目的为了提升基于单模态B型超声(B超)的乳腺癌计算机辅助诊断(computer-aided diagnosis,CAD)模型性能,提出一种基于两阶段深度迁移学习(two-stage deep transfer learning,TSDTL)的乳腺超声CAD算法,将超声弹性图像中的有效信息迁移至基...目的为了提升基于单模态B型超声(B超)的乳腺癌计算机辅助诊断(computer-aided diagnosis,CAD)模型性能,提出一种基于两阶段深度迁移学习(two-stage deep transfer learning,TSDTL)的乳腺超声CAD算法,将超声弹性图像中的有效信息迁移至基于B超的乳腺癌CAD模型之中,进一步提升该CAD模型的性能。方法在第1阶段的深度迁移学习中,提出将双模态超声图像重建任务作为一种自监督学习任务,训练一个关联多模态深度卷积神经网络模型,实现B超图像和超声弹性图像之间的信息交互迁移;在第2阶段的深度迁移学习中,基于隐式的特权信息学习(learning using privilaged information,LUPI)范式,进行基于双模态超声图像的乳腺肿瘤分类任务,通过标签信息引导下的分类进一步加强两个模态之间的特征融合与信息交互;采用单模态B超数据对所对应通道的分类网络进行微调,实现最终的乳腺癌B超图像分类模型。结果实验在一个乳腺肿瘤双模超声数据集上进行算法性能验证。实验结果表明,通过迁移超声弹性图像的信息,TSDTL在基于B超的乳腺癌诊断任务中取得的平均分类准确率为87.84±2.08%、平均敏感度为88.89±3.70%、平均特异度为86.71±2.21%、平均约登指数为75.60±4.07%,优于直接基于单模态B超训练的分类模型以及多种典型迁移学习算法。结论提出的TSDTL算法通过两阶段的深度迁移学习,将超声弹性图像的信息有效迁移至基于B超的乳腺癌CAD模型,提升了模型的诊断性能,具备潜在的应用可行性。展开更多
A new semi-serial fusion method of multiple feature based on learning using privileged information(LUPI) model was put forward.The exploitation of LUPI paradigm permits the improvement of the learning accuracy and its...A new semi-serial fusion method of multiple feature based on learning using privileged information(LUPI) model was put forward.The exploitation of LUPI paradigm permits the improvement of the learning accuracy and its stability,by additional information and computations using optimization methods.The execution time is also reduced,by sparsity and dimension of testing feature.The essence of improvements obtained using multiple features types for the emotion recognition(speech expression recognition),is particularly applicable when there is only one modality but still need to improve the recognition.The results show that the LUPI in unimodal case is effective when the size of the feature is considerable.In comparison to other methods using one type of features or combining them in a concatenated way,this new method outperforms others in recognition accuracy,execution reduction,and stability.展开更多
文摘目的为了提升基于单模态B型超声(B超)的乳腺癌计算机辅助诊断(computer-aided diagnosis,CAD)模型性能,提出一种基于两阶段深度迁移学习(two-stage deep transfer learning,TSDTL)的乳腺超声CAD算法,将超声弹性图像中的有效信息迁移至基于B超的乳腺癌CAD模型之中,进一步提升该CAD模型的性能。方法在第1阶段的深度迁移学习中,提出将双模态超声图像重建任务作为一种自监督学习任务,训练一个关联多模态深度卷积神经网络模型,实现B超图像和超声弹性图像之间的信息交互迁移;在第2阶段的深度迁移学习中,基于隐式的特权信息学习(learning using privilaged information,LUPI)范式,进行基于双模态超声图像的乳腺肿瘤分类任务,通过标签信息引导下的分类进一步加强两个模态之间的特征融合与信息交互;采用单模态B超数据对所对应通道的分类网络进行微调,实现最终的乳腺癌B超图像分类模型。结果实验在一个乳腺肿瘤双模超声数据集上进行算法性能验证。实验结果表明,通过迁移超声弹性图像的信息,TSDTL在基于B超的乳腺癌诊断任务中取得的平均分类准确率为87.84±2.08%、平均敏感度为88.89±3.70%、平均特异度为86.71±2.21%、平均约登指数为75.60±4.07%,优于直接基于单模态B超训练的分类模型以及多种典型迁移学习算法。结论提出的TSDTL算法通过两阶段的深度迁移学习,将超声弹性图像的信息有效迁移至基于B超的乳腺癌CAD模型,提升了模型的诊断性能,具备潜在的应用可行性。
文摘针对模拟电路故障诊断识别率较低的问题,提出了基于双空间特征提取的融合特权信息支持向量机的模拟电路故障诊断新方法。首先对采集的信号进行主成分分析(principal component analysis,PCA)——特征提取;并用融合特权信息支持向量机LUPI-SVM(SVM of learning using privileged information,LUPI-SVM)分类器和SVM-GA分类器进行预分类;对分类结果不同的样本进行独立成分分析(independent component analysis,ICA)—特征提取,并用LUPI_SVM进行分类识别,Sallen-Key滤波电路故障诊断仿真实验结果表明该方法有效提高了分类的性能,为模拟电路故障诊断提供了新的途径。
基金supported by the National Key Research and Development Program of China(2016YFB1001404)the National Natural Science Foundation of China(61873299,61702036,61572075)
文摘A new semi-serial fusion method of multiple feature based on learning using privileged information(LUPI) model was put forward.The exploitation of LUPI paradigm permits the improvement of the learning accuracy and its stability,by additional information and computations using optimization methods.The execution time is also reduced,by sparsity and dimension of testing feature.The essence of improvements obtained using multiple features types for the emotion recognition(speech expression recognition),is particularly applicable when there is only one modality but still need to improve the recognition.The results show that the LUPI in unimodal case is effective when the size of the feature is considerable.In comparison to other methods using one type of features or combining them in a concatenated way,this new method outperforms others in recognition accuracy,execution reduction,and stability.
