为解决GVF-Snake(gradient vector flow snake)条纹探测相位解缠时,内部条纹线探测偏离条纹边界的问题,提出了一种融合GVF-Snake条纹探测与马尔科夫随机场(Markov random field, MRF)图切法相位解缠方法。通过判断出条纹探测线不是真实...为解决GVF-Snake(gradient vector flow snake)条纹探测相位解缠时,内部条纹线探测偏离条纹边界的问题,提出了一种融合GVF-Snake条纹探测与马尔科夫随机场(Markov random field, MRF)图切法相位解缠方法。通过判断出条纹探测线不是真实条纹边界的情况,对该条纹探测线上一步探测条纹的内部块用MRF图切法进行分割解缠,按照相应解缠准则将两种解缠结果进行融合,形成含有边界跳跃点的粗解缠结果,并用高通滤波插值法消除粗解缠结果的边界孤立点的方法研究了矿区梯度较大地区的相位解缠。结果表明:以巨野矿区某工作面为实验区,用两景sentinel-1A的单视复数图像进行两轨法干涉处理的真实相位来验证算法的有效性。在面分析上,以自适应局部平滑相位评估(phase estimation using adaptive regulation based on local smoothing, PEARLS)为评价标准,将本文方法与最小费用流等5种相位解缠算法进行比较。对比结果显示,本文方法的平方根误差、平均绝对误差分别是±0.079 1、±0.009 0、±2.317 3 rad。在线分析上,对只含有变形相位的绝对相位,提取各解缠绝对相位工作面走向线、倾向线的变形。以实际水准观测值为标准,本文方法的平方根误差、平均绝对误差、绝对值最大误差分别是±0.177 48、±0.141 07、±0.405 29 cm。面分析中以PEARLS相位重构为基准,可见本文方法要优于其他常规的解缠方法;同理,线分析中以水准数据作为依据其各项指标亦为最优。展开更多
The paper covers the electrical capacitance tomography(ECT) data analysis on shear zones formed during silo discharging process.This is due to the ECT aptitude for detection of slight changes of material concentration...The paper covers the electrical capacitance tomography(ECT) data analysis on shear zones formed during silo discharging process.This is due to the ECT aptitude for detection of slight changes of material concentration.On the basis of ECT visualisations,wall-adjacent shear zone profiles are analysed for different wall roughness parameters.The analysis on changes of material concentration,based on ECT images,enables the calculation for the characteristic parameters of shear zones-size and material concentration inside the shear zone in a dynamic process of silo discharging.In order to verify the methodology a series of experiments on gravitational flow of bulk solids under various conditions were conducted with different initial granular material packing densities and silo wall roughness.The investigation shows that the increase in container wall roughness is an effective method for reducing the dynamic effects during the material discharging,since these effects are resulted from the resonance between hopper construction and trembling material.Such effects will damage industrial equipment in practical applications and need further investigation.展开更多
Objective To develope a deep learning algorithm for pathological classification of chronic gastritis and assess its performance using whole-slide images(WSIs).Methods We retrospectively collected 1,250 gastric biopsy ...Objective To develope a deep learning algorithm for pathological classification of chronic gastritis and assess its performance using whole-slide images(WSIs).Methods We retrospectively collected 1,250 gastric biopsy specimens(1,128 gastritis,122 normal mucosa)from PLA General Hospital.The deep learning algorithm based on DeepLab v3(ResNet-50)architecture was trained and validated using 1,008 WSIs and 100 WSIs,respectively.The diagnostic performance of the algorithm was tested on an independent test set of 142 WSIs,with the pathologists’consensus diagnosis as the gold standard.Results The receiver operating characteristic(ROC)curves were generated for chronic superficial gastritis(CSuG),chronic active gastritis(CAcG),and chronic atrophic gastritis(CAtG)in the test set,respectively.The areas under the ROC curves(AUCs)of the algorithm for CSuG,CAcG,and CAtG were 0.882,0.905 and 0.910,respectively.The sensitivity and specificity of the deep learning algorithm for the classification of CSuG,CAcG,and CAtG were 0.790 and 1.000(accuracy 0.880),0.985 and 0.829(accuracy 0.901),0.952 and 0.992(accuracy 0.986),respectively.The overall predicted accuracy for three different types of gastritis was 0.867.By flagging the suspicious regions identified by the algorithm in WSI,a more transparent and interpretable diagnosis can be generated.Conclusion The deep learning algorithm achieved high accuracy for chronic gastritis classification using WSIs.By pre-highlighting the different gastritis regions,it might be used as an auxiliary diagnostic tool to improve the work efficiency of pathologists.展开更多
文摘为解决GVF-Snake(gradient vector flow snake)条纹探测相位解缠时,内部条纹线探测偏离条纹边界的问题,提出了一种融合GVF-Snake条纹探测与马尔科夫随机场(Markov random field, MRF)图切法相位解缠方法。通过判断出条纹探测线不是真实条纹边界的情况,对该条纹探测线上一步探测条纹的内部块用MRF图切法进行分割解缠,按照相应解缠准则将两种解缠结果进行融合,形成含有边界跳跃点的粗解缠结果,并用高通滤波插值法消除粗解缠结果的边界孤立点的方法研究了矿区梯度较大地区的相位解缠。结果表明:以巨野矿区某工作面为实验区,用两景sentinel-1A的单视复数图像进行两轨法干涉处理的真实相位来验证算法的有效性。在面分析上,以自适应局部平滑相位评估(phase estimation using adaptive regulation based on local smoothing, PEARLS)为评价标准,将本文方法与最小费用流等5种相位解缠算法进行比较。对比结果显示,本文方法的平方根误差、平均绝对误差分别是±0.079 1、±0.009 0、±2.317 3 rad。在线分析上,对只含有变形相位的绝对相位,提取各解缠绝对相位工作面走向线、倾向线的变形。以实际水准观测值为标准,本文方法的平方根误差、平均绝对误差、绝对值最大误差分别是±0.177 48、±0.141 07、±0.405 29 cm。面分析中以PEARLS相位重构为基准,可见本文方法要优于其他常规的解缠方法;同理,线分析中以水准数据作为依据其各项指标亦为最优。
基金Supported by the Polish Ministry of Science and Higher Education in 2009-2012 as a research project (3687/B/T02/2009/37)
文摘The paper covers the electrical capacitance tomography(ECT) data analysis on shear zones formed during silo discharging process.This is due to the ECT aptitude for detection of slight changes of material concentration.On the basis of ECT visualisations,wall-adjacent shear zone profiles are analysed for different wall roughness parameters.The analysis on changes of material concentration,based on ECT images,enables the calculation for the characteristic parameters of shear zones-size and material concentration inside the shear zone in a dynamic process of silo discharging.In order to verify the methodology a series of experiments on gravitational flow of bulk solids under various conditions were conducted with different initial granular material packing densities and silo wall roughness.The investigation shows that the increase in container wall roughness is an effective method for reducing the dynamic effects during the material discharging,since these effects are resulted from the resonance between hopper construction and trembling material.Such effects will damage industrial equipment in practical applications and need further investigation.
文摘Objective To develope a deep learning algorithm for pathological classification of chronic gastritis and assess its performance using whole-slide images(WSIs).Methods We retrospectively collected 1,250 gastric biopsy specimens(1,128 gastritis,122 normal mucosa)from PLA General Hospital.The deep learning algorithm based on DeepLab v3(ResNet-50)architecture was trained and validated using 1,008 WSIs and 100 WSIs,respectively.The diagnostic performance of the algorithm was tested on an independent test set of 142 WSIs,with the pathologists’consensus diagnosis as the gold standard.Results The receiver operating characteristic(ROC)curves were generated for chronic superficial gastritis(CSuG),chronic active gastritis(CAcG),and chronic atrophic gastritis(CAtG)in the test set,respectively.The areas under the ROC curves(AUCs)of the algorithm for CSuG,CAcG,and CAtG were 0.882,0.905 and 0.910,respectively.The sensitivity and specificity of the deep learning algorithm for the classification of CSuG,CAcG,and CAtG were 0.790 and 1.000(accuracy 0.880),0.985 and 0.829(accuracy 0.901),0.952 and 0.992(accuracy 0.986),respectively.The overall predicted accuracy for three different types of gastritis was 0.867.By flagging the suspicious regions identified by the algorithm in WSI,a more transparent and interpretable diagnosis can be generated.Conclusion The deep learning algorithm achieved high accuracy for chronic gastritis classification using WSIs.By pre-highlighting the different gastritis regions,it might be used as an auxiliary diagnostic tool to improve the work efficiency of pathologists.
