Different sedimentary zones in coral reefs lead to significant anisotropy in the pore structure of coral reef limestone(CRL),making it difficult to study mechanical behaviors.With X-ray computed tomography(CT),112 CRL...Different sedimentary zones in coral reefs lead to significant anisotropy in the pore structure of coral reef limestone(CRL),making it difficult to study mechanical behaviors.With X-ray computed tomography(CT),112 CRL samples were utilized for training the support vector machine(SVM)-,random forest(RF)-,and back propagation neural network(BPNN)-based models,respectively.Simultaneously,the machine learning model was embedded into genetic algorithm(GA)for parameter optimization to effectively predict uniaxial compressive strength(UCS)of CRL.Results indicate that the BPNN model with five hidden layers presents the best training effect in the data set of CRL.The SVM-based model shows a tendency to overfitting in the training set and poor generalization ability in the testing set.The RF-based model is suitable for training CRL samples with large data.Analysis of Pearson correlation coefficient matrix and the percentage increment method of performance metrics shows that the dry density,pore structure,and porosity of CRL are strongly correlated to UCS.However,the P-wave velocity is almost uncorrelated to the UCS,which is significantly distinct from the law for homogenous geomaterials.In addition,the pore tensor proposed in this paper can effectively reflect the pore structure of coral framework limestone(CFL)and coral boulder limestone(CBL),realizing the quantitative characterization of the heterogeneity and anisotropy of pore.The pore tensor provides a feasible idea to establish the relationship between pore structure and mechanical behavior of CRL.展开更多
Image quality in positron emission tomography(PET)is affected by random and scattered coincidences and reconstruction protocols.In this study,we investigated the effects of scattered and random coincidences from outsi...Image quality in positron emission tomography(PET)is affected by random and scattered coincidences and reconstruction protocols.In this study,we investigated the effects of scattered and random coincidences from outside the field of view(FOV)on PET image quality for different reconstruction protocols.Imaging was performed on the Discovery 690 PET/CT scanner,using experimental configurations including the NEMA phantom(a body phantom,with six spheres of different sizes)with a signal background ratio of 4:1.The NEMA phantom(phantom I)was scanned separately in a one-bed position.To simulate the effect of random and scatter coincidences from outside the FOV,six cylindrical phantoms with various diameters were added to the NEMA phantom(phantom II).The 18 emission datasets with mean intervals of 15 min were acquired(3 min/scan).The emission data were reconstructed using different techniques.The image quality parameters were evaluated by both phantoms.Variations in the signal-to-noise ratio(SNR)in a 28-mm(10-mm)sphere of phantom II were 37.9%(86.5%)for ordered-subset expectation maximization(OSEM-only),36.8%(81.5%)for point spread function(PSF),32.7%(80.7%)for time of flight(TOF),and 31.5%(77.8%)for OSEM+PSF+TOF,respectively,indicating that OSEM+PSF+TOF reconstruction had the lowest noise levels and lowest coefficient of variation(COV)values.Random and scatter coincidences from outside the FOV induced lower SNR,lower contrast,and higher COV values,indicating image deterioration and significantly impacting smaller sphere sizes.Amongst reconstruction protocols,OSEM+PSF+TOF and OSEM+PSF showed higher contrast values for sphere sizes of 22,28,and 37 mm and higher contrast recovery coefficient values for smaller sphere sizes of 10 and 13 mm.展开更多
目的探讨基于冠状动脉CT血管成像(CCTA)的人工智能(AI)诊断系统及CT无创血流储备分数(CT-FFR)在评估高海拔地区冠状动脉临界病变结构及功能学中的应用价值。方法前瞻性收集2022年1月~2023年10月青海大学附属医院冠心病临界病变患者164例...目的探讨基于冠状动脉CT血管成像(CCTA)的人工智能(AI)诊断系统及CT无创血流储备分数(CT-FFR)在评估高海拔地区冠状动脉临界病变结构及功能学中的应用价值。方法前瞻性收集2022年1月~2023年10月青海大学附属医院冠心病临界病变患者164例,按居住地海拔进行分组,其中2000~3000m为A组(n=83),3000m以上为B组(n=81),再将两组患者按冠脉狭窄程度细分为50%~60%亚组(n=84)和61%~70%亚组(n=80)。将患者冠状动脉CT血管成像数据导入AI辅助诊断及CT-FFR测量系统,以冠脉造影及冠脉传统血流储备分数(FFR)为金标准,分别评价AI及CT-FFR在高海拔地区冠脉临界病变诊断中的应用。结果以FFR为金标准,CT-FFR与FFR的一致性为83.75%。B组钙化斑块、易损斑块高于A组(P=0.037、0.020);B组冠状动脉多支病变、61%~70%狭窄程度发生率均高于A组(P<0.05);A组、B组在61%~70%亚组钙化斑块、易损斑块发生率均高于50%~60%亚组(P<0.05)。B组CT-FFR值低于A组(0.76±0.04 vs 0.88±0.05,P<0.01);A、B两组在61%~70%亚组CT-FFR值≤0.80、<0.70的发生率高于50%~60%亚组(P<0.05)。结论AI诊断系统及CT-FFR对评估高海拔地区冠状动脉临界病变的结构特征及血流动力学改变的结果与冠脉造影、FFR一致性高,具有较高的诊断敏感度和特异度。展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.41877267 and 41877260)the Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA13010201).
文摘Different sedimentary zones in coral reefs lead to significant anisotropy in the pore structure of coral reef limestone(CRL),making it difficult to study mechanical behaviors.With X-ray computed tomography(CT),112 CRL samples were utilized for training the support vector machine(SVM)-,random forest(RF)-,and back propagation neural network(BPNN)-based models,respectively.Simultaneously,the machine learning model was embedded into genetic algorithm(GA)for parameter optimization to effectively predict uniaxial compressive strength(UCS)of CRL.Results indicate that the BPNN model with five hidden layers presents the best training effect in the data set of CRL.The SVM-based model shows a tendency to overfitting in the training set and poor generalization ability in the testing set.The RF-based model is suitable for training CRL samples with large data.Analysis of Pearson correlation coefficient matrix and the percentage increment method of performance metrics shows that the dry density,pore structure,and porosity of CRL are strongly correlated to UCS.However,the P-wave velocity is almost uncorrelated to the UCS,which is significantly distinct from the law for homogenous geomaterials.In addition,the pore tensor proposed in this paper can effectively reflect the pore structure of coral framework limestone(CFL)and coral boulder limestone(CBL),realizing the quantitative characterization of the heterogeneity and anisotropy of pore.The pore tensor provides a feasible idea to establish the relationship between pore structure and mechanical behavior of CRL.
基金supported by the Tehran University of Medical Sciences under Grant No.36291PET/CT and Cyclotron Center of Masih Daneshvari Hospital at Shahid Beheshti University of Medical Sciences。
文摘Image quality in positron emission tomography(PET)is affected by random and scattered coincidences and reconstruction protocols.In this study,we investigated the effects of scattered and random coincidences from outside the field of view(FOV)on PET image quality for different reconstruction protocols.Imaging was performed on the Discovery 690 PET/CT scanner,using experimental configurations including the NEMA phantom(a body phantom,with six spheres of different sizes)with a signal background ratio of 4:1.The NEMA phantom(phantom I)was scanned separately in a one-bed position.To simulate the effect of random and scatter coincidences from outside the FOV,six cylindrical phantoms with various diameters were added to the NEMA phantom(phantom II).The 18 emission datasets with mean intervals of 15 min were acquired(3 min/scan).The emission data were reconstructed using different techniques.The image quality parameters were evaluated by both phantoms.Variations in the signal-to-noise ratio(SNR)in a 28-mm(10-mm)sphere of phantom II were 37.9%(86.5%)for ordered-subset expectation maximization(OSEM-only),36.8%(81.5%)for point spread function(PSF),32.7%(80.7%)for time of flight(TOF),and 31.5%(77.8%)for OSEM+PSF+TOF,respectively,indicating that OSEM+PSF+TOF reconstruction had the lowest noise levels and lowest coefficient of variation(COV)values.Random and scatter coincidences from outside the FOV induced lower SNR,lower contrast,and higher COV values,indicating image deterioration and significantly impacting smaller sphere sizes.Amongst reconstruction protocols,OSEM+PSF+TOF and OSEM+PSF showed higher contrast values for sphere sizes of 22,28,and 37 mm and higher contrast recovery coefficient values for smaller sphere sizes of 10 and 13 mm.
文摘目的探讨基于冠状动脉CT血管成像(CCTA)的人工智能(AI)诊断系统及CT无创血流储备分数(CT-FFR)在评估高海拔地区冠状动脉临界病变结构及功能学中的应用价值。方法前瞻性收集2022年1月~2023年10月青海大学附属医院冠心病临界病变患者164例,按居住地海拔进行分组,其中2000~3000m为A组(n=83),3000m以上为B组(n=81),再将两组患者按冠脉狭窄程度细分为50%~60%亚组(n=84)和61%~70%亚组(n=80)。将患者冠状动脉CT血管成像数据导入AI辅助诊断及CT-FFR测量系统,以冠脉造影及冠脉传统血流储备分数(FFR)为金标准,分别评价AI及CT-FFR在高海拔地区冠脉临界病变诊断中的应用。结果以FFR为金标准,CT-FFR与FFR的一致性为83.75%。B组钙化斑块、易损斑块高于A组(P=0.037、0.020);B组冠状动脉多支病变、61%~70%狭窄程度发生率均高于A组(P<0.05);A组、B组在61%~70%亚组钙化斑块、易损斑块发生率均高于50%~60%亚组(P<0.05)。B组CT-FFR值低于A组(0.76±0.04 vs 0.88±0.05,P<0.01);A、B两组在61%~70%亚组CT-FFR值≤0.80、<0.70的发生率高于50%~60%亚组(P<0.05)。结论AI诊断系统及CT-FFR对评估高海拔地区冠状动脉临界病变的结构特征及血流动力学改变的结果与冠脉造影、FFR一致性高,具有较高的诊断敏感度和特异度。
