Objective Primary liver cancer,predominantly hepatocellular carcinoma(HCC),is a significant global health issue,ranking as the sixth most diagnosed cancer and the third leading cause of cancer-related mortality.Accura...Objective Primary liver cancer,predominantly hepatocellular carcinoma(HCC),is a significant global health issue,ranking as the sixth most diagnosed cancer and the third leading cause of cancer-related mortality.Accurate and early diagnosis of HCC is crucial for effective treatment,as HCC and non-HCC malignancies like intrahepatic cholangiocarcinoma(ICC)exhibit different prognoses and treatment responses.Traditional diagnostic methods,including liver biopsy and contrast-enhanced ultrasound(CEUS),face limitations in applicability and objectivity.The primary objective of this study was to develop an advanced,lightweighted classification network capable of distinguishing HCC from other non-HCC malignancies by leveraging the automatic analysis of brightness changes in CEUS images.The ultimate goal was to create a user-friendly and cost-efficient computer-aided diagnostic tool that could assist radiologists in making more accurate and efficient clinical decisions.Methods This retrospective study encompassed a total of 161 patients,comprising 131 diagnosed with HCC and 30 with non-HCC malignancies.To achieve accurate tumor detection,the YOLOX network was employed to identify the region of interest(ROI)on both B-mode ultrasound and CEUS images.A custom-developed algorithm was then utilized to extract brightness change curves from the tumor and adjacent liver parenchyma regions within the CEUS images.These curves provided critical data for the subsequent analysis and classification process.To analyze the extracted brightness change curves and classify the malignancies,we developed and compared several models.These included one-dimensional convolutional neural networks(1D-ResNet,1D-ConvNeXt,and 1D-CNN),as well as traditional machine-learning methods such as support vector machine(SVM),ensemble learning(EL),k-nearest neighbor(KNN),and decision tree(DT).The diagnostic performance of each method in distinguishing HCC from non-HCC malignancies was rigorously evaluated using four key metrics:area under the receiver operating characteristic(AUC),accuracy(ACC),sensitivity(SE),and specificity(SP).Results The evaluation of the machine-learning methods revealed AUC values of 0.70 for SVM,0.56 for ensemble learning,0.63 for KNN,and 0.72 for the decision tree.These results indicated moderate to fair performance in classifying the malignancies based on the brightness change curves.In contrast,the deep learning models demonstrated significantly higher AUCs,with 1D-ResNet achieving an AUC of 0.72,1D-ConvNeXt reaching 0.82,and 1D-CNN obtaining the highest AUC of 0.84.Moreover,under the five-fold cross-validation scheme,the 1D-CNN model outperformed other models in both accuracy and specificity.Specifically,it achieved accuracy improvements of 3.8%to 10.0%and specificity enhancements of 6.6%to 43.3%over competing approaches.The superior performance of the 1D-CNN model highlighted its potential as a powerful tool for accurate classification.Conclusion The 1D-CNN model proved to be the most effective in differentiating HCC from non-HCC malignancies,surpassing both traditional machine-learning methods and other deep learning models.This study successfully developed a user-friendly and cost-efficient computer-aided diagnostic solution that would significantly enhances radiologists’diagnostic capabilities.By improving the accuracy and efficiency of clinical decision-making,this tool has the potential to positively impact patient care and outcomes.Future work may focus on further refining the model and exploring its integration with multimodal ultrasound data to maximize its accuracy and applicability.展开更多
Cotton is an essential agricultural commodity,but its global yield is greatly affected by climate change,which poses a serious threat to the agriculture sector.This review aims to provide an overview of the impact of ...Cotton is an essential agricultural commodity,but its global yield is greatly affected by climate change,which poses a serious threat to the agriculture sector.This review aims to provide an overview of the impact of climate change on cotton production and the use of genomic approaches to increase stress tolerance in cotton.This paper discusses the effects of rising temperatures,changing precipitation patterns,and extreme weather events on cotton yield.It then explores various genomic strategies,such as genomic selection and marker-assisted selection,which can be used to develop stress-tolerant cotton varieties.The review emphasizes the need for interdisciplinary research efforts and policy interventions to mitigate the adverse effects of climate change on cotton production.Furthermore,this paper presents advanced prospects,including genomic selection,gene editing,multi-omics integration,highthroughput phenotyping,genomic data sharing,climate-informed breeding,and phenomics-assisted genomic selection,for enhancing stress resilience in cotton.Those innovative approaches can assist cotton researchers and breeders in developing highly resilient cotton varieties capable of withstanding the challenges posed by climate change,ensuring the sustainable and prosperous future of cotton production.展开更多
Metasurfaces provide a potent platform for the dynamic manipulation of electromagnetic waves.Coupled with phase-change materials,they facilitate the creation of versatile metadevices,showcasing various tunable functio...Metasurfaces provide a potent platform for the dynamic manipulation of electromagnetic waves.Coupled with phase-change materials,they facilitate the creation of versatile metadevices,showcasing various tunable functions based on the transition between amorphous and crystalline states.However,the inherent limitation in tunable states imposes constraints on the multiplexing channels of metadevices.Here,this paper introduces a novel approach-a multi-functional metadevice achieved through the two-level control of the encoding phasechange metaatoms.Utilizing the phase-change material Ge_(2)Sb_(2)Se_(4)Te1(GSST)and high refractive-index liquid diiodomethane(CH_(2)I_(2)),this paper showcases precise control over electromagnetic wave manipulation.The GSST state governs the tunable function,switching it ON and OFF,while the presence of liquid in the hole dictates the deflection angle when the tunable function is active.Importantly,our tunable coding metasurface exhibits robust performance across a broad wavelength spectrum.The incorporation of high refractive-index liquid extends the regulatory dimension of the metadevice,enabling dynamic switching of encoding bit levels.This two-level tunable metadevice,rooted in phase-change materials,presents a promising avenue for the dynamic control of functions.展开更多
Overlooking the issue of false alarm suppression in heterogeneous change detection leads to inferior detection per-formance.This paper proposes a method to handle false alarms in heterogeneous change detection.A light...Overlooking the issue of false alarm suppression in heterogeneous change detection leads to inferior detection per-formance.This paper proposes a method to handle false alarms in heterogeneous change detection.A lightweight network of two channels is bulit based on the combination of convolutional neural network(CNN)and graph convolutional network(GCN).CNNs learn feature difference maps of multitemporal images,and attention modules adaptively fuse CNN-based and graph-based features for different scales.GCNs with a new kernel filter adaptively distinguish between nodes with the same and those with different labels,generating change maps.Experimental evaluation on two datasets validates the efficacy of the pro-posed method in addressing false alarms.展开更多
文摘Objective Primary liver cancer,predominantly hepatocellular carcinoma(HCC),is a significant global health issue,ranking as the sixth most diagnosed cancer and the third leading cause of cancer-related mortality.Accurate and early diagnosis of HCC is crucial for effective treatment,as HCC and non-HCC malignancies like intrahepatic cholangiocarcinoma(ICC)exhibit different prognoses and treatment responses.Traditional diagnostic methods,including liver biopsy and contrast-enhanced ultrasound(CEUS),face limitations in applicability and objectivity.The primary objective of this study was to develop an advanced,lightweighted classification network capable of distinguishing HCC from other non-HCC malignancies by leveraging the automatic analysis of brightness changes in CEUS images.The ultimate goal was to create a user-friendly and cost-efficient computer-aided diagnostic tool that could assist radiologists in making more accurate and efficient clinical decisions.Methods This retrospective study encompassed a total of 161 patients,comprising 131 diagnosed with HCC and 30 with non-HCC malignancies.To achieve accurate tumor detection,the YOLOX network was employed to identify the region of interest(ROI)on both B-mode ultrasound and CEUS images.A custom-developed algorithm was then utilized to extract brightness change curves from the tumor and adjacent liver parenchyma regions within the CEUS images.These curves provided critical data for the subsequent analysis and classification process.To analyze the extracted brightness change curves and classify the malignancies,we developed and compared several models.These included one-dimensional convolutional neural networks(1D-ResNet,1D-ConvNeXt,and 1D-CNN),as well as traditional machine-learning methods such as support vector machine(SVM),ensemble learning(EL),k-nearest neighbor(KNN),and decision tree(DT).The diagnostic performance of each method in distinguishing HCC from non-HCC malignancies was rigorously evaluated using four key metrics:area under the receiver operating characteristic(AUC),accuracy(ACC),sensitivity(SE),and specificity(SP).Results The evaluation of the machine-learning methods revealed AUC values of 0.70 for SVM,0.56 for ensemble learning,0.63 for KNN,and 0.72 for the decision tree.These results indicated moderate to fair performance in classifying the malignancies based on the brightness change curves.In contrast,the deep learning models demonstrated significantly higher AUCs,with 1D-ResNet achieving an AUC of 0.72,1D-ConvNeXt reaching 0.82,and 1D-CNN obtaining the highest AUC of 0.84.Moreover,under the five-fold cross-validation scheme,the 1D-CNN model outperformed other models in both accuracy and specificity.Specifically,it achieved accuracy improvements of 3.8%to 10.0%and specificity enhancements of 6.6%to 43.3%over competing approaches.The superior performance of the 1D-CNN model highlighted its potential as a powerful tool for accurate classification.Conclusion The 1D-CNN model proved to be the most effective in differentiating HCC from non-HCC malignancies,surpassing both traditional machine-learning methods and other deep learning models.This study successfully developed a user-friendly and cost-efficient computer-aided diagnostic solution that would significantly enhances radiologists’diagnostic capabilities.By improving the accuracy and efficiency of clinical decision-making,this tool has the potential to positively impact patient care and outcomes.Future work may focus on further refining the model and exploring its integration with multimodal ultrasound data to maximize its accuracy and applicability.
基金supported by major national R&D projects(No.2023ZD04040-01)National Natural Science Foundation of China(No.5201101621)National Key R&D Plan(No.2022YFD1200304).
文摘Cotton is an essential agricultural commodity,but its global yield is greatly affected by climate change,which poses a serious threat to the agriculture sector.This review aims to provide an overview of the impact of climate change on cotton production and the use of genomic approaches to increase stress tolerance in cotton.This paper discusses the effects of rising temperatures,changing precipitation patterns,and extreme weather events on cotton yield.It then explores various genomic strategies,such as genomic selection and marker-assisted selection,which can be used to develop stress-tolerant cotton varieties.The review emphasizes the need for interdisciplinary research efforts and policy interventions to mitigate the adverse effects of climate change on cotton production.Furthermore,this paper presents advanced prospects,including genomic selection,gene editing,multi-omics integration,highthroughput phenotyping,genomic data sharing,climate-informed breeding,and phenomics-assisted genomic selection,for enhancing stress resilience in cotton.Those innovative approaches can assist cotton researchers and breeders in developing highly resilient cotton varieties capable of withstanding the challenges posed by climate change,ensuring the sustainable and prosperous future of cotton production.
基金Supported by the Strategic Priority Research Program(B)of Chinese Academy of Sciences(XDB0580000,XDB43010200)National Natural Science Foundation of China(62222514,62350073,U2341226,61991440)+6 种基金National Key Research and Development Program of China(2023YFA1406900)Shanghai Science and Technology Committee(23ZR1482000,22JC1402900,22ZR1472700)Natural Science Foundation of Zhejiang Province(LR22F050004)Shanghai Municipal Science and Technology Major Project(2019SHZDZX01)Youth Innovation Promotion Association(Y2021070)and International Partnership Program(112GJHZ2022002FN)of Chinese Academy of SciencesShanghai Human Resources and Social Security Bureau(2022670)China Postdoctoral Science Foundation(2023T160661,2022TQ0353 and 2022M713261).
文摘Metasurfaces provide a potent platform for the dynamic manipulation of electromagnetic waves.Coupled with phase-change materials,they facilitate the creation of versatile metadevices,showcasing various tunable functions based on the transition between amorphous and crystalline states.However,the inherent limitation in tunable states imposes constraints on the multiplexing channels of metadevices.Here,this paper introduces a novel approach-a multi-functional metadevice achieved through the two-level control of the encoding phasechange metaatoms.Utilizing the phase-change material Ge_(2)Sb_(2)Se_(4)Te1(GSST)and high refractive-index liquid diiodomethane(CH_(2)I_(2)),this paper showcases precise control over electromagnetic wave manipulation.The GSST state governs the tunable function,switching it ON and OFF,while the presence of liquid in the hole dictates the deflection angle when the tunable function is active.Importantly,our tunable coding metasurface exhibits robust performance across a broad wavelength spectrum.The incorporation of high refractive-index liquid extends the regulatory dimension of the metadevice,enabling dynamic switching of encoding bit levels.This two-level tunable metadevice,rooted in phase-change materials,presents a promising avenue for the dynamic control of functions.
基金This work was supported by the Natural Science Foundation of Heilongjiang Province(LH2022F049).
文摘Overlooking the issue of false alarm suppression in heterogeneous change detection leads to inferior detection per-formance.This paper proposes a method to handle false alarms in heterogeneous change detection.A lightweight network of two channels is bulit based on the combination of convolutional neural network(CNN)and graph convolutional network(GCN).CNNs learn feature difference maps of multitemporal images,and attention modules adaptively fuse CNN-based and graph-based features for different scales.GCNs with a new kernel filter adaptively distinguish between nodes with the same and those with different labels,generating change maps.Experimental evaluation on two datasets validates the efficacy of the pro-posed method in addressing false alarms.
