为了提高融合多序列MR图像应用于脑肿瘤提取时分割区域的准确性,基于核稀疏表示分类方法,联合多序列MR图像中的空间结构和灰度特征信息,提出一种空间特征联合的脑肿瘤核稀疏表示分类方法.首先构建各个类别的子字典,再用邻域滤波核稀疏...为了提高融合多序列MR图像应用于脑肿瘤提取时分割区域的准确性,基于核稀疏表示分类方法,联合多序列MR图像中的空间结构和灰度特征信息,提出一种空间特征联合的脑肿瘤核稀疏表示分类方法.首先构建各个类别的子字典,再用邻域滤波核稀疏表示方法对多序列脑MR图像进行分类,该邻域滤波核可以有效地将灰度特征与空间结构结合起来提高脑肿瘤提取的准确性.对国际数据库MICCAI Bra TS提供的临床和仿真数据进行分割.结果表明:与稀疏表示分类方法相比,所提出的基于空间特征联合核稀疏表示的脑肿瘤提取方法由于增加了空间结构信息,所得的提取准确率提高了5%~6%.展开更多
Algebraic solutions of the D-dimensional Schrodinger equation with Killingbeck potential are investigated using the Lie algebraic approach within the framework of quasi-exact solvability. The spectrum and wavefunction...Algebraic solutions of the D-dimensional Schrodinger equation with Killingbeck potential are investigated using the Lie algebraic approach within the framework of quasi-exact solvability. The spectrum and wavefunctions of the system are reported and the allowed values of the potential parameters are obtained through the sl(2) algebraization.展开更多
文摘为了提高融合多序列MR图像应用于脑肿瘤提取时分割区域的准确性,基于核稀疏表示分类方法,联合多序列MR图像中的空间结构和灰度特征信息,提出一种空间特征联合的脑肿瘤核稀疏表示分类方法.首先构建各个类别的子字典,再用邻域滤波核稀疏表示方法对多序列脑MR图像进行分类,该邻域滤波核可以有效地将灰度特征与空间结构结合起来提高脑肿瘤提取的准确性.对国际数据库MICCAI Bra TS提供的临床和仿真数据进行分割.结果表明:与稀疏表示分类方法相比,所提出的基于空间特征联合核稀疏表示的脑肿瘤提取方法由于增加了空间结构信息,所得的提取准确率提高了5%~6%.
文摘Algebraic solutions of the D-dimensional Schrodinger equation with Killingbeck potential are investigated using the Lie algebraic approach within the framework of quasi-exact solvability. The spectrum and wavefunctions of the system are reported and the allowed values of the potential parameters are obtained through the sl(2) algebraization.