目的:分析人工智能(AI)在辅助肺结节诊断方面的研究现状、热点及问题,以探究我国在该领域的优势与不足,厘清后续发展思路。方法:以Web of Science核心合集数据库作为数据来源,纳入2003年1月至2023年1月AI辅助肺结节诊断相关文献1 468篇...目的:分析人工智能(AI)在辅助肺结节诊断方面的研究现状、热点及问题,以探究我国在该领域的优势与不足,厘清后续发展思路。方法:以Web of Science核心合集数据库作为数据来源,纳入2003年1月至2023年1月AI辅助肺结节诊断相关文献1 468篇,利用CiteSpace绘制可视化知识图谱,依次分析合作网络、共被引网络和关键词共现。结果:AI辅助肺结节诊断研究存在核心国家、机构;国内已经形成稳定的研究与合作团队,但跨国家的合作明显不足;美国在研究中处于领先、核心地位,中国是后起之秀,韩国是近年的先锋;AI算法导致研究热点的大幅度转移,目前研究重点是利用CT断层扫描和深度学习算法辅助判断肺结节和低密度磨玻璃结节,进行诊断和病因分析。结论:AI辅助肺结节诊断的研究近年飞速发展,需增强各国研究团队的合作。此领域受算法性能影响较大,后继应该继续关注AI等用于计算机辅助诊断的新算法性能的提升。展开更多
Data assimilation(DA)and uncertainty quantification(UQ)are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal dynamics.Typical applications span from computational fluid ...Data assimilation(DA)and uncertainty quantification(UQ)are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal dynamics.Typical applications span from computational fluid dynamics(CFD)to geoscience and climate systems.Recently,much effort has been given in combining DA,UQ and machine learning(ML)techniques.These research efforts seek to address some critical challenges in high-dimensional dynamical systems,including but not limited to dynamical system identification,reduced order surrogate modelling,error covariance specification and model error correction.A large number of developed techniques and methodologies exhibit a broad applicability across numerous domains,resulting in the necessity for a comprehensive guide.This paper provides the first overview of state-of-the-art researches in this interdisciplinary field,covering a wide range of applications.This review is aimed at ML scientists who attempt to apply DA and UQ techniques to improve the accuracy and the interpretability of their models,but also at DA and UQ experts who intend to integrate cutting-edge ML approaches to their systems.Therefore,this article has a special focus on how ML methods can overcome the existing limits of DA and UQ,and vice versa.Some exciting perspectives of this rapidly developing research field are also discussed.Index Terms-Data assimilation(DA),deep learning,machine learning(ML),reduced-order-modelling,uncertainty quantification(UQ).展开更多
Brain midline delineation can facilitate the clinical evaluation of brain midline shift,which has a pivotal role in the diagnosis and prognosis of various brain pathology.However,there are still challenges for brain m...Brain midline delineation can facilitate the clinical evaluation of brain midline shift,which has a pivotal role in the diagnosis and prognosis of various brain pathology.However,there are still challenges for brain midline delineation:1)the largely deformed midline is hard to localize if mixed with severe cerebral hemorrhage;2)the predicted midlines of recent methods are not smooth and continuous which violates the structural priority.To overcome these challenges,we propose an anisotropic three dimensional(3D)network with context-aware refinement(A3D-CAR)for brain midline modeling.The proposed network fuses 3D context from different two dimensional(2D)slices through asymmetric context fusion.To exploit the elongated structure of the midline,an anisotropic block is designed to balance the difference between the adjacent pixels in the horizontal and vertical directions.For maintaining the structural priority of a brain midline,we present a novel 3D connectivity regular loss(3D CRL)to penalize the disconnectivity between nearby coordinates.Extensive experiments on the CQ dataset and one in-house dataset show that the proposed method outperforms three state-of-the-art methods on four evaluation metrics without excessive computational burden.展开更多
Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution.However,obtained information of these con-volutional neural networks cannot completely exp...Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution.However,obtained information of these con-volutional neural networks cannot completely express predicted high‐quality images for complex scenes.A dynamic network for image super‐resolution(DSRNet)is presented,which contains a residual enhancement block,wide enhancement block,feature refine-ment block and construction block.The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐resolution.To enhance robustness of obtained super‐resolution model for complex scenes,a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying scenes.To prevent interference of components in a wide enhancement block,a refine-ment block utilises a stacked architecture to accurately learn obtained features.Also,a residual learning operation is embedded in the refinement block to prevent long‐term dependency problem.Finally,a construction block is responsible for reconstructing high‐quality images.Designed heterogeneous architecture can not only facilitate richer structural information,but also be lightweight,which is suitable for mobile digital devices.Experimental results show that our method is more competitive in terms of performance,recovering time of image super‐resolution and complexity.The code of DSRNet can be obtained at https://github.com/hellloxiaotian/DSRNet.展开更多
Reviewing the empirical and theoretical parameter relationships between various parameters is a good way to understand more about contact binary systems.In this investigation,two-dimensional(2D)relationships for P–MV...Reviewing the empirical and theoretical parameter relationships between various parameters is a good way to understand more about contact binary systems.In this investigation,two-dimensional(2D)relationships for P–MV(system),P–L1,2,M1,2–L1,2,and q–Lratiowere revisited.The sample used is related to 118 contact binary systems with an orbital period shorter than 0.6 days whose absolute parameters were estimated based on the Gaia Data Release 3 parallax.We reviewed previous studies on 2D relationships and updated six parameter relationships.Therefore,Markov chain Monte Carlo and Machine Learning methods were used,and the outcomes were compared.We selected 22 contact binary systems from eight previous studies for comparison,which had light curve solutions using spectroscopic data.The results show that the systems are in good agreement with the results of this study.展开更多
The first photometric light curve investigation of the NSVS 8294044,V1023 Her,and V1397 Her binary systems is presented.We used ground-based observations for the NSVS 8294044 system and Transiting Exoplanet Survey Sat...The first photometric light curve investigation of the NSVS 8294044,V1023 Her,and V1397 Her binary systems is presented.We used ground-based observations for the NSVS 8294044 system and Transiting Exoplanet Survey Satellite data for V1023 Her and V1397 Her.The primary and secondary times of minima were extracted from al the data,and,by collecting the literature,a new ephemeris was computed for each system.Linear fits for the O-C diagrams were conducted using the Markov Chain Monte Carlo (MCMC) method.Light curve solutions were performed using the PHysics Of Eclipsing BinariEs Python code and the MCMC approach.The systems were found to be contact binary stars based on the fillout factor and mass ratio.V1023 Her showed the O’Connell effect and a cold starspot on the secondary component was required for the light curve solution.The absolute parameters of the system were estimated based on an empirical relationship between orbital period and mass.We presented a new T–M equation based on a sample of 428 contact binary systems and found that our three target systems were in good agreement with the fit.The positions of the systems were also depicted on the M–L,M–R,q–L_(ratio),and M_(tot)–J_(0)diagrams in the logarithmic scales.展开更多
We conducted the first light curve study of the binary star EL Tuc within the Binary Systems of South and North project's framework.The photometric observations were made using standard multiband BVR_cI_c filters ...We conducted the first light curve study of the binary star EL Tuc within the Binary Systems of South and North project's framework.The photometric observations were made using standard multiband BVR_cI_c filters at an observatory in Argentina.We presented a new ephemeris for EL Tuc and a linear fit to the O–C diagram,utilizing our extracted times of minima and additional literature.We employed the PHysics Of Eclipsing BinariEs Python code and the Markov chain Monte Carlo approach for the system's light curve analysis.The target system's light curve solution required a cold starspot on the hotter component.We conclude that EL Tuc is a total contact binary system with a low mass ratio of q=0.172±0.002,an orbital inclination of i=83°.74±0°.40,and a fillout factor of f=53.7%±1.6%.We used the P-a relationship and the Gaia Data Release 3 parallax method to determine the absolute parameters of EL Tuc to compare the precision of our results.This system was classified as W-type based on the mass and effective temperature of the companion stars.The positions of the systems were depicted on the M-L,M-R,T-M,and q-Lratiodiagrams.The relationship between the spectroscopic and photometric mass ratios of binaries was discussed.展开更多
The Ki67 index (KI) is a standard clinical marker for tumor proliferation;however, its application is hindered by intratumoral heterogeneity. In this study, we used digital image analysis to comprehensively analyze Ki...The Ki67 index (KI) is a standard clinical marker for tumor proliferation;however, its application is hindered by intratumoral heterogeneity. In this study, we used digital image analysis to comprehensively analyze Ki67 heterogeneity and distribution patterns in breast carcinoma. Using Smart Pathology software, we digitized and analyzed 42 excised breast carcinoma Ki67 slides. Boxplots, histograms, and heat maps were generated to illustrate the KI distribution. We found that 30% of cases (13/42) exhibited discrepancies between global and hotspot KI when using a 14% KI threshold for classification. Patients with higher global or hotspot KI values displayed greater heterogenicity. Ki67 distribution patterns were categorized as randomly distributed (52%, 22/42), peripheral (43%, 18/42), and centered (5%, 2/42). Our sampling simulator indicated analyzing more than 10 high-power fields was typically required to accurately estimate global KI, with sampling size being correlated with heterogeneity. In conclusion, using digital image analysis in whole-slide images allows for comprehensive Ki67 profile assessment, shedding light on heterogeneity and distribution patterns. This spatial information can facilitate KI surveys of breast cancer and other malignancies.展开更多
The light curve analyses and orbital period variations for two contact binary stars,LS Del and V997 Cyg,are presented in this work which was conducted in the frame of the Binary Systems of South and North project Grou...The light curve analyses and orbital period variations for two contact binary stars,LS Del and V997 Cyg,are presented in this work which was conducted in the frame of the Binary Systems of South and North project Ground-based photometric observations were performed at two observatories in France.We used the Transiting Exoplanet Survey Satellite(TESS)data for extracting times of minima and light curve analysis of the targe systems.The O-C diagram for both systems displays a parabolic trend.LS Del and V997 Cyg’s orbital periods are increasing at rates of dP/dt=7.20×10^(-08)days yr^(-1)and dP/dt=2.54×10^(-08)days yr^(-1),respectively Therefore,it can be concluded that mass is being transferred from the less massive star to the more massive component with a rate of dM/dt=-1.96×10^(-7)M_(⊙)yr^(-1)for the LS Del system,and dM/dt=-3.83×10^(-7)M_(⊙)yr-1for V997 Cyg.The parameters of a third possible object in the system are also considered.The PHysics Of Eclipsing BinariEs Python code was used to analyze the light curves.The light curve solutions needed a cold starspot due to the asymmetry in the LS Del system’s light curve maxima.The mass ratio fill-out factor,and star temperature all indicate that both systems are contact binary types in this investigation.Two methods were applied to estimate the absolute parameters of the systems:one method relied on the parallax of Gaia DR3,and the other used a P-M relationship.The positions of the systems are also depicted on the M-L,M-R q-L_(ratio),and logM_(tot)-logJ_(0)diagrams.We recommend that further observations and investigations be done on the existence of a fourth body in this system.展开更多
Blockchain is a technology that uses community validation to synchronize the content of ledgers replicated by multiple users.Although Blockchain derives its origins from technologies introduced decades ago,recently it...Blockchain is a technology that uses community validation to synchronize the content of ledgers replicated by multiple users.Although Blockchain derives its origins from technologies introduced decades ago,recently it has received an astonishing amount of attention in both academic and industry due to its charac-teristics of decentralization,point-to-point transmission,transparency,traceability,non-tampering,and data security.Both researchers and practitioners have recognized that Blockchain can be used to solve complex technical or socio-economic problems.展开更多
Because some efficient motion estimation algorithms need considering global camera motion such as zooming, panning, rotating and tilting, a frequency domain algorithm is proposed to solve this problem. Utilizing the m...Because some efficient motion estimation algorithms need considering global camera motion such as zooming, panning, rotating and tilting, a frequency domain algorithm is proposed to solve this problem. Utilizing the magnitude relationship and phase relationship between successive images’ spectra, the authors can solve the full parameter camera motion robustly with acceptable computational complexity.展开更多
文摘目的:分析人工智能(AI)在辅助肺结节诊断方面的研究现状、热点及问题,以探究我国在该领域的优势与不足,厘清后续发展思路。方法:以Web of Science核心合集数据库作为数据来源,纳入2003年1月至2023年1月AI辅助肺结节诊断相关文献1 468篇,利用CiteSpace绘制可视化知识图谱,依次分析合作网络、共被引网络和关键词共现。结果:AI辅助肺结节诊断研究存在核心国家、机构;国内已经形成稳定的研究与合作团队,但跨国家的合作明显不足;美国在研究中处于领先、核心地位,中国是后起之秀,韩国是近年的先锋;AI算法导致研究热点的大幅度转移,目前研究重点是利用CT断层扫描和深度学习算法辅助判断肺结节和低密度磨玻璃结节,进行诊断和病因分析。结论:AI辅助肺结节诊断的研究近年飞速发展,需增强各国研究团队的合作。此领域受算法性能影响较大,后继应该继续关注AI等用于计算机辅助诊断的新算法性能的提升。
基金the support of the Leverhulme Centre for Wildfires,Environment and Society through the Leverhulme Trust(RC-2018-023)Sibo Cheng,César Quilodran-Casas,and Rossella Arcucci acknowledge the support of the PREMIERE project(EP/T000414/1)+5 种基金the support of EPSRC grant:PURIFY(EP/V000756/1)the Fundamental Research Funds for the Central Universitiesthe support of the SASIP project(353)funded by Schmidt Futures–a philanthropic initiative that seeks to improve societal outcomes through the development of emerging science and technologiesDFG for the Heisenberg Programm Award(JA 1077/4-1)the National Natural Science Foundation of China(61976120)the Natural Science Key Foundat ion of Jiangsu Education Department(21KJA510004)。
文摘Data assimilation(DA)and uncertainty quantification(UQ)are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal dynamics.Typical applications span from computational fluid dynamics(CFD)to geoscience and climate systems.Recently,much effort has been given in combining DA,UQ and machine learning(ML)techniques.These research efforts seek to address some critical challenges in high-dimensional dynamical systems,including but not limited to dynamical system identification,reduced order surrogate modelling,error covariance specification and model error correction.A large number of developed techniques and methodologies exhibit a broad applicability across numerous domains,resulting in the necessity for a comprehensive guide.This paper provides the first overview of state-of-the-art researches in this interdisciplinary field,covering a wide range of applications.This review is aimed at ML scientists who attempt to apply DA and UQ techniques to improve the accuracy and the interpretability of their models,but also at DA and UQ experts who intend to integrate cutting-edge ML approaches to their systems.Therefore,this article has a special focus on how ML methods can overcome the existing limits of DA and UQ,and vice versa.Some exciting perspectives of this rapidly developing research field are also discussed.Index Terms-Data assimilation(DA),deep learning,machine learning(ML),reduced-order-modelling,uncertainty quantification(UQ).
基金supported by National Natural Science Foundation of China(NSFC)(Nos.62106022,62225601,and U19B2036)Key Program of Beijing Municipal Natural Science Foundation(No.7191003)Beijing Natural Science Foundation Project(No.Z200002).
文摘Brain midline delineation can facilitate the clinical evaluation of brain midline shift,which has a pivotal role in the diagnosis and prognosis of various brain pathology.However,there are still challenges for brain midline delineation:1)the largely deformed midline is hard to localize if mixed with severe cerebral hemorrhage;2)the predicted midlines of recent methods are not smooth and continuous which violates the structural priority.To overcome these challenges,we propose an anisotropic three dimensional(3D)network with context-aware refinement(A3D-CAR)for brain midline modeling.The proposed network fuses 3D context from different two dimensional(2D)slices through asymmetric context fusion.To exploit the elongated structure of the midline,an anisotropic block is designed to balance the difference between the adjacent pixels in the horizontal and vertical directions.For maintaining the structural priority of a brain midline,we present a novel 3D connectivity regular loss(3D CRL)to penalize the disconnectivity between nearby coordinates.Extensive experiments on the CQ dataset and one in-house dataset show that the proposed method outperforms three state-of-the-art methods on four evaluation metrics without excessive computational burden.
基金the TCL Science and Technology Innovation Fundthe Youth Science and Technology Talent Promotion Project of Jiangsu Association for Science and Technology,Grant/Award Number:JSTJ‐2023‐017+4 种基金Shenzhen Municipal Science and Technology Innovation Council,Grant/Award Number:JSGG20220831105002004National Natural Science Foundation of China,Grant/Award Number:62201468Postdoctoral Research Foundation of China,Grant/Award Number:2022M722599the Fundamental Research Funds for the Central Universities,Grant/Award Number:D5000210966the Guangdong Basic and Applied Basic Research Foundation,Grant/Award Number:2021A1515110079。
文摘Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution.However,obtained information of these con-volutional neural networks cannot completely express predicted high‐quality images for complex scenes.A dynamic network for image super‐resolution(DSRNet)is presented,which contains a residual enhancement block,wide enhancement block,feature refine-ment block and construction block.The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐resolution.To enhance robustness of obtained super‐resolution model for complex scenes,a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying scenes.To prevent interference of components in a wide enhancement block,a refine-ment block utilises a stacked architecture to accurately learn obtained features.Also,a residual learning operation is embedded in the refinement block to prevent long‐term dependency problem.Finally,a construction block is responsible for reconstructing high‐quality images.Designed heterogeneous architecture can not only facilitate richer structural information,but also be lightweight,which is suitable for mobile digital devices.Experimental results show that our method is more competitive in terms of performance,recovering time of image super‐resolution and complexity.The code of DSRNet can be obtained at https://github.com/hellloxiaotian/DSRNet.
基金The Binary Systems of South and North(BSN)project(https://bsnp.info/)。
文摘Reviewing the empirical and theoretical parameter relationships between various parameters is a good way to understand more about contact binary systems.In this investigation,two-dimensional(2D)relationships for P–MV(system),P–L1,2,M1,2–L1,2,and q–Lratiowere revisited.The sample used is related to 118 contact binary systems with an orbital period shorter than 0.6 days whose absolute parameters were estimated based on the Gaia Data Release 3 parallax.We reviewed previous studies on 2D relationships and updated six parameter relationships.Therefore,Markov chain Monte Carlo and Machine Learning methods were used,and the outcomes were compared.We selected 22 contact binary systems from eight previous studies for comparison,which had light curve solutions using spectroscopic data.The results show that the systems are in good agreement with the results of this study.
文摘The first photometric light curve investigation of the NSVS 8294044,V1023 Her,and V1397 Her binary systems is presented.We used ground-based observations for the NSVS 8294044 system and Transiting Exoplanet Survey Satellite data for V1023 Her and V1397 Her.The primary and secondary times of minima were extracted from al the data,and,by collecting the literature,a new ephemeris was computed for each system.Linear fits for the O-C diagrams were conducted using the Markov Chain Monte Carlo (MCMC) method.Light curve solutions were performed using the PHysics Of Eclipsing BinariEs Python code and the MCMC approach.The systems were found to be contact binary stars based on the fillout factor and mass ratio.V1023 Her showed the O’Connell effect and a cold starspot on the secondary component was required for the light curve solution.The absolute parameters of the system were estimated based on an empirical relationship between orbital period and mass.We presented a new T–M equation based on a sample of 428 contact binary systems and found that our three target systems were in good agreement with the fit.The positions of the systems were also depicted on the M–L,M–R,q–L_(ratio),and M_(tot)–J_(0)diagrams in the logarithmic scales.
文摘We conducted the first light curve study of the binary star EL Tuc within the Binary Systems of South and North project's framework.The photometric observations were made using standard multiband BVR_cI_c filters at an observatory in Argentina.We presented a new ephemeris for EL Tuc and a linear fit to the O–C diagram,utilizing our extracted times of minima and additional literature.We employed the PHysics Of Eclipsing BinariEs Python code and the Markov chain Monte Carlo approach for the system's light curve analysis.The target system's light curve solution required a cold starspot on the hotter component.We conclude that EL Tuc is a total contact binary system with a low mass ratio of q=0.172±0.002,an orbital inclination of i=83°.74±0°.40,and a fillout factor of f=53.7%±1.6%.We used the P-a relationship and the Gaia Data Release 3 parallax method to determine the absolute parameters of EL Tuc to compare the precision of our results.This system was classified as W-type based on the mass and effective temperature of the companion stars.The positions of the systems were depicted on the M-L,M-R,T-M,and q-Lratiodiagrams.The relationship between the spectroscopic and photometric mass ratios of binaries was discussed.
文摘The Ki67 index (KI) is a standard clinical marker for tumor proliferation;however, its application is hindered by intratumoral heterogeneity. In this study, we used digital image analysis to comprehensively analyze Ki67 heterogeneity and distribution patterns in breast carcinoma. Using Smart Pathology software, we digitized and analyzed 42 excised breast carcinoma Ki67 slides. Boxplots, histograms, and heat maps were generated to illustrate the KI distribution. We found that 30% of cases (13/42) exhibited discrepancies between global and hotspot KI when using a 14% KI threshold for classification. Patients with higher global or hotspot KI values displayed greater heterogenicity. Ki67 distribution patterns were categorized as randomly distributed (52%, 22/42), peripheral (43%, 18/42), and centered (5%, 2/42). Our sampling simulator indicated analyzing more than 10 high-power fields was typically required to accurately estimate global KI, with sampling size being correlated with heterogeneity. In conclusion, using digital image analysis in whole-slide images allows for comprehensive Ki67 profile assessment, shedding light on heterogeneity and distribution patterns. This spatial information can facilitate KI surveys of breast cancer and other malignancies.
基金project was supported by the Scientific Research Projects Coordination Unit of Erciyes University(project number FBA-2022-11737)the TESS mission is provided by the NASA Explorer Program。
文摘The light curve analyses and orbital period variations for two contact binary stars,LS Del and V997 Cyg,are presented in this work which was conducted in the frame of the Binary Systems of South and North project Ground-based photometric observations were performed at two observatories in France.We used the Transiting Exoplanet Survey Satellite(TESS)data for extracting times of minima and light curve analysis of the targe systems.The O-C diagram for both systems displays a parabolic trend.LS Del and V997 Cyg’s orbital periods are increasing at rates of dP/dt=7.20×10^(-08)days yr^(-1)and dP/dt=2.54×10^(-08)days yr^(-1),respectively Therefore,it can be concluded that mass is being transferred from the less massive star to the more massive component with a rate of dM/dt=-1.96×10^(-7)M_(⊙)yr^(-1)for the LS Del system,and dM/dt=-3.83×10^(-7)M_(⊙)yr-1for V997 Cyg.The parameters of a third possible object in the system are also considered.The PHysics Of Eclipsing BinariEs Python code was used to analyze the light curves.The light curve solutions needed a cold starspot due to the asymmetry in the LS Del system’s light curve maxima.The mass ratio fill-out factor,and star temperature all indicate that both systems are contact binary types in this investigation.Two methods were applied to estimate the absolute parameters of the systems:one method relied on the parallax of Gaia DR3,and the other used a P-M relationship.The positions of the systems are also depicted on the M-L,M-R q-L_(ratio),and logM_(tot)-logJ_(0)diagrams.We recommend that further observations and investigations be done on the existence of a fourth body in this system.
文摘Blockchain is a technology that uses community validation to synchronize the content of ledgers replicated by multiple users.Although Blockchain derives its origins from technologies introduced decades ago,recently it has received an astonishing amount of attention in both academic and industry due to its charac-teristics of decentralization,point-to-point transmission,transparency,traceability,non-tampering,and data security.Both researchers and practitioners have recognized that Blockchain can be used to solve complex technical or socio-economic problems.
文摘Because some efficient motion estimation algorithms need considering global camera motion such as zooming, panning, rotating and tilting, a frequency domain algorithm is proposed to solve this problem. Utilizing the magnitude relationship and phase relationship between successive images’ spectra, the authors can solve the full parameter camera motion robustly with acceptable computational complexity.
