Microscopy imaging is fundamental in analyzing bacterial morphology and dynamics,offering critical insights into bacterial physiology and pathogenicity.Image segmentation techniques enable quantitative analysis of bac...Microscopy imaging is fundamental in analyzing bacterial morphology and dynamics,offering critical insights into bacterial physiology and pathogenicity.Image segmentation techniques enable quantitative analysis of bacterial structures,facilitating precise measurement of morphological variations and population behaviors at single-cell resolution.This paper reviews advancements in bacterial image segmentation,emphasizing the shift from traditional thresholding and watershed methods to deep learning-driven approaches.Convolutional neural networks(CNNs),U-Net architectures,and three-dimensional(3D)frameworks excel at segmenting dense biofilms and resolving antibiotic-induced morphological changes.These methods combine automated feature extraction with physics-informed postprocessing.Despite progress,challenges persist in computational efficiency,cross-species generalizability,and integration with multimodal experimental workflows.Future progress will depend on improving model robustness across species and imaging modalities,integrating multimodal data for phenotype-function mapping,and developing standard pipelines that link computational tools with clinical diagnostics.These innovations will expand microbial phenotyping beyond structural analysis,enabling deeper insights into bacterial physiology and ecological interactions.展开更多
In the image fusion field,fusing infrared images(IRIs)and visible images(VIs)excelled is a key area.The differences between IRIs and VIs make it challenging to fuse both types into a high-quality image.Accordingly,eff...In the image fusion field,fusing infrared images(IRIs)and visible images(VIs)excelled is a key area.The differences between IRIs and VIs make it challenging to fuse both types into a high-quality image.Accordingly,efficiently combining the advantages of both images while overcoming their shortcomings is necessary.To handle this challenge,we developed an end-to-end IRI andVI fusionmethod based on frequency decomposition and enhancement.By applying concepts from frequency domain analysis,we used the layering mechanism to better capture the salient thermal targets from the IRIs and the rich textural information from the VIs,respectively,significantly boosting the image fusion quality and effectiveness.In addition,the backbone network combined Restormer Blocks and Dense Blocks;Restormer blocks utilize global attention to extract shallow features.Meanwhile,Dense Blocks ensure the integration between shallow and deep features,thereby avoiding the loss of shallow attributes.Extensive experiments on TNO and MSRS datasets demonstrated that the suggested method achieved state-of-the-art(SOTA)performance in various metrics:Entropy(EN),Mutual Information(MI),Standard Deviation(SD),The Structural Similarity Index Measure(SSIM),Fusion quality(Qabf),MI of the pixel(FMI_(pixel)),and modified Visual Information Fidelity(VIF_(m)).展开更多
Organoids possess immense potential for unraveling the intricate functions of human tissues and facilitating preclinical disease treatment.Their applications span from high-throughput drug screening to the modeling of...Organoids possess immense potential for unraveling the intricate functions of human tissues and facilitating preclinical disease treatment.Their applications span from high-throughput drug screening to the modeling of complex diseases,with some even achieving clinical translation.Changes in the overall size,shape,boundary,and other morphological features of organoids provide a noninvasive method for assessing organoid drug sensitivity.However,the precise segmentation of organoids in bright-field microscopy images is made difficult by the complexity of the organoid morphology and interference,including overlapping organoids,bubbles,dust particles,and cell fragments.This paper introduces the precision organoid segmentation technique(POST),which is a deep-learning algorithm for segmenting challenging organoids under simple bright-field imaging conditions.Unlike existing methods,POST accurately segments each organoid and eliminates various artifacts encountered during organoid culturing and imaging.Furthermore,it is sensitive to and aligns with measurements of organoid activity in drug sensitivity experiments.POST is expected to be a valuable tool for drug screening using organoids owing to its capability of automatically and rapidly eliminating interfering substances and thereby streamlining the organoid analysis and drug screening process.展开更多
The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and hist...The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and historical context,DL offers a powerful complement by enhancing the speed,objectivity,and precision of the classification process.This research explores the significance of image data augmentation techniques in optimizing the performance of convolutional neural networks(CNNs)for geological image analysis,particularly in the classification of igneous,metamorphic,and sedimentary rock types from rock thin section(RTS)images.This study primarily focuses on classic image augmentation techniques and evaluates their impact on model accuracy and precision.Results demonstrate that augmentation techniques like Equalize significantly enhance the model's classification capabilities,achieving an F1-Score of 0.9869 for igneous rocks,0.9884 for metamorphic rocks,and 0.9929 for sedimentary rocks,representing improvements compared to the baseline original results.Moreover,the weighted average F1-Score across all classes and techniques is 0.9886,indicating an enhancement.Conversely,methods like Distort lead to decreased accuracy and F1-Score,with an F1-Score of 0.949 for igneous rocks,0.954 for metamorphic rocks,and 0.9416 for sedimentary rocks,exacerbating the performance compared to the baseline.The study underscores the practicality of image data augmentation in geological image classification and advocates for the adoption of DL methods in this domain for automation and improved results.The findings of this study can benefit various fields,including remote sensing,mineral exploration,and environmental monitoring,by enhancing the accuracy of geological image analysis both for scientific research and industrial applications.展开更多
Background:Brain volume measurement serves as a critical approach for assessing brain health status.Considering the close biological connection between the eyes and brain,this study aims to investigate the feasibility...Background:Brain volume measurement serves as a critical approach for assessing brain health status.Considering the close biological connection between the eyes and brain,this study aims to investigate the feasibility of estimating brain volume through retinal fundus imaging integrated with clinical metadata,and to offer a cost-effective approach for assessing brain health.Methods:Based on clinical information,retinal fundus images,and neuroimaging data derived from a multicenter,population-based cohort study,the Kai Luan Study,we proposed a cross-modal correlation representation(CMCR)network to elucidate the intricate co-degenerative relationships between the eyes and brain for 755 subjects.Specifically,individual clinical information,which has been followed up for as long as 12 years,was encoded as a prompt to enhance the accuracy of brain volume estimation.Independent internal validation and external validation were performed to assess the robustness of the proposed model.Root mean square error(RMSE),peak signal-tonoise ratio(PSNR),and structural similarity index measure(SSIM)metrics were employed to quantitatively evaluate the quality of synthetic brain images derived from retinal imaging data.Results:The proposed framework yielded average RMSE,PSNR,and SSIM values of 98.23,35.78 d B,and 0.64,respectively,which significantly outperformed 5 other methods:multi-channel Variational Autoencoder(mcVAE),Pixelto-Pixel(Pixel2pixel),transformer-based U-Net(Trans UNet),multi-scale transformer network(MT-Net),and residual vision transformer(ResViT).The two-(2D)and three-dimensional(3D)visualization results showed that the shape and texture of the synthetic brain images generated by the proposed method most closely resembled those of actual brain images.Thus,the CMCR framework accurately captured the latent structural correlations between the fundus and the brain.The average difference between predicted and actual brain volumes was 61.36 cm~3,with a relative error of 4.54%.When all of the clinical information(including age and sex,daily habits,cardiovascular factors,metabolic factors,and inflammatory factors)was encoded,the difference was decreased to 53.89 cm~3,with a relative error of 3.98%.Based on the synthesized brain magnetic resonance images from retinal fundus images,the volumes of brain tissues could be estimated with high accuracy.Conclusion:This study provides an innovative,accurate,and cost-effective approach to characterize brain health status through readily accessible retinal fundus images.展开更多
Elliptic curve(EC)based cryptosystems gained more attention due to enhanced security than the existing public key cryptosystems.A substitution box(S-box)plays a vital role in securing modern symmetric key cryptosystem...Elliptic curve(EC)based cryptosystems gained more attention due to enhanced security than the existing public key cryptosystems.A substitution box(S-box)plays a vital role in securing modern symmetric key cryptosystems.However,the recently developed EC based algorithms usually trade off between computational efficiency and security,necessitating the design of a new algorithm with the desired cryptographic strength.To address these shortcomings,this paper proposes a new scheme based onMordell elliptic curve(MEC)over the complex field for generating distinct,dynamic,and highly uncorrelated S-boxes.Furthermore,we count the exact number of the obtained S-boxes,and demonstrate that the permuted version of the presented S-box is statistically optimal.The nonsingularity of the presented algorithm and the injectivity of the resultant output are explored.Rigorous theoretical analysis and experimental results demonstrate that the proposedmethod is highly effective in generating a large number of dynamic S-boxes with adequate cryptographic properties,surpassing current state-of-the-art S-box generation algorithms in terms of security.Apart fromthis,the generated S-box is benchmarked using side-channel attacks,and its performance is compared with highly nonlinear S-boxes,demonstrating comparable results.In addition,we present an application of our proposed S-box generator by incorporating it into an image encryption technique.The encrypted and decrypted images are tested by employing extensive standard security metrics,including the Number of Pixel Change Rate,the Unified Average Changing Intensity,information entropy,correlation coefficient,and histogram analysis.Moreover,the analysis is extended beyond conventional metrics to validate the new method using advanced tests,such as the NIST statistical test suite,robustness analysis,and noise and cropping attacks.Experimental outcomes show that the presented algorithm strengthens the existing encryption scheme against various well-known cryptographic attacks.展开更多
This paper proposes a tamper detection technique for semi-fragile watermarking using Quantizationbased Discrete Cosine Transform(DCT)for tamper localization.In this study,the proposed embedding strategy is investigate...This paper proposes a tamper detection technique for semi-fragile watermarking using Quantizationbased Discrete Cosine Transform(DCT)for tamper localization.In this study,the proposed embedding strategy is investigated by experimental tests over the diagonal order of the DCT coefficients.The cover image is divided into non-overlapping blocks of size 8×8 pixels.The DCT is applied to each block,and the coefficients are arranged using a zig-zag pattern within the block.In this study,the low-frequency coefficients are selected to examine the impact of the imperceptibility score and tamper detection accuracy.High accuracy of tamper detection can be achieved by checking the surrounding blocks to determine whether the corresponding block has been tampered with.The proposed tamper detection is tested under various malicious,incidental,and hybrid attacks(both incidental and malicious attacks).The experimental results demonstrate that the proposed technique achieves a Peak-Signal-to-Noise Ratio(PSNR)value of 41.2318 dB,an average Structural Similarity Index Measure(SSIM)value of 0.9768.The proposed scheme is also evaluated against malicious attacks such as copy-move,object deletion,object manipulation,and collage attacks.The proposed scheme can detect the malicious attack localization under various tampering rates.In addition,the proposed scheme can still detect tampered pixels under a hybrid attack,such as a combination ofmalicious and incidental attacks,with an average accuracy of 96.44%.展开更多
Scattering obscures information carried by waves by producing speckle patterns,posing a fundamental challenge across diverse fields,from microscopy to astronomy.Although machine learning has recently shown promise in ...Scattering obscures information carried by waves by producing speckle patterns,posing a fundamental challenge across diverse fields,from microscopy to astronomy.Although machine learning has recently shown promise in speckle analysis,existing approaches are hindered by their dependence on large,labeled datasets—a significant bottleneck in many real-world applications.Here,we introduce speckle unsupervised recognition and evaluation(SURE),a groundbreaking unsupervised learning strategy for speckle recognition that eliminates the need for labeled training data.SURE's distinctive feature lies in its ability to extract invariant features through advanced clustering algorithms to enable direct classification of high-level information from speckle patterns without prior knowledge.We demonstrate the transformative potential of this approach in two key applications:(1)a noninvasive glucose monitoring system that accurately tracks glucose concentrations over time without extensive calibration and(2)a high-throughput communication system using multimode fibers,achieving improved performance in dynamic environments.In addition,we showcase SURE's unprecedented capability to classify objects hidden behind obstacles using scattered light,further broadening its scope.This versatile approach opens new frontiers in biomedical diagnostics,quantum network decoupling,and remote sensing,unlocking a transformative new paradigm for extracting information from seemingly random optical patterns.展开更多
Background Computed tomography(CT) and cone-beam computed tomography(CBCT) image registration play pivotal roles in computer-assisted navigation for orthopedic surgery. Traditional methods often apply uniform deformat...Background Computed tomography(CT) and cone-beam computed tomography(CBCT) image registration play pivotal roles in computer-assisted navigation for orthopedic surgery. Traditional methods often apply uniform deformation models, neglecting the biomechanical differences between rigid structures and soft tissues, which compromises registration accuracy, especially during significant bone displacements. Method To address this issue, we introduce RE-Reg, a rigid-elastic CT-CBCT image registration framework that jointly learns rigid bone motion and soft tissue deformation. RE-Reg incorporates a rigid alignment(RA) module to estimate global bone motion and an elastic deformation(ED) module to model soft tissue deformation, preserving bony structures through bone shape preservation(BSP) loss. Result Our comprehensive evaluation on publicly available datasets demonstrates that RE-Reg significantly outperforms existing methods in terms of registration accuracy and rigid bone structure preservation, achieving a 1.3% improvement in Dice similarity coefficient(DSC) and a 23% reduction in rigid bone deformation(%Δvol) compared with the best baseline. Conclusion This framework not only enhances anatomical fidelity but also ensures biomechanical plausibility and provides a valuable tool for image-guided orthopedic surgery. This code is available athttps://github.com/Zq-Huang/RE-Reg.展开更多
Medical image segmentation is of critical importance in the domain of contemporary medical imaging.However,U-Net and its variants exhibit limitations in capturing complex nonlinear patterns and global contextual infor...Medical image segmentation is of critical importance in the domain of contemporary medical imaging.However,U-Net and its variants exhibit limitations in capturing complex nonlinear patterns and global contextual information.Although the subsequent U-KAN model enhances nonlinear representation capabilities,it still faces challenges such as gradient vanishing during deep network training and spatial detail loss during feature downsampling,resulting in insufficient segmentation accuracy for edge structures and minute lesions.To address these challenges,this paper proposes the RE-UKAN model,which innovatively improves upon U-KAN.Firstly,a residual network is introduced into the encoder to effectively mitigate gradient vanishing through cross-layer identity mappings,thus enhancing modelling capabilities for complex pathological structures.Secondly,Efficient Local Attention(ELA)is integrated to suppress spatial detail loss during downsampling,thereby improving the perception of edge structures and minute lesions.Experimental results on four public datasets demonstrate that RE-UKAN outperforms existing medical image segmentation methods across multiple evaluation metrics,with particularly outstanding performance on the TN-SCUI 2020 dataset,achieving IoU of 88.18%and Dice of 93.57%.Compared to the baseline model,it achieves improvements of 3.05%and 1.72%,respectively.These results fully demonstrate RE-UKAN’s superior detail retention capability and boundary recognition accuracy in complex medical image segmentation tasks,providing a reliable solution for clinical precision segmentation.展开更多
With the rapid development of transportation infrastructure,ensuring road safety through timely and accurate highway inspection has become increasingly critical.Traditional manual inspection methods are not only time-...With the rapid development of transportation infrastructure,ensuring road safety through timely and accurate highway inspection has become increasingly critical.Traditional manual inspection methods are not only time-consuming and labor-intensive,but they also struggle to provide consistent,high-precision detection and realtime monitoring of pavement surface defects.To overcome these limitations,we propose an Automatic Recognition of PavementDefect(ARPD)algorithm,which leverages unmanned aerial vehicle(UAV)-based aerial imagery to automate the inspection process.The ARPD framework incorporates a backbone network based on the Selective State Space Model(S3M),which is designed to capture long-range temporal dependencies.This enables effective modeling of dynamic correlations among redundant and often repetitive structures commonly found in road imagery.Furthermore,a neck structure based on Semantics and Detail Infusion(SDI)is introduced to guide cross-scale feature fusion.The SDI module enhances the integration of low-level spatial details with high-level semantic cues,thereby improving feature expressiveness and defect localization accuracy.Experimental evaluations demonstrate that theARPDalgorithm achieves a mean average precision(mAP)of 86.1%on a custom-labeled pavement defect dataset,outperforming the state-of-the-art YOLOv11 segmentation model.The algorithm also maintains strong generalization ability on public datasets.These results confirm that ARPD is well-suited for diverse real-world applications in intelligent,large-scale highway defect monitoring and maintenance planning.展开更多
The historical image of Ouyang Xiu constructed during the Song Dynasty evolved from a multifaceted portrayal that balanced his political and literary achievements into a singular cultural symbol.In the Northern Song D...The historical image of Ouyang Xiu constructed during the Song Dynasty evolved from a multifaceted portrayal that balanced his political and literary achievements into a singular cultural symbol.In the Northern Song Dynasty,writings by Ouyang Xiu's family and epitaphs by his colleagues crafted a balanced narrative emphasizing both his official duties and literary merits,thus constructing a dual image of him as a principled remonstrator and a literary master.In the Southern Song Dynasty,official historiography gradually eroded his complex persona as a political reformer by selectively trimming political disputes and emphasizing his literary lineage,ultimately establishing him as a cultural exemplar beyond factional strife.Throughout this evolution of historical writing,Ouyang Xiu's sharpness as a remonstrator was gradually obscured in historical texts,while his image as a literary master,revered by all,became firmly established.The reshaping of Ouyang Xiu's image in historical writings across the Northern and Southern Song dynasties not only reflects the logic of selecting scholar-official role models under the influence of official ideology but also reveals the inherent pattern whereby individual distinctiveness fades into symbolic construction in historical writing.展开更多
Digital watermarking technology plays an important role in detecting malicious tampering and protecting image copyright.However,in practical applications,this technology faces various problems such as severe image dis...Digital watermarking technology plays an important role in detecting malicious tampering and protecting image copyright.However,in practical applications,this technology faces various problems such as severe image distortion,inaccurate localization of the tampered regions,and difficulty in recovering content.Given these shortcomings,a fragile image watermarking algorithm for tampering blind-detection and content self-recovery is proposed.The multi-feature watermarking authentication code(AC)is constructed using texture feature of local binary patterns(LBP),direct coefficient of discrete cosine transform(DCT)and contrast feature of gray level co-occurrence matrix(GLCM)for detecting the tampered region,and the recovery code(RC)is designed according to the average grayscale value of pixels in image blocks for recovering the tampered content.Optimal pixel adjustment process(OPAP)and least significant bit(LSB)algorithms are used to embed the recovery code and authentication code into the image in a staggered manner.When detecting the integrity of the image,the authentication code comparison method and threshold judgment method are used to perform two rounds of tampering detection on the image and blindly recover the tampered content.Experimental results show that this algorithm has good transparency,strong and blind detection,and self-recovery performance against four types of malicious attacks and some conventional signal processing operations.When resisting copy-paste,text addition,cropping and vector quantization under the tampering rate(TR)10%,the average tampering detection rate is up to 94.09%,and the peak signal-to-noise ratio(PSNR)of the watermarked image and the recovered image are both greater than 41.47 and 40.31 dB,which demonstrates its excellent advantages compared with other related algorithms in recent years.展开更多
Roadbed disease detection is essential for maintaining road functionality.Ground penetrating radar(GPR)enables non-destructive detection without drilling.However,current identification often relies on manual inspectio...Roadbed disease detection is essential for maintaining road functionality.Ground penetrating radar(GPR)enables non-destructive detection without drilling.However,current identification often relies on manual inspection,which requires extensive experience,suffers from low efficiency,and is highly subjective.As the results are presented as radar images,image processing methods can be applied for fast and objective identification.Deep learning-based approaches now offer a robust solution for automated roadbed disease detection.This study proposes an enhanced Faster Region-based Convolutional Neural Networks(R-CNN)framework integrating ResNet-50 as the backbone and two-dimensional discrete Fourier spectrum transformation(2D-DFT)for frequency-domain feature fusion.A dedicated GPR image dataset comprising 1650 annotated images was constructed and augmented to 6600 images via median filtering,histogram equalization,and binarization.The proposed model segments defect regions,applies binary masking,and fuses frequency-domain features to improve small-target detection under noisy backgrounds.Experimental results show that the improved Faster R-CNN achieves a mean Average Precision(mAP)of 0.92,representing a 0.22 increase over the baseline.Precision improved by 26%while recall remained stable at 87%.The model was further validated on real urban road data,demonstrating robust detection capability even under interference.These findings highlight the potential of combining GPR with deep learning for efficient,non-destructive roadbed health monitoring.展开更多
Background:Medical imaging advancements are constrained by fundamental trade-offs between acquisition speed,radiation dose,and image quality,forcing clinicians to work with noisy,incomplete data.Existing reconstructio...Background:Medical imaging advancements are constrained by fundamental trade-offs between acquisition speed,radiation dose,and image quality,forcing clinicians to work with noisy,incomplete data.Existing reconstruction methods either compromise on accuracy with iterative algorithms or suffer from limited generalizability with task-specific deep learning approaches.Methods:We present LDM-PIR,a lightweight physics-conditioned diffusion multi-model for medical image reconstruction that addresses key challenges in magnetic resonance imaging(MRI),CT,and low-photon imaging.Unlike traditional iterative methods,which are computationally expensive,or task-specific deep learning approaches lacking generalizability,integrates three innovations.A physics-conditioned diffusion framework that embeds acquisition operators(Fourier/Radon transforms)and noise models directly into the reconstruction process.A multi-model architecture that unifies denoising,inpainting,and super-resolution via shared weight conditioning.A lightweight design(2.1M parameters)enabling rapid inference(0.8s/image on GPU).Through self-supervised fine-tuning with measurement consistency losses adapts to new imaging modalities using fewer annotated samples.Results:Achieves state-of-the-art performance on fastMRI(peak signal-to-noise ratio(PSNR):34.04 for single-coil/31.50 for multi-coil)and Lung Image Database Consortium and Image Database Resource Initiative(28.83 PSNR under Poisson noise).Clinical evaluations demonstrate superior preservation of anatomical structures,with SSIM improvements of 8.8%for single-coil and 4.36%for multi-coil MRI over uDPIR.Conclusion:It offers a flexible,efficient,and scalable solution for medical image reconstruction,addressing the challenges of noise,undersampling,and modality generalization.The model’s lightweight design allows for rapid inference,while its self-supervised fine-tuning capability minimizes reliance on large annotated datasets,making it suitable for real-world clinical applications.展开更多
The advent of 5G technology has significantly enhanced the transmission of images over networks,expanding data accessibility and exposure across various applications in digital technology and social media.Consequently...The advent of 5G technology has significantly enhanced the transmission of images over networks,expanding data accessibility and exposure across various applications in digital technology and social media.Consequently,the protection of sensitive data has become increasingly critical.Regardless of the complexity of the encryption algorithm used,a robust and highly secure encryption key is essential,with randomness and key space being crucial factors.This paper proposes a new Robust Deoxyribonucleic Acid(RDNA)nucleotide-based encryption method.The RDNA encryption method leverages the unique properties of DNA nucleotides,including their inherent randomness and extensive key space,to generate a highly secure encryption key.By employing transposition and substitution operations,the RDNA method ensures significant diffusion and confusion in the encrypted images.Additionally,it utilises a pseudorandom generation technique based on the random sequence of nucleotides in the DNA secret key.The performance of the RDNA encryption method is evaluated through various statistical and visual tests,and compared against established encryption methods such as 3DES,AES,and a DNA-based method.Experimental results demonstrate that the RDNA encryption method outperforms its rivals in the literature,and achieves superior performance in terms of information entropy,avalanche effect,encryption execution time,and correlation reduction,while maintaining competitive values for NMAE,PSNR,NPCR,and UACI.The high degree of randomness and sensitivity to key changes inherent in the RDNA method offers enhanced security,making it highly resistant to brute force and differential attacks.展开更多
Military image encryption plays a vital role in ensuring the secure transmission of sensitive visual information from unauthorized access.This paper proposes a new Tri-independent keying method for encrypting military...Military image encryption plays a vital role in ensuring the secure transmission of sensitive visual information from unauthorized access.This paper proposes a new Tri-independent keying method for encrypting military images.The proposed encryption method is based on multilevel security stages of pixel-level scrambling,bitlevel manipulation,and block-level shuffling operations.For having a vast key space,the input password is hashed by the Secure Hash Algorithm 256-bit(SHA-256)for generating independently deterministic keys used in the multilevel stages.A piecewise pixel-level scrambling function is introduced to perform a dual flipping process controlled with an adaptive key for obscuring the spatial relationships between the adjacent pixels.Adynamicmasking scheme is presented for conducting a bit-level manipulation based on distinct keys that change over image regions,providing completely different encryption results on identical regions.To handle the global correlation between large-scale patterns,a chaotic index-map system is employed for shuffling image regions randomly across the image domain based on a logistic map seeded with a private key.Experimental results on a dataset of military images show the effectiveness of the proposed encryption method in producing excellent quantitative and qualitative results.The proposed method obtains uniform histogram distributions,high entropy values around the ideal(≈8 bits),Number of Pixel Change Rate(NPCR)values above 99.5%,and low Peak Signal-to-Noise Ratio(PSNR)over all encrypted images.This validates the robustness of the proposed method against cryptanalytic attacks,verifying its ability to serve as a practical basis for secure image transmission in defense systems.展开更多
This article studies the problem of image segmentation-based semantic communication in autonomous driving.In real traffic scenes,the detecting of objects(e.g.,vehicles and pedestrians)is more important to guarantee dr...This article studies the problem of image segmentation-based semantic communication in autonomous driving.In real traffic scenes,the detecting of objects(e.g.,vehicles and pedestrians)is more important to guarantee driving safety,which is always ignored in existing works.Therefore,we propose a vehicular image segmentation-oriented semantic communication system,termed VIS-SemCom,focusing on transmitting and recovering image semantic features of high-important objects to reduce transmission redundancy.First,we develop a semantic codec based on Swin Transformer architecture,which expands the perceptual field thus improving the segmentation accuracy.To highlight the important objects'accuracy,we propose a multi-scale semantic extraction method by assigning the number of Swin Transformer blocks for diverse resolution semantic features.Also,an importance-aware loss incorporating important levels is devised,and an online hard example mining(OHEM)strategy is proposed to handle small sample issues in the dataset.Finally,experimental results demonstrate that the proposed VIS-SemCom can achieve a significant mean intersection over union(mIoU)performance in the SNR regions,a reduction of transmitted data volume by about 60%at 60%mIoU,and improve the segmentation accuracy of important objects,compared to baseline image communication.展开更多
Common strong noise interferences like metal splashes,smoke,and arc light during welding can seriously pollute the laser stripe images,causing the tracking model to drift and leading to tracking failure.At present,the...Common strong noise interferences like metal splashes,smoke,and arc light during welding can seriously pollute the laser stripe images,causing the tracking model to drift and leading to tracking failure.At present,there are already many mature methods for identifying and extracting feature points of linear laser stripes.When the laser stripe forms a curved shape on the surface of the workpiece,these linear methods will no longer be applicable.To eliminate interference sources,enhance the robustness of the weld tracking model,and effectively extract the feature points of curved laser stripes under strong noise conditions.This paper proposes a Conditional Generative Adversarial Network(CGAN)based anti-interference recognition method for welding images.The generator adopts an improved U-Net++structure,adds a Multi-scale Channel Attention module(MS-CAM),introduces Deep Supervision,and proposes a Multi-output Fusion strategy(MOFS)in the output result to en-hance the image inpainting effect;the discriminator uses PatchGAN.The center of the laser stripe is obtained using the grayscale center of mass method and then combined with polynomial fitting to extract the feature points of the weld seam.The experimental results show that the PSNR of the inpainting image is 26.24 dB,the SSIM is 0.98,and the LPIPS is 0.032.The centerline of the inpainting image and the centerline of the noise-free image laser stripe are fitted with a curve.The error of centerline feature points is no more than 5%,confirming the superiority and feasibility of the method.展开更多
基金financially supported by the Open Project Program of Wuhan National Laboratory for Optoelectronics(No.2022WNLOKF009)the National Natural Science Foundation of China(No.62475216)+2 种基金the Key Research and Development Program of Shaanxi(No.2024GH-ZDXM-37)the Fujian Provincial Natural Science Foundation of China(No.2024J01060)the Startup Program of XMU,and the Fundamental Research Funds for the Central Universities.
文摘Microscopy imaging is fundamental in analyzing bacterial morphology and dynamics,offering critical insights into bacterial physiology and pathogenicity.Image segmentation techniques enable quantitative analysis of bacterial structures,facilitating precise measurement of morphological variations and population behaviors at single-cell resolution.This paper reviews advancements in bacterial image segmentation,emphasizing the shift from traditional thresholding and watershed methods to deep learning-driven approaches.Convolutional neural networks(CNNs),U-Net architectures,and three-dimensional(3D)frameworks excel at segmenting dense biofilms and resolving antibiotic-induced morphological changes.These methods combine automated feature extraction with physics-informed postprocessing.Despite progress,challenges persist in computational efficiency,cross-species generalizability,and integration with multimodal experimental workflows.Future progress will depend on improving model robustness across species and imaging modalities,integrating multimodal data for phenotype-function mapping,and developing standard pipelines that link computational tools with clinical diagnostics.These innovations will expand microbial phenotyping beyond structural analysis,enabling deeper insights into bacterial physiology and ecological interactions.
基金funded by Anhui Province University Key Science and Technology Project(2024AH053415)Anhui Province University Major Science and Technology Project(2024AH040229)+3 种基金Talent Research Initiation Fund Project of Tongling University(2024tlxyrc019)Tongling University School-Level Scientific Research Project(2024tlxyptZD07)TheUniversity Synergy Innovation Programof Anhui Province(GXXT-2023-050)Tongling City Science and Technology Major Special Project(Unveiling and Commanding Model)(200401JB004).
文摘In the image fusion field,fusing infrared images(IRIs)and visible images(VIs)excelled is a key area.The differences between IRIs and VIs make it challenging to fuse both types into a high-quality image.Accordingly,efficiently combining the advantages of both images while overcoming their shortcomings is necessary.To handle this challenge,we developed an end-to-end IRI andVI fusionmethod based on frequency decomposition and enhancement.By applying concepts from frequency domain analysis,we used the layering mechanism to better capture the salient thermal targets from the IRIs and the rich textural information from the VIs,respectively,significantly boosting the image fusion quality and effectiveness.In addition,the backbone network combined Restormer Blocks and Dense Blocks;Restormer blocks utilize global attention to extract shallow features.Meanwhile,Dense Blocks ensure the integration between shallow and deep features,thereby avoiding the loss of shallow attributes.Extensive experiments on TNO and MSRS datasets demonstrated that the suggested method achieved state-of-the-art(SOTA)performance in various metrics:Entropy(EN),Mutual Information(MI),Standard Deviation(SD),The Structural Similarity Index Measure(SSIM),Fusion quality(Qabf),MI of the pixel(FMI_(pixel)),and modified Visual Information Fidelity(VIF_(m)).
基金supported by the National Key R&D Program of China(No.2022YFC2504403)the National Natural Science Foundation of China(No.62172202)+1 种基金the Experiment Project of China Manned Space Program(No.HYZHXM01019)the Fundamental Research Funds for the Central Universities from Southeast University(No.3207032101C3)。
文摘Organoids possess immense potential for unraveling the intricate functions of human tissues and facilitating preclinical disease treatment.Their applications span from high-throughput drug screening to the modeling of complex diseases,with some even achieving clinical translation.Changes in the overall size,shape,boundary,and other morphological features of organoids provide a noninvasive method for assessing organoid drug sensitivity.However,the precise segmentation of organoids in bright-field microscopy images is made difficult by the complexity of the organoid morphology and interference,including overlapping organoids,bubbles,dust particles,and cell fragments.This paper introduces the precision organoid segmentation technique(POST),which is a deep-learning algorithm for segmenting challenging organoids under simple bright-field imaging conditions.Unlike existing methods,POST accurately segments each organoid and eliminates various artifacts encountered during organoid culturing and imaging.Furthermore,it is sensitive to and aligns with measurements of organoid activity in drug sensitivity experiments.POST is expected to be a valuable tool for drug screening using organoids owing to its capability of automatically and rapidly eliminating interfering substances and thereby streamlining the organoid analysis and drug screening process.
文摘The integration of image analysis through deep learning(DL)into rock classification represents a significant leap forward in geological research.While traditional methods remain invaluable for their expertise and historical context,DL offers a powerful complement by enhancing the speed,objectivity,and precision of the classification process.This research explores the significance of image data augmentation techniques in optimizing the performance of convolutional neural networks(CNNs)for geological image analysis,particularly in the classification of igneous,metamorphic,and sedimentary rock types from rock thin section(RTS)images.This study primarily focuses on classic image augmentation techniques and evaluates their impact on model accuracy and precision.Results demonstrate that augmentation techniques like Equalize significantly enhance the model's classification capabilities,achieving an F1-Score of 0.9869 for igneous rocks,0.9884 for metamorphic rocks,and 0.9929 for sedimentary rocks,representing improvements compared to the baseline original results.Moreover,the weighted average F1-Score across all classes and techniques is 0.9886,indicating an enhancement.Conversely,methods like Distort lead to decreased accuracy and F1-Score,with an F1-Score of 0.949 for igneous rocks,0.954 for metamorphic rocks,and 0.9416 for sedimentary rocks,exacerbating the performance compared to the baseline.The study underscores the practicality of image data augmentation in geological image classification and advocates for the adoption of DL methods in this domain for automation and improved results.The findings of this study can benefit various fields,including remote sensing,mineral exploration,and environmental monitoring,by enhancing the accuracy of geological image analysis both for scientific research and industrial applications.
基金supported by the National Natural Science Foundation of China(62522119 and 62372358)the Beijing Natural Science Foundation(7242267)+2 种基金the Beijing Scholars Program([2015]160)the Natural Science Basic Research Program of Shaanxi(2023-JC-QN-0719)the Guangdong Basic and Applied Basic Research Foundation(2022A1515110453)。
文摘Background:Brain volume measurement serves as a critical approach for assessing brain health status.Considering the close biological connection between the eyes and brain,this study aims to investigate the feasibility of estimating brain volume through retinal fundus imaging integrated with clinical metadata,and to offer a cost-effective approach for assessing brain health.Methods:Based on clinical information,retinal fundus images,and neuroimaging data derived from a multicenter,population-based cohort study,the Kai Luan Study,we proposed a cross-modal correlation representation(CMCR)network to elucidate the intricate co-degenerative relationships between the eyes and brain for 755 subjects.Specifically,individual clinical information,which has been followed up for as long as 12 years,was encoded as a prompt to enhance the accuracy of brain volume estimation.Independent internal validation and external validation were performed to assess the robustness of the proposed model.Root mean square error(RMSE),peak signal-tonoise ratio(PSNR),and structural similarity index measure(SSIM)metrics were employed to quantitatively evaluate the quality of synthetic brain images derived from retinal imaging data.Results:The proposed framework yielded average RMSE,PSNR,and SSIM values of 98.23,35.78 d B,and 0.64,respectively,which significantly outperformed 5 other methods:multi-channel Variational Autoencoder(mcVAE),Pixelto-Pixel(Pixel2pixel),transformer-based U-Net(Trans UNet),multi-scale transformer network(MT-Net),and residual vision transformer(ResViT).The two-(2D)and three-dimensional(3D)visualization results showed that the shape and texture of the synthetic brain images generated by the proposed method most closely resembled those of actual brain images.Thus,the CMCR framework accurately captured the latent structural correlations between the fundus and the brain.The average difference between predicted and actual brain volumes was 61.36 cm~3,with a relative error of 4.54%.When all of the clinical information(including age and sex,daily habits,cardiovascular factors,metabolic factors,and inflammatory factors)was encoded,the difference was decreased to 53.89 cm~3,with a relative error of 3.98%.Based on the synthesized brain magnetic resonance images from retinal fundus images,the volumes of brain tissues could be estimated with high accuracy.Conclusion:This study provides an innovative,accurate,and cost-effective approach to characterize brain health status through readily accessible retinal fundus images.
文摘Elliptic curve(EC)based cryptosystems gained more attention due to enhanced security than the existing public key cryptosystems.A substitution box(S-box)plays a vital role in securing modern symmetric key cryptosystems.However,the recently developed EC based algorithms usually trade off between computational efficiency and security,necessitating the design of a new algorithm with the desired cryptographic strength.To address these shortcomings,this paper proposes a new scheme based onMordell elliptic curve(MEC)over the complex field for generating distinct,dynamic,and highly uncorrelated S-boxes.Furthermore,we count the exact number of the obtained S-boxes,and demonstrate that the permuted version of the presented S-box is statistically optimal.The nonsingularity of the presented algorithm and the injectivity of the resultant output are explored.Rigorous theoretical analysis and experimental results demonstrate that the proposedmethod is highly effective in generating a large number of dynamic S-boxes with adequate cryptographic properties,surpassing current state-of-the-art S-box generation algorithms in terms of security.Apart fromthis,the generated S-box is benchmarked using side-channel attacks,and its performance is compared with highly nonlinear S-boxes,demonstrating comparable results.In addition,we present an application of our proposed S-box generator by incorporating it into an image encryption technique.The encrypted and decrypted images are tested by employing extensive standard security metrics,including the Number of Pixel Change Rate,the Unified Average Changing Intensity,information entropy,correlation coefficient,and histogram analysis.Moreover,the analysis is extended beyond conventional metrics to validate the new method using advanced tests,such as the NIST statistical test suite,robustness analysis,and noise and cropping attacks.Experimental outcomes show that the presented algorithm strengthens the existing encryption scheme against various well-known cryptographic attacks.
基金funded by Ministry of Higher Education Malaysia through Universiti Malaysia Pahang Al-Sultan Abdullah under Internal Research Grant(RDU233003).
文摘This paper proposes a tamper detection technique for semi-fragile watermarking using Quantizationbased Discrete Cosine Transform(DCT)for tamper localization.In this study,the proposed embedding strategy is investigated by experimental tests over the diagonal order of the DCT coefficients.The cover image is divided into non-overlapping blocks of size 8×8 pixels.The DCT is applied to each block,and the coefficients are arranged using a zig-zag pattern within the block.In this study,the low-frequency coefficients are selected to examine the impact of the imperceptibility score and tamper detection accuracy.High accuracy of tamper detection can be achieved by checking the surrounding blocks to determine whether the corresponding block has been tampered with.The proposed tamper detection is tested under various malicious,incidental,and hybrid attacks(both incidental and malicious attacks).The experimental results demonstrate that the proposed technique achieves a Peak-Signal-to-Noise Ratio(PSNR)value of 41.2318 dB,an average Structural Similarity Index Measure(SSIM)value of 0.9768.The proposed scheme is also evaluated against malicious attacks such as copy-move,object deletion,object manipulation,and collage attacks.The proposed scheme can detect the malicious attack localization under various tampering rates.In addition,the proposed scheme can still detect tampered pixels under a hybrid attack,such as a combination ofmalicious and incidental attacks,with an average accuracy of 96.44%.
基金supported by the National Natural Science Foundation of China(Grant Nos.11934011,12074339,62075194,U21A6006,62202418,and U21B2004)the National Key Research and Development Program of China(Grant Nos.2019YFA0308100,2023YFB2806000,and 2022YFA1204700)+4 种基金the Strategic Priority Research Program of Chinese Academy of Sciences(Grant No.XDB28000000)the Leading Innovation and Entrepreneurship Team in Zhejiang Province(Grant No.2020R01001)the Open Program of the State Key Laboratory of Advanced Optical Communication Systems and Networks at Shanghai Jiao Tong University(Grant No.2023GZKF024)the Fundamental Research Funds for the Central Universities,the Information Technology Center and State Key Lab of CAD&CG at the Zhejiang University,the Zhejiang Provincial Key Laboratory of Information Processing,Communication and Networking(IPCAN)the National Institutes of Health(NIH)(Grant Nos.R01GM127696,R01GM152633,R21GM142107,and R21CA269099)。
文摘Scattering obscures information carried by waves by producing speckle patterns,posing a fundamental challenge across diverse fields,from microscopy to astronomy.Although machine learning has recently shown promise in speckle analysis,existing approaches are hindered by their dependence on large,labeled datasets—a significant bottleneck in many real-world applications.Here,we introduce speckle unsupervised recognition and evaluation(SURE),a groundbreaking unsupervised learning strategy for speckle recognition that eliminates the need for labeled training data.SURE's distinctive feature lies in its ability to extract invariant features through advanced clustering algorithms to enable direct classification of high-level information from speckle patterns without prior knowledge.We demonstrate the transformative potential of this approach in two key applications:(1)a noninvasive glucose monitoring system that accurately tracks glucose concentrations over time without extensive calibration and(2)a high-throughput communication system using multimode fibers,achieving improved performance in dynamic environments.In addition,we showcase SURE's unprecedented capability to classify objects hidden behind obstacles using scattered light,further broadening its scope.This versatile approach opens new frontiers in biomedical diagnostics,quantum network decoupling,and remote sensing,unlocking a transformative new paradigm for extracting information from seemingly random optical patterns.
基金Supported by the National Natural Science Foundation of China(Grant Nos.62025104,62331005,and U22A2052)the Beijing Natural Science Foundation(Grant No.L242100).
文摘Background Computed tomography(CT) and cone-beam computed tomography(CBCT) image registration play pivotal roles in computer-assisted navigation for orthopedic surgery. Traditional methods often apply uniform deformation models, neglecting the biomechanical differences between rigid structures and soft tissues, which compromises registration accuracy, especially during significant bone displacements. Method To address this issue, we introduce RE-Reg, a rigid-elastic CT-CBCT image registration framework that jointly learns rigid bone motion and soft tissue deformation. RE-Reg incorporates a rigid alignment(RA) module to estimate global bone motion and an elastic deformation(ED) module to model soft tissue deformation, preserving bony structures through bone shape preservation(BSP) loss. Result Our comprehensive evaluation on publicly available datasets demonstrates that RE-Reg significantly outperforms existing methods in terms of registration accuracy and rigid bone structure preservation, achieving a 1.3% improvement in Dice similarity coefficient(DSC) and a 23% reduction in rigid bone deformation(%Δvol) compared with the best baseline. Conclusion This framework not only enhances anatomical fidelity but also ensures biomechanical plausibility and provides a valuable tool for image-guided orthopedic surgery. This code is available athttps://github.com/Zq-Huang/RE-Reg.
文摘Medical image segmentation is of critical importance in the domain of contemporary medical imaging.However,U-Net and its variants exhibit limitations in capturing complex nonlinear patterns and global contextual information.Although the subsequent U-KAN model enhances nonlinear representation capabilities,it still faces challenges such as gradient vanishing during deep network training and spatial detail loss during feature downsampling,resulting in insufficient segmentation accuracy for edge structures and minute lesions.To address these challenges,this paper proposes the RE-UKAN model,which innovatively improves upon U-KAN.Firstly,a residual network is introduced into the encoder to effectively mitigate gradient vanishing through cross-layer identity mappings,thus enhancing modelling capabilities for complex pathological structures.Secondly,Efficient Local Attention(ELA)is integrated to suppress spatial detail loss during downsampling,thereby improving the perception of edge structures and minute lesions.Experimental results on four public datasets demonstrate that RE-UKAN outperforms existing medical image segmentation methods across multiple evaluation metrics,with particularly outstanding performance on the TN-SCUI 2020 dataset,achieving IoU of 88.18%and Dice of 93.57%.Compared to the baseline model,it achieves improvements of 3.05%and 1.72%,respectively.These results fully demonstrate RE-UKAN’s superior detail retention capability and boundary recognition accuracy in complex medical image segmentation tasks,providing a reliable solution for clinical precision segmentation.
基金supported in part by the Technical Service for the Development and Application of an Intelligent Visual Management Platformfor Expressway Construction Progress Based on BIM Technology(grant NO.JKYZLX-2023-09)in partby the Technical Service for the Development of an Early Warning Model in the Research and Application of Key Technologies for Tunnel Operation Safety Monitoring and Early Warning Based on Digital Twin(grant NO.JK-S02-ZNGS-202412-JISHU-FA-0035)sponsored by Yunnan Transportation Science Research Institute Co.,Ltd.
文摘With the rapid development of transportation infrastructure,ensuring road safety through timely and accurate highway inspection has become increasingly critical.Traditional manual inspection methods are not only time-consuming and labor-intensive,but they also struggle to provide consistent,high-precision detection and realtime monitoring of pavement surface defects.To overcome these limitations,we propose an Automatic Recognition of PavementDefect(ARPD)algorithm,which leverages unmanned aerial vehicle(UAV)-based aerial imagery to automate the inspection process.The ARPD framework incorporates a backbone network based on the Selective State Space Model(S3M),which is designed to capture long-range temporal dependencies.This enables effective modeling of dynamic correlations among redundant and often repetitive structures commonly found in road imagery.Furthermore,a neck structure based on Semantics and Detail Infusion(SDI)is introduced to guide cross-scale feature fusion.The SDI module enhances the integration of low-level spatial details with high-level semantic cues,thereby improving feature expressiveness and defect localization accuracy.Experimental evaluations demonstrate that theARPDalgorithm achieves a mean average precision(mAP)of 86.1%on a custom-labeled pavement defect dataset,outperforming the state-of-the-art YOLOv11 segmentation model.The algorithm also maintains strong generalization ability on public datasets.These results confirm that ARPD is well-suited for diverse real-world applications in intelligent,large-scale highway defect monitoring and maintenance planning.
基金an initial outcome of the Research on the Interactive Relationship Between Biographies and Epitaphs in Ancient China,a project(ID:24BZW023)supported by the National Social Science Fund of China。
文摘The historical image of Ouyang Xiu constructed during the Song Dynasty evolved from a multifaceted portrayal that balanced his political and literary achievements into a singular cultural symbol.In the Northern Song Dynasty,writings by Ouyang Xiu's family and epitaphs by his colleagues crafted a balanced narrative emphasizing both his official duties and literary merits,thus constructing a dual image of him as a principled remonstrator and a literary master.In the Southern Song Dynasty,official historiography gradually eroded his complex persona as a political reformer by selectively trimming political disputes and emphasizing his literary lineage,ultimately establishing him as a cultural exemplar beyond factional strife.Throughout this evolution of historical writing,Ouyang Xiu's sharpness as a remonstrator was gradually obscured in historical texts,while his image as a literary master,revered by all,became firmly established.The reshaping of Ouyang Xiu's image in historical writings across the Northern and Southern Song dynasties not only reflects the logic of selecting scholar-official role models under the influence of official ideology but also reveals the inherent pattern whereby individual distinctiveness fades into symbolic construction in historical writing.
基金supported by Postgraduate Research&Practice Innovation Program of Jiangsu Province,China(Grant No.SJCX24_1332)Jiangsu Province Education Science Planning Project in 2024(Grant No.B-b/2024/01/122)High-Level Talent Scientific Research Foundation of Jinling Institute of Technology,China(Grant No.jit-b-201918).
文摘Digital watermarking technology plays an important role in detecting malicious tampering and protecting image copyright.However,in practical applications,this technology faces various problems such as severe image distortion,inaccurate localization of the tampered regions,and difficulty in recovering content.Given these shortcomings,a fragile image watermarking algorithm for tampering blind-detection and content self-recovery is proposed.The multi-feature watermarking authentication code(AC)is constructed using texture feature of local binary patterns(LBP),direct coefficient of discrete cosine transform(DCT)and contrast feature of gray level co-occurrence matrix(GLCM)for detecting the tampered region,and the recovery code(RC)is designed according to the average grayscale value of pixels in image blocks for recovering the tampered content.Optimal pixel adjustment process(OPAP)and least significant bit(LSB)algorithms are used to embed the recovery code and authentication code into the image in a staggered manner.When detecting the integrity of the image,the authentication code comparison method and threshold judgment method are used to perform two rounds of tampering detection on the image and blindly recover the tampered content.Experimental results show that this algorithm has good transparency,strong and blind detection,and self-recovery performance against four types of malicious attacks and some conventional signal processing operations.When resisting copy-paste,text addition,cropping and vector quantization under the tampering rate(TR)10%,the average tampering detection rate is up to 94.09%,and the peak signal-to-noise ratio(PSNR)of the watermarked image and the recovered image are both greater than 41.47 and 40.31 dB,which demonstrates its excellent advantages compared with other related algorithms in recent years.
基金supported by the Second Batch of Key Textbook Construction Projects of“14th Five-Year Plan”of Zhejiang Vocational Colleges(SZDJC-2412).
文摘Roadbed disease detection is essential for maintaining road functionality.Ground penetrating radar(GPR)enables non-destructive detection without drilling.However,current identification often relies on manual inspection,which requires extensive experience,suffers from low efficiency,and is highly subjective.As the results are presented as radar images,image processing methods can be applied for fast and objective identification.Deep learning-based approaches now offer a robust solution for automated roadbed disease detection.This study proposes an enhanced Faster Region-based Convolutional Neural Networks(R-CNN)framework integrating ResNet-50 as the backbone and two-dimensional discrete Fourier spectrum transformation(2D-DFT)for frequency-domain feature fusion.A dedicated GPR image dataset comprising 1650 annotated images was constructed and augmented to 6600 images via median filtering,histogram equalization,and binarization.The proposed model segments defect regions,applies binary masking,and fuses frequency-domain features to improve small-target detection under noisy backgrounds.Experimental results show that the improved Faster R-CNN achieves a mean Average Precision(mAP)of 0.92,representing a 0.22 increase over the baseline.Precision improved by 26%while recall remained stable at 87%.The model was further validated on real urban road data,demonstrating robust detection capability even under interference.These findings highlight the potential of combining GPR with deep learning for efficient,non-destructive roadbed health monitoring.
文摘Background:Medical imaging advancements are constrained by fundamental trade-offs between acquisition speed,radiation dose,and image quality,forcing clinicians to work with noisy,incomplete data.Existing reconstruction methods either compromise on accuracy with iterative algorithms or suffer from limited generalizability with task-specific deep learning approaches.Methods:We present LDM-PIR,a lightweight physics-conditioned diffusion multi-model for medical image reconstruction that addresses key challenges in magnetic resonance imaging(MRI),CT,and low-photon imaging.Unlike traditional iterative methods,which are computationally expensive,or task-specific deep learning approaches lacking generalizability,integrates three innovations.A physics-conditioned diffusion framework that embeds acquisition operators(Fourier/Radon transforms)and noise models directly into the reconstruction process.A multi-model architecture that unifies denoising,inpainting,and super-resolution via shared weight conditioning.A lightweight design(2.1M parameters)enabling rapid inference(0.8s/image on GPU).Through self-supervised fine-tuning with measurement consistency losses adapts to new imaging modalities using fewer annotated samples.Results:Achieves state-of-the-art performance on fastMRI(peak signal-to-noise ratio(PSNR):34.04 for single-coil/31.50 for multi-coil)and Lung Image Database Consortium and Image Database Resource Initiative(28.83 PSNR under Poisson noise).Clinical evaluations demonstrate superior preservation of anatomical structures,with SSIM improvements of 8.8%for single-coil and 4.36%for multi-coil MRI over uDPIR.Conclusion:It offers a flexible,efficient,and scalable solution for medical image reconstruction,addressing the challenges of noise,undersampling,and modality generalization.The model’s lightweight design allows for rapid inference,while its self-supervised fine-tuning capability minimizes reliance on large annotated datasets,making it suitable for real-world clinical applications.
文摘The advent of 5G technology has significantly enhanced the transmission of images over networks,expanding data accessibility and exposure across various applications in digital technology and social media.Consequently,the protection of sensitive data has become increasingly critical.Regardless of the complexity of the encryption algorithm used,a robust and highly secure encryption key is essential,with randomness and key space being crucial factors.This paper proposes a new Robust Deoxyribonucleic Acid(RDNA)nucleotide-based encryption method.The RDNA encryption method leverages the unique properties of DNA nucleotides,including their inherent randomness and extensive key space,to generate a highly secure encryption key.By employing transposition and substitution operations,the RDNA method ensures significant diffusion and confusion in the encrypted images.Additionally,it utilises a pseudorandom generation technique based on the random sequence of nucleotides in the DNA secret key.The performance of the RDNA encryption method is evaluated through various statistical and visual tests,and compared against established encryption methods such as 3DES,AES,and a DNA-based method.Experimental results demonstrate that the RDNA encryption method outperforms its rivals in the literature,and achieves superior performance in terms of information entropy,avalanche effect,encryption execution time,and correlation reduction,while maintaining competitive values for NMAE,PSNR,NPCR,and UACI.The high degree of randomness and sensitivity to key changes inherent in the RDNA method offers enhanced security,making it highly resistant to brute force and differential attacks.
文摘Military image encryption plays a vital role in ensuring the secure transmission of sensitive visual information from unauthorized access.This paper proposes a new Tri-independent keying method for encrypting military images.The proposed encryption method is based on multilevel security stages of pixel-level scrambling,bitlevel manipulation,and block-level shuffling operations.For having a vast key space,the input password is hashed by the Secure Hash Algorithm 256-bit(SHA-256)for generating independently deterministic keys used in the multilevel stages.A piecewise pixel-level scrambling function is introduced to perform a dual flipping process controlled with an adaptive key for obscuring the spatial relationships between the adjacent pixels.Adynamicmasking scheme is presented for conducting a bit-level manipulation based on distinct keys that change over image regions,providing completely different encryption results on identical regions.To handle the global correlation between large-scale patterns,a chaotic index-map system is employed for shuffling image regions randomly across the image domain based on a logistic map seeded with a private key.Experimental results on a dataset of military images show the effectiveness of the proposed encryption method in producing excellent quantitative and qualitative results.The proposed method obtains uniform histogram distributions,high entropy values around the ideal(≈8 bits),Number of Pixel Change Rate(NPCR)values above 99.5%,and low Peak Signal-to-Noise Ratio(PSNR)over all encrypted images.This validates the robustness of the proposed method against cryptanalytic attacks,verifying its ability to serve as a practical basis for secure image transmission in defense systems.
基金National Natural Science Foundation of China under Grants No.62171047,U22B2001,62271065,62001051Beijing Natural Science Foundation under Grant L223027BUPT Excellent Ph.D Students Foundation under Grants CX2021114。
文摘This article studies the problem of image segmentation-based semantic communication in autonomous driving.In real traffic scenes,the detecting of objects(e.g.,vehicles and pedestrians)is more important to guarantee driving safety,which is always ignored in existing works.Therefore,we propose a vehicular image segmentation-oriented semantic communication system,termed VIS-SemCom,focusing on transmitting and recovering image semantic features of high-important objects to reduce transmission redundancy.First,we develop a semantic codec based on Swin Transformer architecture,which expands the perceptual field thus improving the segmentation accuracy.To highlight the important objects'accuracy,we propose a multi-scale semantic extraction method by assigning the number of Swin Transformer blocks for diverse resolution semantic features.Also,an importance-aware loss incorporating important levels is devised,and an online hard example mining(OHEM)strategy is proposed to handle small sample issues in the dataset.Finally,experimental results demonstrate that the proposed VIS-SemCom can achieve a significant mean intersection over union(mIoU)performance in the SNR regions,a reduction of transmitted data volume by about 60%at 60%mIoU,and improve the segmentation accuracy of important objects,compared to baseline image communication.
基金Supported by the"The 14th Five Year Plan"Hubei Provincial ad-vantaged characteristic disciplines(groups)project of Wuhan University of Science and Technology(Grant No.2023B0404)National Natural Science Foundation of China(Grant Nos.52275503 and 72471181)+2 种基金Hubei Provincial Outstanding Youth Fund of China(Grant No.2023AFA092)Hubei Provincial Natural Science Foundation of China(Grant No.2023AFB915)Hubei Provincial Key Research and Development Plan Project of China(Grant No.2023BAB048).
文摘Common strong noise interferences like metal splashes,smoke,and arc light during welding can seriously pollute the laser stripe images,causing the tracking model to drift and leading to tracking failure.At present,there are already many mature methods for identifying and extracting feature points of linear laser stripes.When the laser stripe forms a curved shape on the surface of the workpiece,these linear methods will no longer be applicable.To eliminate interference sources,enhance the robustness of the weld tracking model,and effectively extract the feature points of curved laser stripes under strong noise conditions.This paper proposes a Conditional Generative Adversarial Network(CGAN)based anti-interference recognition method for welding images.The generator adopts an improved U-Net++structure,adds a Multi-scale Channel Attention module(MS-CAM),introduces Deep Supervision,and proposes a Multi-output Fusion strategy(MOFS)in the output result to en-hance the image inpainting effect;the discriminator uses PatchGAN.The center of the laser stripe is obtained using the grayscale center of mass method and then combined with polynomial fitting to extract the feature points of the weld seam.The experimental results show that the PSNR of the inpainting image is 26.24 dB,the SSIM is 0.98,and the LPIPS is 0.032.The centerline of the inpainting image and the centerline of the noise-free image laser stripe are fitted with a curve.The error of centerline feature points is no more than 5%,confirming the superiority and feasibility of the method.
