Background:In recent years,deep convolutional neural networks(CNNs)have achieved great successes in medical imaging.However,it is difficult to obtain accurate pathological information for clinical diagnosis and treatm...Background:In recent years,deep convolutional neural networks(CNNs)have achieved great successes in medical imaging.However,it is difficult to obtain accurate pathological information for clinical diagnosis and treatment by leveraging single-modality medical images.This study aims to provide an efficient multimodality whole heart segmentation method for the diagnosis of coronary heart disease.Methods:We propose SFAM-TransUnet for multimodality whole heart segmentation,a novel deep learning framework combining CNNs and transformers.Primarily,the method integrates CNNs and visual transformers(Vits)into a unified fusion framework.Specifically,the shallow feature fusion module is designed to connect MRI and CT images,thereby providing a powerful and efficient multimodality fusion backbone for semantic segmentation.Furthermore,we propose a fusion ViT(FViT)module including self-attention(SA)and adaptive mutual boost attention(Ada-MBA)to enhance contextual information within and across modalities.The Ada-MBA module assigns attention to semantic perception regions by calculating SA and cross-attention,which improves the ability to understand context from the different modalities.Extensive experiments are con-ducted on the clinical Multi-Modality Whole Heart Segmentation datasets.Results:We successfully improved the whole heart segmentation DSCs to 0.902(AA),0.920(LV-blood),0.863(LA-blood),and 0.837(LV-myo),the HDs to 9.886(AA),9.947(LV-blood),11.911(LA-blood),and 13.599(LV-myo),the PSNR values to 33.577(AA),30.091(LV-blood),32.055(LA-blood),and 29.837(LV-myo),SSMI values to 0.901(AA),0.818(LV-blood),0.765(LA-blood),and 0.743(LV-myo).This demonstrate SFAM-TransUnet outperforms various alternative methods.Conclusions:We propose SFAM-TransUnet,an efficient framework tailored for whole heart segmentation that combines CNNs and transformers.It provides a powerful multimodality fusion network to improve the performance of whole heart semantic segmentation.These results demonstrate the efficacy of SFAM-TransUnet in integrating relevant information between different modalities in multimodal tasks.展开更多
Similar to other heavy flavor mesons,the weak decays of D*_((s))mesons can provide a platform to verify the standard model,explore new physics,and understand the mechanisms of weak interactions.At present,the theoreti...Similar to other heavy flavor mesons,the weak decays of D*_((s))mesons can provide a platform to verify the standard model,explore new physics,and understand the mechanisms of weak interactions.At present,the theoretical and experimental studies on D*_((s))mesons are relatively limited.In addition to the dominant electromagnetic decays,the D*_((s)) weak decays should be feasible to explore the D*_((s)) mesons.In this study,we used the covariant lit-front quark model to study the form factors o the transitions D*_((s)) →π,K,η_(q,s),and then calculated the branching ratios of the semi-leptonic decays D*_((s))→Pe+ve and the non-leptonic decays D*_((s))→PP,PV with P =π,K,η^((,)),V=ρ,K*,Φ,and e=e,μ.The channels D*_(s)^(+)→ηe+ve and D*_(s)^(+)→ηρ^(+) possess the largest branching ratios,which can reach an order of 10^(-6) among these decays,and are most likely to be accessible in experiments at future high-luminosity colliders.Furthermore,we predict and discuss the longitudinal polarization fraction f_(L) and the forwardbackward asymmetry A_(FB) for the considered semi-leptonic D*_(s)decays.展开更多
Selenium is an essential trace element for human health,but its nutritional application is limited by uneven global distribution and poor bioavailability of conventional supplements.Selenium-rich peptides(SePPs),compl...Selenium is an essential trace element for human health,but its nutritional application is limited by uneven global distribution and poor bioavailability of conventional supplements.Selenium-rich peptides(SePPs),complexes of selenium and bioactive peptides,have demonstrated remarkable synergistic effects and bio-activities,becoming a high-value focus in nutrition and functional foods.Artificial intelligence(AI)technologies encompassing machine learning(ML),deep learning(DL),molecular docking(MD),and so on,are driving revolutionary advances in SePPs research.This review comprehensively summarizes the latest progress on AIfacilitated SePPs,focusing on their synthesis,characterization,biological activity,pharmacological mecha-nisms,food industrial applications,and development prospects.Major preparation approaches include extraction from natural sources,chemical synthesis,and biosynthesis.Advanced techniques enable accurate structural identification,stability evaluation,and bioavailability assessment of SePPs.SePPs indicate multiple bioactivities such as antioxidant,immunomodulatory,thyroid-regulating,and neuroprotective effects with potential health benefits against cancer and cardiovascular disease.AI has been increasingly integrated into biosynthesis,virtual screening,activity prediction,and mechanism exploration of SePPs,although its application is still in the early stage.Current research is abundant in antioxidant properties but limited in clinical translation and diseasespecific mechanisms,especially regarding thyroid and cardiovascular regulation.This review further discusses current challenges,future research directions,and regulatory considerations for the application of AI-facilitated SePPs.Overall,AI-assisted development and application of SePPs offer great promise for functional food inno-vation and the advancement of precision nutrition,providing a rational basis for the design and application of next-generation selenium supplements.展开更多
Biosensors based on organic electrochemical transistors(OECTs)have been a research highlight in recent years owing to their remarkable biocompatibility,low operating voltage,and substantial signal amplification capabi...Biosensors based on organic electrochemical transistors(OECTs)have been a research highlight in recent years owing to their remarkable biocompatibility,low operating voltage,and substantial signal amplification capability.Especially,as an emerging fundamental device for biosensing,OECTs show great potential for pH,ions,molecules,and biomarker sensing.This review highlights the research progress of biomolecule sensors based on OECTs,focusing on recent publications in the past 5 years.Specifically,OECT-based biomolecule sensors for small molecules(glucose,dopamine,lactate,etc.that act as signals or effectors),and macromolecules(DNA,RNA,proteins,etc.that are often used as markers in physiology and medicine),are summarized.Additionally,emerging technologies and materials used to enhance sensitivity,detection limits,and detection ranges are described comprehensively.Last,aspects of OECT-based biomolecule sensors that need further improvement are discussed along with future opportunities and challenges.展开更多
The semileptonic and nonleptonic decays of the b-flavor vector mesons B_(u,d,s)^(*) and B_(c)^(*) are investigated within the covariant light-front quark model(CLFQM).By calculating the form factors of the transitions...The semileptonic and nonleptonic decays of the b-flavor vector mesons B_(u,d,s)^(*) and B_(c)^(*) are investigated within the covariant light-front quark model(CLFQM).By calculating the form factors of the transitions B_(u,d,s)^(*)→P under the CLFQM,with P denoting a pseudoscalar meson,i.e.,π,K,η_(c)(1S,2S),D_((s)),B_((s)),we predict and discuss several physical observables,including the branching ratios,polarization fractions f_(L),f_(∥),and forward-backward asymmetries A_(FB).The total widths of the single-photon radiative decay channels for these b-flavor vector mesons are estimated using their partial widths.In these considered decays,one can find that the semileptonic decays B_(s)_(*0)→D_(s)^(-)l′+ν_(l′)and B_(c)^(*+)→B_(s)^(0)l′+ν_(l′),η_(c)l′+ν_(l′),with l′being e orτ,and the nonleptonic channels B*+c→B0sπ+,B0sρ+have the largest branching ratios,which can reach up to the 10^(-7) order,and are most likely to be accessible at the future high-luminosity LHCb and Belle-II experiments.展开更多
基金supported by the Henan Province Science and Technology Research Project(Grant 252102311276)Henan Province Key Scientific Research Projects of Universities(Grant 25B520002)+1 种基金the Fund of the Institute of Complexity Science from Henan University of Technology(Grant CSKFJJ-2025-13)the 2023 Research Nursery Engineering Project of Henan University of Chinese Medicine(Grant MP2023-10).
文摘Background:In recent years,deep convolutional neural networks(CNNs)have achieved great successes in medical imaging.However,it is difficult to obtain accurate pathological information for clinical diagnosis and treatment by leveraging single-modality medical images.This study aims to provide an efficient multimodality whole heart segmentation method for the diagnosis of coronary heart disease.Methods:We propose SFAM-TransUnet for multimodality whole heart segmentation,a novel deep learning framework combining CNNs and transformers.Primarily,the method integrates CNNs and visual transformers(Vits)into a unified fusion framework.Specifically,the shallow feature fusion module is designed to connect MRI and CT images,thereby providing a powerful and efficient multimodality fusion backbone for semantic segmentation.Furthermore,we propose a fusion ViT(FViT)module including self-attention(SA)and adaptive mutual boost attention(Ada-MBA)to enhance contextual information within and across modalities.The Ada-MBA module assigns attention to semantic perception regions by calculating SA and cross-attention,which improves the ability to understand context from the different modalities.Extensive experiments are con-ducted on the clinical Multi-Modality Whole Heart Segmentation datasets.Results:We successfully improved the whole heart segmentation DSCs to 0.902(AA),0.920(LV-blood),0.863(LA-blood),and 0.837(LV-myo),the HDs to 9.886(AA),9.947(LV-blood),11.911(LA-blood),and 13.599(LV-myo),the PSNR values to 33.577(AA),30.091(LV-blood),32.055(LA-blood),and 29.837(LV-myo),SSMI values to 0.901(AA),0.818(LV-blood),0.765(LA-blood),and 0.743(LV-myo).This demonstrate SFAM-TransUnet outperforms various alternative methods.Conclusions:We propose SFAM-TransUnet,an efficient framework tailored for whole heart segmentation that combines CNNs and transformers.It provides a powerful multimodality fusion network to improve the performance of whole heart semantic segmentation.These results demonstrate the efficacy of SFAM-TransUnet in integrating relevant information between different modalities in multimodal tasks.
基金the National Natural Science Foundation of China(11347030)the Program of Science and Technology Innovation Talents in Universities of Henan Province(14HASTIT037)the Natural Science Foundation of Henan Province(232300420116,252300421302)。
文摘Similar to other heavy flavor mesons,the weak decays of D*_((s))mesons can provide a platform to verify the standard model,explore new physics,and understand the mechanisms of weak interactions.At present,the theoretical and experimental studies on D*_((s))mesons are relatively limited.In addition to the dominant electromagnetic decays,the D*_((s)) weak decays should be feasible to explore the D*_((s)) mesons.In this study,we used the covariant lit-front quark model to study the form factors o the transitions D*_((s)) →π,K,η_(q,s),and then calculated the branching ratios of the semi-leptonic decays D*_((s))→Pe+ve and the non-leptonic decays D*_((s))→PP,PV with P =π,K,η^((,)),V=ρ,K*,Φ,and e=e,μ.The channels D*_(s)^(+)→ηe+ve and D*_(s)^(+)→ηρ^(+) possess the largest branching ratios,which can reach an order of 10^(-6) among these decays,and are most likely to be accessible in experiments at future high-luminosity colliders.Furthermore,we predict and discuss the longitudinal polarization fraction f_(L) and the forwardbackward asymmetry A_(FB) for the considered semi-leptonic D*_(s)decays.
基金supported by Key Research and Development Project of Henan Province(231111310700)Key Research and Development Project of Henan Province(241111310500)+2 种基金Henan Provincial Key Science&Technology Special Project(231100110300)supported by Henan Provincial Postdoctoral Research Project Funding(HN2025152)Cultivation Program for Young Backbone Teachers in Henan University of Technology and Student Innovation and Entrepreneurship Training Program(202510463007).
文摘Selenium is an essential trace element for human health,but its nutritional application is limited by uneven global distribution and poor bioavailability of conventional supplements.Selenium-rich peptides(SePPs),complexes of selenium and bioactive peptides,have demonstrated remarkable synergistic effects and bio-activities,becoming a high-value focus in nutrition and functional foods.Artificial intelligence(AI)technologies encompassing machine learning(ML),deep learning(DL),molecular docking(MD),and so on,are driving revolutionary advances in SePPs research.This review comprehensively summarizes the latest progress on AIfacilitated SePPs,focusing on their synthesis,characterization,biological activity,pharmacological mecha-nisms,food industrial applications,and development prospects.Major preparation approaches include extraction from natural sources,chemical synthesis,and biosynthesis.Advanced techniques enable accurate structural identification,stability evaluation,and bioavailability assessment of SePPs.SePPs indicate multiple bioactivities such as antioxidant,immunomodulatory,thyroid-regulating,and neuroprotective effects with potential health benefits against cancer and cardiovascular disease.AI has been increasingly integrated into biosynthesis,virtual screening,activity prediction,and mechanism exploration of SePPs,although its application is still in the early stage.Current research is abundant in antioxidant properties but limited in clinical translation and diseasespecific mechanisms,especially regarding thyroid and cardiovascular regulation.This review further discusses current challenges,future research directions,and regulatory considerations for the application of AI-facilitated SePPs.Overall,AI-assisted development and application of SePPs offer great promise for functional food inno-vation and the advancement of precision nutrition,providing a rational basis for the design and application of next-generation selenium supplements.
基金supported by the National Key R&D Program of China(2023YFC2411800)the National Natural Science Foundation of China(62303094,62273073)+5 种基金the National Key R&D Program of China(2024YFB3211600,2022YFE0134800)the Natural Science Foundation of Sichuan(2025ZNSFSC0515)the Key Research Project of the Henan Educational Committee of China(24A413001)the Aeronautical Science Foundation of China(20230024080002)Chengdu Science and Technology Bureau(2023-YF06-00028-HZ)the Fundamental Research Funds for the Central Universities(ZYGX2024XJ029).
文摘Biosensors based on organic electrochemical transistors(OECTs)have been a research highlight in recent years owing to their remarkable biocompatibility,low operating voltage,and substantial signal amplification capability.Especially,as an emerging fundamental device for biosensing,OECTs show great potential for pH,ions,molecules,and biomarker sensing.This review highlights the research progress of biomolecule sensors based on OECTs,focusing on recent publications in the past 5 years.Specifically,OECT-based biomolecule sensors for small molecules(glucose,dopamine,lactate,etc.that act as signals or effectors),and macromolecules(DNA,RNA,proteins,etc.that are often used as markers in physiology and medicine),are summarized.Additionally,emerging technologies and materials used to enhance sensitivity,detection limits,and detection ranges are described comprehensively.Last,aspects of OECT-based biomolecule sensors that need further improvement are discussed along with future opportunities and challenges.
基金partly supported by the National Natural Science Foundation of China(11347030)the Program for Science and Technology Innovation Talents in Universities of Henan Province(14HASTIT037)the Natural Science Foundation of Henan Province,China(232300420116)。
文摘The semileptonic and nonleptonic decays of the b-flavor vector mesons B_(u,d,s)^(*) and B_(c)^(*) are investigated within the covariant light-front quark model(CLFQM).By calculating the form factors of the transitions B_(u,d,s)^(*)→P under the CLFQM,with P denoting a pseudoscalar meson,i.e.,π,K,η_(c)(1S,2S),D_((s)),B_((s)),we predict and discuss several physical observables,including the branching ratios,polarization fractions f_(L),f_(∥),and forward-backward asymmetries A_(FB).The total widths of the single-photon radiative decay channels for these b-flavor vector mesons are estimated using their partial widths.In these considered decays,one can find that the semileptonic decays B_(s)_(*0)→D_(s)^(-)l′+ν_(l′)and B_(c)^(*+)→B_(s)^(0)l′+ν_(l′),η_(c)l′+ν_(l′),with l′being e orτ,and the nonleptonic channels B*+c→B0sπ+,B0sρ+have the largest branching ratios,which can reach up to the 10^(-7) order,and are most likely to be accessible at the future high-luminosity LHCb and Belle-II experiments.
