This paper presents an approach of singular value de- composition plus digital phase lock loop to solve the difficult problem of blind pseudo-noise （PN） sequence estimation in low signal to noise ratios （SNR） dire...This paper presents an approach of singular value de- composition plus digital phase lock loop to solve the difficult problem of blind pseudo-noise （PN） sequence estimation in low signal to noise ratios （SNR） direct sequence spread spectrum （DS-SS） signals with residual carrier. This approach needs some given parameters, such as the period and code rate of PN sequence. The received signal is firstly sampled and divided into non-overlapping signal vectors according to a temporal window, whose duration is two periods of PN sequence. An autocorrelation matrix is then computed and accumulated by those signal vectors one by one. The PN sequence with residual carrier can be estimated by the principal eigenvector of the autocorrelation matrix. Further more, a digital phase lock loop is used to process the estimated PN sequence, it estimates and tracks the residual carrier and removes the residual carrier in the end. Theory analysis and computer simulation results show that this approach can effectively realize the PN sequence blind estimation from the input DS-SS signals with residual carrier in lower SNR.展开更多
In order to solve the problem of coherent signal subspace method(CSSM) depending on the estimated accuracy of signal subspace, a new direction of arrival(DOA) estimation method of wideband source, which is based on it...In order to solve the problem of coherent signal subspace method(CSSM) depending on the estimated accuracy of signal subspace, a new direction of arrival(DOA) estimation method of wideband source, which is based on iterative adaptive spectral reconstruction, is proposed. Firstly, the wideband signals are divided into several narrowband signals of different frequency bins by discrete Fourier transformation(DFT). Then, the signal matched power spectrum in referenced frequency bins is computed, which can form the initial covariance matrix. Finally, the linear restrained minimum variance spectral(Capon spectral) of signals in other frequency bins are reconstructed using sequential iterative means, so the DOA can be estimated by the locations of spectral peaks. Theoretical analysis and simulation results show the proposed method based on the iterative spectral reconstruction for the covariance matrices of all sub-bands can avoid the problem of determining the signal subspace accurately with the coherent signal subspace method under the conditions of small samples and low signal to noise ratio(SNR), and it can also realize full dimensional focusing of different sub-band data, which can be applied to coherent sources and can significantly improve the accuracy of DOA estimation.展开更多
A system that allows computer interaction by disabled people with very low mobility and who cannot use the standard procedure based on keyboard and mouse is presented. The development device uses the patient’s volunt...A system that allows computer interaction by disabled people with very low mobility and who cannot use the standard procedure based on keyboard and mouse is presented. The development device uses the patient’s voluntary biomechanical signals, specifically, winks—which constitute an ability that generally remains in this kind of patients—, as interface to control the computer. A prototype based on robust and low-cost elements has been built and its performance has been validated through real trials by 16 users without previous training. The system can be optimized after a learning period in order to be adapted to every user. Also, good results were obtained in a subjective satisfaction survey that was completed by the users after carrying out the test trials.展开更多
In many domains of science and technology, as the need for secured transmission of information has grown over the years, a variety of methods have been studied and devised to achieve this goal. In this paper, we prese...In many domains of science and technology, as the need for secured transmission of information has grown over the years, a variety of methods have been studied and devised to achieve this goal. In this paper, we present an information securing method using chaos encryption. Our proposal uses only one chaotic oscillator both for signal encryption and decryption for?avoiding the delicate synchronisation step. We carried out numerical and electronic simulations of the proposed circuit using electrocardiographic signals as input. Results obtained from both simulations were compared and exhibited a good agreement proving the suitability of our system for signal encryption and decryption.展开更多
The topic of this paper is the utilization of time for optical information processing. As clock rates in computing and communication systems increase and reach the THz border, optical techniques for signal filtering, ...The topic of this paper is the utilization of time for optical information processing. As clock rates in computing and communication systems increase and reach the THz border, optical techniques for signal filtering, shaping and clock distribution become attractive. We discuss the use of optics in temporal processing and consider in particular diffractive solutions. In part one of this paper, we discuss the basic concepts of temporal optics.展开更多
The topic of this presentation is the utilization of time for optical information processing. As clock rates in computing and communication systems increase and reach the THz border, optical techniques for signal filt...The topic of this presentation is the utilization of time for optical information processing. As clock rates in computing and communication systems increase and reach the THz border, optical techniques for signal filtering, shaping and clock distribution become attractive. We discuss the use of optics in temporal processing and consider in particular diffractive solutions, in this paper, we describe the use of double diffraction for implementing an ultrafast tapped-delay line.展开更多
The strawberry crimp nematode(Aphelenchoides fragariae) is a serious pathogen of ornamental crops and a significant quarantine concern in approximately 50 countries and regions,including China.A nematode population be...The strawberry crimp nematode(Aphelenchoides fragariae) is a serious pathogen of ornamental crops and a significant quarantine concern in approximately 50 countries and regions,including China.A nematode population belonging to the genus Aphelenchoides was isolated from symptomatic leaves of fuchsia plants(Fuchsia×hybrida Hort.ex Sieb.& Voss.) in Chengdu,Sichuan Province,China.Morphological and morphometric characteristics were determined using light microscopy and scanning electron microscopy.Detailed examination revealed diagnostic features consistent with A.fragariae.Three ribosomal DNA(rDNA) regions,i.e.,partial small subunit(SSU) rRNA,D2-D3 expansion segments of the large subunit(LSU) rRNA,and the internal transcribed spacer(ITS),were amplified and sequenced.Bayesian phylogenetic analyses based on these sequences placed the isolate in a well-supported monophyletic clade with reference A.fragariae specimens,clearly separated from other Aphelenchoides species.Furthermore,host-suitability assays demonstrated that this nematode population not only infects and reproduces on Fuchsia×hybrida,but also on Fragaria ananassa and Pteris vittata,two known hosts of A.fragariae.Collectively,morphological,molecular,and host-range evidence confirm the identification of this nematode as A.fragariae.To our knowledge,this represents the first molecular and morphological confirmation of A.fragariae in China,and the first report of Fuchsia×hybrida as a natural host for this species.展开更多
Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows rais...Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows raises concerns,particularly the risk of subtle distortions or hallucinations that may undermine diagnostic accuracy and weaken trust in AI-assisted decision-making.To address this challenge,we propose a hybrid deep learning framework designed to detect GAN-induced artifacts in medical images,thereby reinforcing the reliability of AI-driven diagnostics.The framework integrates low-level statistical descriptors,including high-frequency residuals and Gray-Level Co-occurrence Matrix(GLCM)texture features,with high-level semantic representations extracted from a pre-trained ResNet18.This dual-stream approach enables detection of both pixel-level anomalies and structural inconsistencies introduced by GAN-based manipulation.We validated the framework on a curated dataset of 10,000 medical images,evenly split between authentic and GAN-generated samples across four modalities:MRI,CT,X-ray,and fundus photography.To improve generalizability to real-world clinical settings,we incorporated domain adaptation strategies such as adversarial training and style transfer,reducing domain shift by 15%.Experimental results demonstrate robust performance,achieving 92.6%accuracy and an F1-score of 0.91 on synthetic test data,and maintaining strong performance on real-world GAN-modified images with 87.3%accuracy and an F1-score of 0.85.Additionally,the model attained an AUC of 0.96 and an average precision of 0.92,outperforming conventional GAN detection pipelines and baseline Convolutional Neural Network(CNN)architectures.These findings establish the proposed framework as an effective and reliable solution for detecting GAN-induced hallucinations in medical imaging,representing an important step toward building trustworthy and clinically deployable AI systems.展开更多
Lung cancer remains a major global health challenge,with early diagnosis crucial for improved patient survival.Traditional diagnostic techniques,including manual histopathology and radiological assessments,are prone t...Lung cancer remains a major global health challenge,with early diagnosis crucial for improved patient survival.Traditional diagnostic techniques,including manual histopathology and radiological assessments,are prone to errors and variability.Deep learning methods,particularly Vision Transformers(ViT),have shown promise for improving diagnostic accuracy by effectively extracting global features.However,ViT-based approaches face challenges related to computational complexity and limited generalizability.This research proposes the DualSet ViT-PSO-SVM framework,integrating aViTwith dual attentionmechanisms,Particle Swarm Optimization(PSO),and SupportVector Machines(SVM),aiming for efficient and robust lung cancer classification acrossmultiple medical image datasets.The study utilized three publicly available datasets:LIDC-IDRI,LUNA16,and TCIA,encompassing computed tomography(CT)scans and histopathological images.Data preprocessing included normalization,augmentation,and segmentation.Dual attention mechanisms enhanced ViT’s feature extraction capabilities.PSO optimized feature selection,and SVM performed classification.Model performance was evaluated on individual and combined datasets,benchmarked against CNN-based and standard ViT approaches.The DualSet ViT-PSO-SVM significantly outperformed existing methods,achieving superior accuracy rates of 97.85%(LIDC-IDRI),98.32%(LUNA16),and 96.75%(TCIA).Crossdataset evaluations demonstrated strong generalization capabilities and stability across similar imagingmodalities.The proposed framework effectively bridges advanced deep learning techniques with clinical applicability,offering a robust diagnostic tool for lung cancer detection,reducing complexity,and improving diagnostic reliability and interpretability.展开更多
critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study pr...critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study proposes a non-invasive approach using digital mammography images and deep learning algorithm for classifying breast cancer molecular subtypes.Four pretrained models,including two Convolutional Neural Networks(MobileNet_V3_Large and VGG-16)and two Vision Transformers(ViT_B_16 and ViT_Base_Patch16_Clip_224)were fine-tuned to classify images into HER2-enriched,Luminal,Normal-like,and Triple Negative subtypes.Hyperparameter tuning,including learning rate adjustment and layer freezing strategies,was applied to optimize performance.Among the evaluated models,ViT_Base_Patch16_Clip_224 achieved the highest test accuracy(94.44%),with equally high precision,recall,and F1-score of 0.94,demonstrating excellent generalization.MobileNet_V3_Large achieved the same accuracy but showed less training stability.In contrast,VGG-16 recorded the lowest performance,indicating a limitation in its generalizability for this classification task.The study also highlighted the superior performance of the Vision Transformer models over CNNs,particularly due to their ability to capture global contextual features and the benefit of CLIP-based pretraining in ViT_Base_Patch16_Clip_224.To enhance clinical applicability,a graphical user interface(GUI)named“BCMS Dx”was developed for streamlined subtype prediction.Deep learning applied to mammography has proven effective for accurate and non-invasive molecular subtyping.The proposed Vision Transformer-based model and supporting GUI offer a promising direction for augmenting diagnostic workflows,minimizing the need for invasive procedures,and advancing personalized breast cancer management.展开更多
Little is known about how chronic inflammation contributes to the progression of hepatoceUular carcinoma （HCC）, especially the initiation of cancer. To uncover the critical transition from chronic inflammation to HC...Little is known about how chronic inflammation contributes to the progression of hepatoceUular carcinoma （HCC）, especially the initiation of cancer. To uncover the critical transition from chronic inflammation to HCC and the molecular mechanisms at a network level, we analyzed the time-series proteomic data of woodchuck hepatitis virus/c.myc mice and age-matched wt-C57BL/6 mice using our dynamical network biomarker （DNB） model. DNB analysis indicated that the 5th month after birth of transgenic mice was the critical period of cancer initiation, just before the critical transition, which is consistent with clinical symptoms. Meanwhile, the DNB-associated network showed a drastic inversion of protein expression and coexpression levels before and after the critical transition. Two members of DNB, PLA2G6 and CYP2C44, along with their associated differentially expressed proteins, were found to induce dysfunction of arachidonic acid metabolism, further activate inflammatory responses through inflammatory mediator regulation of transient receptor potential channels, and finally lead to impairments of liver detoxification and malignant transition to cancer. As a c-Myc target, PLA2G6 positively correlated with c-Myc in expression, showing a trend from decreasing to increasing during carcinogenesis, with the minimal point at the critical transition or tipping point. Such trend of homologous PLA2G6 and c-Myc was also observed during human hepatocarcinogenesis, with the minimal point at high-grade dysplastic nodules （a stage just before the carcinogenesis）. Our study implies that PLA2G6 might function as an oncogene like famous c-Myc during hepatocar- cinogenesis, while downregulation of PLA2G6 and c-Myc could be a warning signal indicating imminent carcinogenesis.展开更多
The phase group synchronization between any signals is further revealed,which is based on proposing the new concepts of the greatest common factor frequency,the least common multiple period,quantized phase shift resol...The phase group synchronization between any signals is further revealed,which is based on proposing the new concepts of the greatest common factor frequency,the least common multiple period,quantized phase shift resolution,equivalent phase comparison frequency and so on.Then the problem of phase comparison and processing between different frequency signals is solved and shown in detail.Using the basic principle and the variation law of group phase difference,the frequency stability better than 10-14/s can be easily obtained in the time&frequency measurement and control domain,and experimental results also show the phase relations between atomic energy level transition signal and the locked crystal oscillator signal in an active hydrogen atomic clock are strict phase group synchronization,and locked precision with 10-13/s can be reached based on phase group synchronization.The phase group synchronization can provide technical support to frequency linking among radio frequency,microwave and light frequency.展开更多
Prostate cancer(PCa)remains a major cause of cancer-related mortality in men,largely due to therapy resistance and metastatic progression.Increasing evidence highlights the tumor microenvironment(TME),particularly can...Prostate cancer(PCa)remains a major cause of cancer-related mortality in men,largely due to therapy resistance and metastatic progression.Increasing evidence highlights the tumor microenvironment(TME),particularly cancer-associated fibroblasts(CAFs),as a critical determinant of disease behavior.CAFs constitute a heterogeneous population originating from fibroblasts,mesenchymal stem cells,endothelial cells,epithelial cells undergoing epithelial-mesenchymal transition(EMT),and adipose tissue.Through dynamic crosstalk with tumor,immune,endothelial,and adipocyte compartments,CAFs orchestrate oncogenic processes including tumor proliferation,invasion,immune evasion,extracellular matrix remodeling,angiogenesis,and metabolic reprogramming.This review comprehensively summarizes the cellular origins,phenotypic and functional heterogeneity,and spatial distribution of CAFs within the prostate TME.We further elucidate the molecular mechanisms by which CAFs regulate PCa progression and therapeutic resistance,and critically evaluate emerging strategies to therapeutically target CAFmediated signaling,metabolic,and immune pathways.By integrating recent advances from single-cell and spatial transcriptomics(ST),our objective is to provide a holistic framework for understanding CAF biology and to highlight potential avenues for stromal reprogramming as an adjunct to current PCa therapies.展开更多
The contrast function remains to be an open problem in blind source separation （BSS） when the number of source signals is unknown and/or dynamically changed. The paper studies this problem and proves that the mutual...The contrast function remains to be an open problem in blind source separation （BSS） when the number of source signals is unknown and/or dynamically changed. The paper studies this problem and proves that the mutual information is still the contrast function for BSS if the mixing matrix is of full column rank. The mutual information reaches its minimum at the separation points, where the random outputs of the BSS system are the scaled and permuted source signals, while the others are zero outputs. Using the property that the transpose of the mixing matrix and a matrix composed by m observed signals have the indentical null space with probability one, a practical method, which can detect the unknown number of source signals n, ulteriorly traces the dynamical change of the sources number with a few of data, is proposed. The effectiveness of the proposed theorey and the developed novel algorithm is verified by adaptive BSS simulations with unknown and dynamically changing number of source signals.展开更多
Artificial intelligence(AI)is transforming the diagnostic landscape of malignant tumors in the urinary system,including prostate cancer,bladder cancer,and renal cell carcinoma(RCC).By integrating imaging,pathology,and...Artificial intelligence(AI)is transforming the diagnostic landscape of malignant tumors in the urinary system,including prostate cancer,bladder cancer,and renal cell carcinoma(RCC).By integrating imaging,pathology,and molecular data,AI enhances the precision and reproducibility of tumor detection,grading,and risk stratification.In prostate cancer,AI-assisted multiparametric Magnetic resonance imaging(MRI)and digital pathology systems improve lesion localization and Gleason scoring.For bladder cancer,deep learning-based cystoscopy and radiomics models from Computed tomography/magnetic resonance imaging(CT/MRI)enable real-time lesion segmentation and non-invasive biomarker prediction,such as Programmed Cell Death-Ligand 1(PD-L1)expression.In RCC,AI,combined with CT/MRI and multi-omics data,aids in subtype classification and prognostic prediction,supporting personalized therapy.However,despite these promising advances,challenges such as data standardization,model generalizability,interpretability,and regulatory compliance hinder AI’s clinical translation.This review outlines the current state of AI in urological cancer diagnosis and prognosis,its technological innovations,and the clinical challenges and opportunities that lie ahead.展开更多
A wide-band (1530-1610 nm) and high efficient double-pass discrete Raman amplifier is reported. In this Raman amplifier, by using a one-end gilded fiber as the broadband reflector, signals and multi-pump are both refl...A wide-band (1530-1610 nm) and high efficient double-pass discrete Raman amplifier is reported. In this Raman amplifier, by using a one-end gilded fiber as the broadband reflector, signals and multi-pump are both reflected to propagate through the gain fiber for a second time. An increase in net gain of more than 150% has been achieved compared with that in the typical co-pumped Raman amplifier. The advantages of this proposed new configuration have been experimentally studied by comparing with the recently existing Raman amplifier configurations.展开更多
Two ring signals P1, P2 beyond the Uranian ε Ring are detected from noise by statistical method. Applying the time series test and the wave form correlation test to the Beijing data of March 10, 1977 occultation by t...Two ring signals P1, P2 beyond the Uranian ε Ring are detected from noise by statistical method. Applying the time series test and the wave form correlation test to the Beijing data of March 10, 1977 occultation by the Uranus systems, we discovered two ring signals beyond the ε Ring. The method and formulae used and the meaning of the sign are the same as in Ref. [1].展开更多
基金supported by the National Natural Science Foundation of China (10776040 60602057)+4 种基金Program for New Century Excellent Talents in University (NCET)the Project of Key Laboratory of Signal and Information Processing of Chongqing (CSTC2009CA2003)the Natural Science Foundation of Chongqing Science and Technology Commission (CSTC2009BB2287)the Natural Science Foundation of Chongqing Municipal Education Commission (KJ060509 KJ080517)
文摘This paper presents an approach of singular value de- composition plus digital phase lock loop to solve the difficult problem of blind pseudo-noise （PN） sequence estimation in low signal to noise ratios （SNR） direct sequence spread spectrum （DS-SS） signals with residual carrier. This approach needs some given parameters, such as the period and code rate of PN sequence. The received signal is firstly sampled and divided into non-overlapping signal vectors according to a temporal window, whose duration is two periods of PN sequence. An autocorrelation matrix is then computed and accumulated by those signal vectors one by one. The PN sequence with residual carrier can be estimated by the principal eigenvector of the autocorrelation matrix. Further more, a digital phase lock loop is used to process the estimated PN sequence, it estimates and tracks the residual carrier and removes the residual carrier in the end. Theory analysis and computer simulation results show that this approach can effectively realize the PN sequence blind estimation from the input DS-SS signals with residual carrier in lower SNR.
基金supported by the National Natural Science Foundation of China(61671352)the open foundation of Key Laboratory of Cognitive Radio and Information Processing,Ministry of Education(Guilin University of Electronic Technology)(CRKL160206)Xi’an University of Science and Technology Doctor(after)Start Gold Project(2017QDJ018)
文摘In order to solve the problem of coherent signal subspace method(CSSM) depending on the estimated accuracy of signal subspace, a new direction of arrival(DOA) estimation method of wideband source, which is based on iterative adaptive spectral reconstruction, is proposed. Firstly, the wideband signals are divided into several narrowband signals of different frequency bins by discrete Fourier transformation(DFT). Then, the signal matched power spectrum in referenced frequency bins is computed, which can form the initial covariance matrix. Finally, the linear restrained minimum variance spectral(Capon spectral) of signals in other frequency bins are reconstructed using sequential iterative means, so the DOA can be estimated by the locations of spectral peaks. Theoretical analysis and simulation results show the proposed method based on the iterative spectral reconstruction for the covariance matrices of all sub-bands can avoid the problem of determining the signal subspace accurately with the coherent signal subspace method under the conditions of small samples and low signal to noise ratio(SNR), and it can also realize full dimensional focusing of different sub-band data, which can be applied to coherent sources and can significantly improve the accuracy of DOA estimation.
文摘A system that allows computer interaction by disabled people with very low mobility and who cannot use the standard procedure based on keyboard and mouse is presented. The development device uses the patient’s voluntary biomechanical signals, specifically, winks—which constitute an ability that generally remains in this kind of patients—, as interface to control the computer. A prototype based on robust and low-cost elements has been built and its performance has been validated through real trials by 16 users without previous training. The system can be optimized after a learning period in order to be adapted to every user. Also, good results were obtained in a subjective satisfaction survey that was completed by the users after carrying out the test trials.
文摘In many domains of science and technology, as the need for secured transmission of information has grown over the years, a variety of methods have been studied and devised to achieve this goal. In this paper, we present an information securing method using chaos encryption. Our proposal uses only one chaotic oscillator both for signal encryption and decryption for?avoiding the delicate synchronisation step. We carried out numerical and electronic simulations of the proposed circuit using electrocardiographic signals as input. Results obtained from both simulations were compared and exhibited a good agreement proving the suitability of our system for signal encryption and decryption.
文摘The topic of this paper is the utilization of time for optical information processing. As clock rates in computing and communication systems increase and reach the THz border, optical techniques for signal filtering, shaping and clock distribution become attractive. We discuss the use of optics in temporal processing and consider in particular diffractive solutions. In part one of this paper, we discuss the basic concepts of temporal optics.
文摘The topic of this presentation is the utilization of time for optical information processing. As clock rates in computing and communication systems increase and reach the THz border, optical techniques for signal filtering, shaping and clock distribution become attractive. We discuss the use of optics in temporal processing and consider in particular diffractive solutions, in this paper, we describe the use of double diffraction for implementing an ultrafast tapped-delay line.
基金financially supported by the Shaanxi Innovation Team Project,China (2024RS-CXTD-73)the National Natural Science Foundation of China (31772136)。
文摘The strawberry crimp nematode(Aphelenchoides fragariae) is a serious pathogen of ornamental crops and a significant quarantine concern in approximately 50 countries and regions,including China.A nematode population belonging to the genus Aphelenchoides was isolated from symptomatic leaves of fuchsia plants(Fuchsia×hybrida Hort.ex Sieb.& Voss.) in Chengdu,Sichuan Province,China.Morphological and morphometric characteristics were determined using light microscopy and scanning electron microscopy.Detailed examination revealed diagnostic features consistent with A.fragariae.Three ribosomal DNA(rDNA) regions,i.e.,partial small subunit(SSU) rRNA,D2-D3 expansion segments of the large subunit(LSU) rRNA,and the internal transcribed spacer(ITS),were amplified and sequenced.Bayesian phylogenetic analyses based on these sequences placed the isolate in a well-supported monophyletic clade with reference A.fragariae specimens,clearly separated from other Aphelenchoides species.Furthermore,host-suitability assays demonstrated that this nematode population not only infects and reproduces on Fuchsia×hybrida,but also on Fragaria ananassa and Pteris vittata,two known hosts of A.fragariae.Collectively,morphological,molecular,and host-range evidence confirm the identification of this nematode as A.fragariae.To our knowledge,this represents the first molecular and morphological confirmation of A.fragariae in China,and the first report of Fuchsia×hybrida as a natural host for this species.
基金supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2601).
文摘Generative Adversarial Networks(GANs)have become valuable tools in medical imaging,enabling realistic image synthesis for enhancement,augmentation,and restoration.However,their integration into clinical workflows raises concerns,particularly the risk of subtle distortions or hallucinations that may undermine diagnostic accuracy and weaken trust in AI-assisted decision-making.To address this challenge,we propose a hybrid deep learning framework designed to detect GAN-induced artifacts in medical images,thereby reinforcing the reliability of AI-driven diagnostics.The framework integrates low-level statistical descriptors,including high-frequency residuals and Gray-Level Co-occurrence Matrix(GLCM)texture features,with high-level semantic representations extracted from a pre-trained ResNet18.This dual-stream approach enables detection of both pixel-level anomalies and structural inconsistencies introduced by GAN-based manipulation.We validated the framework on a curated dataset of 10,000 medical images,evenly split between authentic and GAN-generated samples across four modalities:MRI,CT,X-ray,and fundus photography.To improve generalizability to real-world clinical settings,we incorporated domain adaptation strategies such as adversarial training and style transfer,reducing domain shift by 15%.Experimental results demonstrate robust performance,achieving 92.6%accuracy and an F1-score of 0.91 on synthetic test data,and maintaining strong performance on real-world GAN-modified images with 87.3%accuracy and an F1-score of 0.85.Additionally,the model attained an AUC of 0.96 and an average precision of 0.92,outperforming conventional GAN detection pipelines and baseline Convolutional Neural Network(CNN)architectures.These findings establish the proposed framework as an effective and reliable solution for detecting GAN-induced hallucinations in medical imaging,representing an important step toward building trustworthy and clinically deployable AI systems.
文摘Lung cancer remains a major global health challenge,with early diagnosis crucial for improved patient survival.Traditional diagnostic techniques,including manual histopathology and radiological assessments,are prone to errors and variability.Deep learning methods,particularly Vision Transformers(ViT),have shown promise for improving diagnostic accuracy by effectively extracting global features.However,ViT-based approaches face challenges related to computational complexity and limited generalizability.This research proposes the DualSet ViT-PSO-SVM framework,integrating aViTwith dual attentionmechanisms,Particle Swarm Optimization(PSO),and SupportVector Machines(SVM),aiming for efficient and robust lung cancer classification acrossmultiple medical image datasets.The study utilized three publicly available datasets:LIDC-IDRI,LUNA16,and TCIA,encompassing computed tomography(CT)scans and histopathological images.Data preprocessing included normalization,augmentation,and segmentation.Dual attention mechanisms enhanced ViT’s feature extraction capabilities.PSO optimized feature selection,and SVM performed classification.Model performance was evaluated on individual and combined datasets,benchmarked against CNN-based and standard ViT approaches.The DualSet ViT-PSO-SVM significantly outperformed existing methods,achieving superior accuracy rates of 97.85%(LIDC-IDRI),98.32%(LUNA16),and 96.75%(TCIA).Crossdataset evaluations demonstrated strong generalization capabilities and stability across similar imagingmodalities.The proposed framework effectively bridges advanced deep learning techniques with clinical applicability,offering a robust diagnostic tool for lung cancer detection,reducing complexity,and improving diagnostic reliability and interpretability.
基金funded by the Ministry of Higher Education(MoHE)Malaysia through the Fundamental Research Grant Scheme—Early Career Researcher(FRGS-EC),grant number FRGSEC/1/2024/ICT02/UNIMAP/02/8.
文摘critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study proposes a non-invasive approach using digital mammography images and deep learning algorithm for classifying breast cancer molecular subtypes.Four pretrained models,including two Convolutional Neural Networks(MobileNet_V3_Large and VGG-16)and two Vision Transformers(ViT_B_16 and ViT_Base_Patch16_Clip_224)were fine-tuned to classify images into HER2-enriched,Luminal,Normal-like,and Triple Negative subtypes.Hyperparameter tuning,including learning rate adjustment and layer freezing strategies,was applied to optimize performance.Among the evaluated models,ViT_Base_Patch16_Clip_224 achieved the highest test accuracy(94.44%),with equally high precision,recall,and F1-score of 0.94,demonstrating excellent generalization.MobileNet_V3_Large achieved the same accuracy but showed less training stability.In contrast,VGG-16 recorded the lowest performance,indicating a limitation in its generalizability for this classification task.The study also highlighted the superior performance of the Vision Transformer models over CNNs,particularly due to their ability to capture global contextual features and the benefit of CLIP-based pretraining in ViT_Base_Patch16_Clip_224.To enhance clinical applicability,a graphical user interface(GUI)named“BCMS Dx”was developed for streamlined subtype prediction.Deep learning applied to mammography has proven effective for accurate and non-invasive molecular subtyping.The proposed Vision Transformer-based model and supporting GUI offer a promising direction for augmenting diagnostic workflows,minimizing the need for invasive procedures,and advancing personalized breast cancer management.
文摘Little is known about how chronic inflammation contributes to the progression of hepatoceUular carcinoma （HCC）, especially the initiation of cancer. To uncover the critical transition from chronic inflammation to HCC and the molecular mechanisms at a network level, we analyzed the time-series proteomic data of woodchuck hepatitis virus/c.myc mice and age-matched wt-C57BL/6 mice using our dynamical network biomarker （DNB） model. DNB analysis indicated that the 5th month after birth of transgenic mice was the critical period of cancer initiation, just before the critical transition, which is consistent with clinical symptoms. Meanwhile, the DNB-associated network showed a drastic inversion of protein expression and coexpression levels before and after the critical transition. Two members of DNB, PLA2G6 and CYP2C44, along with their associated differentially expressed proteins, were found to induce dysfunction of arachidonic acid metabolism, further activate inflammatory responses through inflammatory mediator regulation of transient receptor potential channels, and finally lead to impairments of liver detoxification and malignant transition to cancer. As a c-Myc target, PLA2G6 positively correlated with c-Myc in expression, showing a trend from decreasing to increasing during carcinogenesis, with the minimal point at the critical transition or tipping point. Such trend of homologous PLA2G6 and c-Myc was also observed during human hepatocarcinogenesis, with the minimal point at high-grade dysplastic nodules （a stage just before the carcinogenesis）. Our study implies that PLA2G6 might function as an oncogene like famous c-Myc during hepatocar- cinogenesis, while downregulation of PLA2G6 and c-Myc could be a warning signal indicating imminent carcinogenesis.
基金supported by the Joint Fund for Fostering Talents of National Natural Science Foundation of China and Henan Province(Grant No.U1304618)the Open Fund of Key Laboratory of Precision Navigation and Timing Technology of Chinese Academy of Sciences(Grant No.2012PNTT01)+4 种基金the Postdoctoral Grant of China(Grant Nos.2011M501446,2012T50798)the Basic and Advanced Technology Research Foundation of Henan Province(Grant No.122300410169)The Key Science and Technology Foundation of Zhengzhou City(Grant Nos.131PPTGG411-6,131PCXTD594)the Doctor Fund of Zhengzhou University of Light Industry(Grant No.2011BSJJ031)the Fundamental Research Funds for the Central Universities(Grant No.K5051204003)
文摘The phase group synchronization between any signals is further revealed,which is based on proposing the new concepts of the greatest common factor frequency,the least common multiple period,quantized phase shift resolution,equivalent phase comparison frequency and so on.Then the problem of phase comparison and processing between different frequency signals is solved and shown in detail.Using the basic principle and the variation law of group phase difference,the frequency stability better than 10-14/s can be easily obtained in the time&frequency measurement and control domain,and experimental results also show the phase relations between atomic energy level transition signal and the locked crystal oscillator signal in an active hydrogen atomic clock are strict phase group synchronization,and locked precision with 10-13/s can be reached based on phase group synchronization.The phase group synchronization can provide technical support to frequency linking among radio frequency,microwave and light frequency.
文摘Prostate cancer(PCa)remains a major cause of cancer-related mortality in men,largely due to therapy resistance and metastatic progression.Increasing evidence highlights the tumor microenvironment(TME),particularly cancer-associated fibroblasts(CAFs),as a critical determinant of disease behavior.CAFs constitute a heterogeneous population originating from fibroblasts,mesenchymal stem cells,endothelial cells,epithelial cells undergoing epithelial-mesenchymal transition(EMT),and adipose tissue.Through dynamic crosstalk with tumor,immune,endothelial,and adipocyte compartments,CAFs orchestrate oncogenic processes including tumor proliferation,invasion,immune evasion,extracellular matrix remodeling,angiogenesis,and metabolic reprogramming.This review comprehensively summarizes the cellular origins,phenotypic and functional heterogeneity,and spatial distribution of CAFs within the prostate TME.We further elucidate the molecular mechanisms by which CAFs regulate PCa progression and therapeutic resistance,and critically evaluate emerging strategies to therapeutically target CAFmediated signaling,metabolic,and immune pathways.By integrating recent advances from single-cell and spatial transcriptomics(ST),our objective is to provide a holistic framework for understanding CAF biology and to highlight potential avenues for stromal reprogramming as an adjunct to current PCa therapies.
基金supported by the National Natural Science Foundation of China(Grant No.60496311).
文摘The contrast function remains to be an open problem in blind source separation （BSS） when the number of source signals is unknown and/or dynamically changed. The paper studies this problem and proves that the mutual information is still the contrast function for BSS if the mixing matrix is of full column rank. The mutual information reaches its minimum at the separation points, where the random outputs of the BSS system are the scaled and permuted source signals, while the others are zero outputs. Using the property that the transpose of the mixing matrix and a matrix composed by m observed signals have the indentical null space with probability one, a practical method, which can detect the unknown number of source signals n, ulteriorly traces the dynamical change of the sources number with a few of data, is proposed. The effectiveness of the proposed theorey and the developed novel algorithm is verified by adaptive BSS simulations with unknown and dynamically changing number of source signals.
基金supported by grants from the Hangzhou Key Project for Agricultural and Social Development under Grant No.20231203A12(JZ)the General Program of the Scientific Research Special Project for Post-Marketing Clinical Research of Innovative Drugs,Development Center for Medical Science&Technology,National Health Commission of the People’s Republic of China under Grant No.WKZX2024CX104202(JZ).
文摘Artificial intelligence(AI)is transforming the diagnostic landscape of malignant tumors in the urinary system,including prostate cancer,bladder cancer,and renal cell carcinoma(RCC).By integrating imaging,pathology,and molecular data,AI enhances the precision and reproducibility of tumor detection,grading,and risk stratification.In prostate cancer,AI-assisted multiparametric Magnetic resonance imaging(MRI)and digital pathology systems improve lesion localization and Gleason scoring.For bladder cancer,deep learning-based cystoscopy and radiomics models from Computed tomography/magnetic resonance imaging(CT/MRI)enable real-time lesion segmentation and non-invasive biomarker prediction,such as Programmed Cell Death-Ligand 1(PD-L1)expression.In RCC,AI,combined with CT/MRI and multi-omics data,aids in subtype classification and prognostic prediction,supporting personalized therapy.However,despite these promising advances,challenges such as data standardization,model generalizability,interpretability,and regulatory compliance hinder AI’s clinical translation.This review outlines the current state of AI in urological cancer diagnosis and prognosis,its technological innovations,and the clinical challenges and opportunities that lie ahead.
基金This work was supported by the National Science Foun- dation of China for Distinguished Young Scholars under Grant No. 60125513.
文摘A wide-band (1530-1610 nm) and high efficient double-pass discrete Raman amplifier is reported. In this Raman amplifier, by using a one-end gilded fiber as the broadband reflector, signals and multi-pump are both reflected to propagate through the gain fiber for a second time. An increase in net gain of more than 150% has been achieved compared with that in the typical co-pumped Raman amplifier. The advantages of this proposed new configuration have been experimentally studied by comparing with the recently existing Raman amplifier configurations.
文摘Two ring signals P1, P2 beyond the Uranian ε Ring are detected from noise by statistical method. Applying the time series test and the wave form correlation test to the Beijing data of March 10, 1977 occultation by the Uranus systems, we discovered two ring signals beyond the ε Ring. The method and formulae used and the meaning of the sign are the same as in Ref. [1].
