant biochemical responses to acetic acid stimulants in MCF-7 cells.Further,combining the Bessel pump beam with a longer wavelength Stokes beam(NIR-II window)provides a superior scattering resilient ability in PM-SRST,enabling rapid tomography in deeper tissue areas.The PM-SRST technique providestwofold enhancement in imaging depth in highly scattering media(e.g.,polymer beads phantom and biotissue like porcine skin and brain tissue)compared with conventional point-scan SRS.We also demonstrate the rapid 3D imaging ability of PM-SRST by observing the dynamic diffusion and uptake processes of deuterium oxide molecules into plant roots.The rapid PM-SRST developed can be used to facilitate label-free 3D chemical imaging of metabolic activities and functional dynamic processes of drug delivery and therapeutics in live cells and tissue.

In vivo tumor ultrasound-switchable fluorescence imaging via intravenous injections of size-controlled thermosensitive nanoparticles

Near-infrared fluorescence imaging has emerged as a noninvasive,inexpensive,and ionizing-radiation-free monitoring tool for assessing tumor growth and treatment efficacy.In particular,ultrasound switchable fluorescence(USF)imaging has been explored with improved imaging sensitivity and spatial resolution in centimeter-deep tissues.This study achieved the size control of polymer-based and indocyanine green(ICG)encapsulated USF contrast agents,capable of accumulating in the tumor after intravenous injections.These nanoprobes varied in size from 58 to 321 nm.The bioimaging profiles demonstrated that the proposed nanoparticles can efficiently eliminate the background light from normal tissue and show a tumor-specific fluorescence enhancement in the BxPC-3 tumor-bearing mice models possibly via the enhanced permeability and retention effect.In vivo tumor USF imaging further demonstrated that these nanoprobes can effectively be switched“ON”with enhanced fluorescence in response to a focused ultrasound stimulation in the tumor microenvironment,contributing to the high-resolution USF images.Therefore,our findings suggest that ICG-encapsulated nanoparticles are good candidates for USF imaging of tumors in live animals,indicating their great potential in optical tumor imaging in deep tissue.

Optical Brain Imaging： A Powerful Tool for Neuroscience

As the control center of organisms, the brain remains little understood due to its complexity. Taking advantage of imaging methods, scientists have found an accessible approach to unraveling the mystery of neuroscience. Among these methods, optical imaging techniques are widely used due to their high molecular specificity and single-molecule sensitivity. Here, we overview several optical imaging techniques in neuroscience of recent years, including brain clearing, the micro-optical sectioning tomography system, and deep tissue imaging.