目的探讨酰胺质子转移加权成像(amide proton transfer weighted imaging,APTw)的影像组学术前预测宫颈癌淋巴血管间隙侵犯(lymphovascular space invasion,LVSI)的价值。材料与方法回顾性分析经手术病理证实的宫颈癌患者病例及影像资...目的探讨酰胺质子转移加权成像(amide proton transfer weighted imaging,APTw)的影像组学术前预测宫颈癌淋巴血管间隙侵犯(lymphovascular space invasion,LVSI)的价值。材料与方法回顾性分析经手术病理证实的宫颈癌患者病例及影像资料66例。所有患者均行盆腔3.0 T MRI检查,包括轴位T2WI、矢状位T2WI、动态对比增强磁共振成像(dynamic contrast enhanced magnetic resonance imaging,DCE-MRI)和3D-APTw序列扫描。在APTw-T2WI融合图像上对肿瘤实质区域进行感兴趣区(region of interest,ROI)勾画并记录APT值。在APT重建图像上进行肿瘤病灶分割并提取影像组学特征。采用组内相关系数(intra-class correlation coefficient,ICC)选取观察者内和观察者间复测信度好的影像组学特征(ICC>0.900)。采用递归特征消除法(recursive feature elimination,RFE)及最小绝对收缩和选择算子(least absolute shrinkage and selection operator,LASSO)算法进行特征降维和筛选。基于logistic回归分类器构建临床模型、APTw影像组学模型和联合组学模型。采用受试者工作特征(receiver operating characteristic,ROC)曲线和决策曲线分析(decision curve analysis,DCA)评估模型的诊断效能和临床价值,采用DeLong检验比较不同模型的预测效能。结果在训练集中,APTw影像组学模型预测宫颈癌LVSI的效能高于临床模型(AUC=0.826 vs.0.675),差异有统计学意义(DeLong检验P<0.05)。联合组学模型在训练集和测试集中的AUC值分别为0.838和0.825。DeLong检验结果显示,联合组学模型在训练集中术前评估LVSI的效能显著高于临床模型和APTw影像组学模型(P均<0.05)。决策曲线显示APTw影像组学模型和联合组学模型在训练集和测试集中均具有较高的临床价值。结论基于APTw的影像组学模型在术前预测宫颈癌LVSI方面具有较高的潜力,联合临床因素能进一步提高预测效能,有望为宫颈癌患者的个体化治疗和预后评估提供重要的支持。展开更多
目的评估基于多参数磁共振的膀胱影像-报告和数据系统(vesical imaging-reporting and data system,VI-RADS)对膀胱癌肌层浸润与否的诊断预测价值。方法收集重庆大学附属肿瘤医院2017年1月至2021年3月行多参数磁共振检查并完成经尿道膀...目的评估基于多参数磁共振的膀胱影像-报告和数据系统(vesical imaging-reporting and data system,VI-RADS)对膀胱癌肌层浸润与否的诊断预测价值。方法收集重庆大学附属肿瘤医院2017年1月至2021年3月行多参数磁共振检查并完成经尿道膀胱肿瘤切除术(transurethral resection of bladder tumor,TURBT)或根治性膀胱切除术的278例膀胱病变患者临床资料;不同影像学医师分别进行磁共振VI-RADS评分,Kappa检验其一致性;分析VI-RADS评分与病理结果的吻合度;采用受试者工作特征曲线(receiver operating characteristic curve,ROC)分析VI-RADS各评分诊断肌层浸润性膀胱癌的效能;比较不同手术方式获取的病理组织与VI-RADS评分吻合度。结果两位影像评估者VI-RADS评分一致性较好(符合率为79.86%,Kappa值=0.7508,P<0.001)。ROC曲线分析显示,VI-RADS评分≥3时预测肌层浸润性膀胱癌的曲线下面积为0.774,约登指数为54.78%,敏感度为96.16%,特异度为58.62%,阳性预测值(positive predictive value,PPV)为58.14%,阴性预测值(negative predictive value,NPV)为96.23%。根治性膀胱切除术获得的病理结果与VI-RADS评分吻合度高达92.85%,显著高于行TURBT术的79.81%(P<0.05)。结论术前多参数磁共振VI-RADS评分具有良好的一致性和稳定性,与术后病理吻合度高;VI-RADS评分≥3分对肌层浸润性膀胱癌的预测价值较好,可指导临床手术选择方式。展开更多
目的评估超分辨率重建技术是否能提高基于T2WI图像的深度学习预测子宫内膜癌淋巴脉管间隙浸润(lymphvascular space invasion,LVSI)的诊断效能。材料与方法回顾性纳入406例病例,按照8∶2随机划分为训练集(n=325例)和验证集(n=81例)。我...目的评估超分辨率重建技术是否能提高基于T2WI图像的深度学习预测子宫内膜癌淋巴脉管间隙浸润(lymphvascular space invasion,LVSI)的诊断效能。材料与方法回顾性纳入406例病例,按照8∶2随机划分为训练集(n=325例)和验证集(n=81例)。我们对常规盆腔矢状位T2WI图像进行超分辨率重建,得到超分辨率T2WI(super high resolution T2WI,SRT2)图像。分别基于常规T2WI及SRT2图像进行深度学习建模,以预测子宫内膜癌LVSI状态。随后,在验证集中对两组图像构建的模型进行验证,对比两个模型在训练集及验证集的诊断效能。以病理诊断为金标准,评估指标包括:曲线下面积(area under the curve,AUC),敏感度、特异度,并采用DeLong检验比较模型差异。结果在训练集及验证集中,基于常规T2WI图像的深度学习模型AUC(95%置信区间)分别为0.792(0.733~0.851)、0.759(0.649~0.870),敏感度分别为77.50%、68.18%,特异度分别为77.08%、80.67%;基于SRT2图像的深度学习模型AUC(95%置信区间)分别为0.897(0.852~0.943)、0.899(0.819~0.980),敏感度分别为87.80%、86.40%,特异度分别为88.45%、89.20%。两个模型在训练集及验证集中的差异均有统计学意义(P<0.05),基于SRT2的深度学习模型表现更优。结论超分辨率重建技术有望通过提高图像质量进而提升深度学习术前预测子宫内膜癌LVSI的诊断效能。展开更多
Rock burst is a severe disaster in mining and underground engineering,and it is important to predict the rock burst risk for minimizing the loss during the constructing process.The rock burst proneness was connected w...Rock burst is a severe disaster in mining and underground engineering,and it is important to predict the rock burst risk for minimizing the loss during the constructing process.The rock burst proneness was connected with the acoustic emission(AE) parameter in this work,which contributes to predicting the rock burst risk using AE technique.Primarily,a rock burst proneness index is proposed,and it just depends on the heterogeneous degree of rock material.Then,the quantificational formula between the value of rock burst proneness index and the accumulative AE counts in rock sample under uniaxial compression with axial strain increases is developed.Finally,three kinds of rock samples,i.e.,granite,limestone and sandstone are tested about variation of the accumulative AE counts under uniaxial compression,and the test data are fitted well with the theoretic formula.展开更多
To make full use of the gas resource, stabilize the pipe network pressure, and obtain higher economic benefits in the iron and steel industry, the surplus gas prediction and scheduling models were proposed. Before app...To make full use of the gas resource, stabilize the pipe network pressure, and obtain higher economic benefits in the iron and steel industry, the surplus gas prediction and scheduling models were proposed. Before applying the forecasting techniques, a support vector classifier was first used to classify the data, and then the filtering was used to create separate trend and volatility sequences. After forecasting, the Markov chain transition probability matrix was introduced to adjust the residual. Simulation results using surplus gas data from an iron and steel enterprise demonstrate that the constructed SVC-HP-ENN-LSSVM-MC prediction model prediction is accurate, and that the classification accuracy is high under different conditions. Based on this, the scheduling model was constructed for surplus gas operating, and it has been used to investigate the comprehensive measures for managing the operational probabilistic risk and optimize the economic benefit at various working conditions and implementations. It has extended the concepts of traditional surplus gas dispatching systems, and provides a method for enterprises to determine optimal schedules.展开更多
Short-term traffic flow prediction is one of the essential issues in intelligent transportation systems(ITS). A new two-stage traffic flow prediction method named AKNN-AVL method is presented, which combines an advanc...Short-term traffic flow prediction is one of the essential issues in intelligent transportation systems(ITS). A new two-stage traffic flow prediction method named AKNN-AVL method is presented, which combines an advanced k-nearest neighbor(AKNN)method and balanced binary tree(AVL) data structure to improve the prediction accuracy. The AKNN method uses pattern recognition two times in the searching process, which considers the previous sequences of traffic flow to forecast the future traffic state. Clustering method and balanced binary tree technique are introduced to build case database to reduce the searching time. To illustrate the effects of these developments, the accuracies performance of AKNN-AVL method, k-nearest neighbor(KNN) method and the auto-regressive and moving average(ARMA) method are compared. These methods are calibrated and evaluated by the real-time data from a freeway traffic detector near North 3rd Ring Road in Beijing under both normal and incident traffic conditions.The comparisons show that the AKNN-AVL method with the optimal neighbor and pattern size outperforms both KNN method and ARMA method under both normal and incident traffic conditions. In addition, the combinations of clustering method and balanced binary tree technique to the prediction method can increase the searching speed and respond rapidly to case database fluctuations.展开更多
When detecting deletions in complex human genomes,split-read approaches using short reads generated with next-generation sequencing still face the challenge that either false discovery rate is high,or sensitivity is l...When detecting deletions in complex human genomes,split-read approaches using short reads generated with next-generation sequencing still face the challenge that either false discovery rate is high,or sensitivity is low.To address the problem,an integrated strategy is proposed.It organically combines the fundamental theories of the three mainstream methods(read-pair approaches,split-read technologies and read-depth analysis) with modern machine learning algorithms,using the recipe of feature extraction as a bridge.Compared with the state-of-art split-read methods for deletion detection in both low and high sequence coverage,the machine-learning-aided strategy shows great ability in intelligently balancing sensitivity and false discovery rate and getting a both more sensitive and more precise call set at single-base-pair resolution.Thus,users do not need to rely on former experience to make an unnecessary trade-off beforehand and adjust parameters over and over again any more.It should be noted that modern machine learning models can play an important role in the field of structural variation prediction.展开更多
文摘目的探讨酰胺质子转移加权成像(amide proton transfer weighted imaging,APTw)的影像组学术前预测宫颈癌淋巴血管间隙侵犯(lymphovascular space invasion,LVSI)的价值。材料与方法回顾性分析经手术病理证实的宫颈癌患者病例及影像资料66例。所有患者均行盆腔3.0 T MRI检查,包括轴位T2WI、矢状位T2WI、动态对比增强磁共振成像(dynamic contrast enhanced magnetic resonance imaging,DCE-MRI)和3D-APTw序列扫描。在APTw-T2WI融合图像上对肿瘤实质区域进行感兴趣区(region of interest,ROI)勾画并记录APT值。在APT重建图像上进行肿瘤病灶分割并提取影像组学特征。采用组内相关系数(intra-class correlation coefficient,ICC)选取观察者内和观察者间复测信度好的影像组学特征(ICC>0.900)。采用递归特征消除法(recursive feature elimination,RFE)及最小绝对收缩和选择算子(least absolute shrinkage and selection operator,LASSO)算法进行特征降维和筛选。基于logistic回归分类器构建临床模型、APTw影像组学模型和联合组学模型。采用受试者工作特征(receiver operating characteristic,ROC)曲线和决策曲线分析(decision curve analysis,DCA)评估模型的诊断效能和临床价值,采用DeLong检验比较不同模型的预测效能。结果在训练集中,APTw影像组学模型预测宫颈癌LVSI的效能高于临床模型(AUC=0.826 vs.0.675),差异有统计学意义(DeLong检验P<0.05)。联合组学模型在训练集和测试集中的AUC值分别为0.838和0.825。DeLong检验结果显示,联合组学模型在训练集中术前评估LVSI的效能显著高于临床模型和APTw影像组学模型(P均<0.05)。决策曲线显示APTw影像组学模型和联合组学模型在训练集和测试集中均具有较高的临床价值。结论基于APTw的影像组学模型在术前预测宫颈癌LVSI方面具有较高的潜力,联合临床因素能进一步提高预测效能,有望为宫颈癌患者的个体化治疗和预后评估提供重要的支持。
文摘目的评估超分辨率重建技术是否能提高基于T2WI图像的深度学习预测子宫内膜癌淋巴脉管间隙浸润(lymphvascular space invasion,LVSI)的诊断效能。材料与方法回顾性纳入406例病例,按照8∶2随机划分为训练集(n=325例)和验证集(n=81例)。我们对常规盆腔矢状位T2WI图像进行超分辨率重建,得到超分辨率T2WI(super high resolution T2WI,SRT2)图像。分别基于常规T2WI及SRT2图像进行深度学习建模,以预测子宫内膜癌LVSI状态。随后,在验证集中对两组图像构建的模型进行验证,对比两个模型在训练集及验证集的诊断效能。以病理诊断为金标准,评估指标包括:曲线下面积(area under the curve,AUC),敏感度、特异度,并采用DeLong检验比较模型差异。结果在训练集及验证集中,基于常规T2WI图像的深度学习模型AUC(95%置信区间)分别为0.792(0.733~0.851)、0.759(0.649~0.870),敏感度分别为77.50%、68.18%,特异度分别为77.08%、80.67%;基于SRT2图像的深度学习模型AUC(95%置信区间)分别为0.897(0.852~0.943)、0.899(0.819~0.980),敏感度分别为87.80%、86.40%,特异度分别为88.45%、89.20%。两个模型在训练集及验证集中的差异均有统计学意义(P<0.05),基于SRT2的深度学习模型表现更优。结论超分辨率重建技术有望通过提高图像质量进而提升深度学习术前预测子宫内膜癌LVSI的诊断效能。
基金Project(2010CB226804)supported by the National Basic Research Program(973 Program)of ChinaProject(11202108)supported by the National Natural Science Foundation of ChinaProject(BK20130189)supported by the Natural Science Foundation of Jiangsu Province,China
文摘Rock burst is a severe disaster in mining and underground engineering,and it is important to predict the rock burst risk for minimizing the loss during the constructing process.The rock burst proneness was connected with the acoustic emission(AE) parameter in this work,which contributes to predicting the rock burst risk using AE technique.Primarily,a rock burst proneness index is proposed,and it just depends on the heterogeneous degree of rock material.Then,the quantificational formula between the value of rock burst proneness index and the accumulative AE counts in rock sample under uniaxial compression with axial strain increases is developed.Finally,three kinds of rock samples,i.e.,granite,limestone and sandstone are tested about variation of the accumulative AE counts under uniaxial compression,and the test data are fitted well with the theoretic formula.
基金Project(51204082)supported by the National Natural Science Foundation of ChinaProject(KKSY201458118)supported by the Talent Cultivation Project of Kuning University of Science and Technology,China
文摘To make full use of the gas resource, stabilize the pipe network pressure, and obtain higher economic benefits in the iron and steel industry, the surplus gas prediction and scheduling models were proposed. Before applying the forecasting techniques, a support vector classifier was first used to classify the data, and then the filtering was used to create separate trend and volatility sequences. After forecasting, the Markov chain transition probability matrix was introduced to adjust the residual. Simulation results using surplus gas data from an iron and steel enterprise demonstrate that the constructed SVC-HP-ENN-LSSVM-MC prediction model prediction is accurate, and that the classification accuracy is high under different conditions. Based on this, the scheduling model was constructed for surplus gas operating, and it has been used to investigate the comprehensive measures for managing the operational probabilistic risk and optimize the economic benefit at various working conditions and implementations. It has extended the concepts of traditional surplus gas dispatching systems, and provides a method for enterprises to determine optimal schedules.
基金Project(2012CB725403)supported by the National Basic Research Program of ChinaProjects(71210001,51338008)supported by the National Natural Science Foundation of ChinaProject supported by World Capital Cities Smooth Traffic Collaborative Innovation Center and Singapore National Research Foundation Under Its Campus for Research Excellence and Technology Enterprise(CREATE)Programme
文摘Short-term traffic flow prediction is one of the essential issues in intelligent transportation systems(ITS). A new two-stage traffic flow prediction method named AKNN-AVL method is presented, which combines an advanced k-nearest neighbor(AKNN)method and balanced binary tree(AVL) data structure to improve the prediction accuracy. The AKNN method uses pattern recognition two times in the searching process, which considers the previous sequences of traffic flow to forecast the future traffic state. Clustering method and balanced binary tree technique are introduced to build case database to reduce the searching time. To illustrate the effects of these developments, the accuracies performance of AKNN-AVL method, k-nearest neighbor(KNN) method and the auto-regressive and moving average(ARMA) method are compared. These methods are calibrated and evaluated by the real-time data from a freeway traffic detector near North 3rd Ring Road in Beijing under both normal and incident traffic conditions.The comparisons show that the AKNN-AVL method with the optimal neighbor and pattern size outperforms both KNN method and ARMA method under both normal and incident traffic conditions. In addition, the combinations of clustering method and balanced binary tree technique to the prediction method can increase the searching speed and respond rapidly to case database fluctuations.
基金Project(61472026)supported by the National Natural Science Foundation of ChinaProject(2014J410081)supported by Guangzhou Scientific Research Program,China
文摘When detecting deletions in complex human genomes,split-read approaches using short reads generated with next-generation sequencing still face the challenge that either false discovery rate is high,or sensitivity is low.To address the problem,an integrated strategy is proposed.It organically combines the fundamental theories of the three mainstream methods(read-pair approaches,split-read technologies and read-depth analysis) with modern machine learning algorithms,using the recipe of feature extraction as a bridge.Compared with the state-of-art split-read methods for deletion detection in both low and high sequence coverage,the machine-learning-aided strategy shows great ability in intelligently balancing sensitivity and false discovery rate and getting a both more sensitive and more precise call set at single-base-pair resolution.Thus,users do not need to rely on former experience to make an unnecessary trade-off beforehand and adjust parameters over and over again any more.It should be noted that modern machine learning models can play an important role in the field of structural variation prediction.
