MRI - STABILITY OF 3 SUPERVISED SEGMENTATION TECHNIQUES
MRI - STABILITY OF 3 SUPERVISED SEGMENTATION TECHNIQUES
复制标题
DOI：
10.1016/0730-725x(93)90417-c
复制
发表时间：
1993-01-01
影响因子：
2.5
通讯作者：
SILBIGER, M
中科院分区：
文献类型：
--
作者：
CLARKE, LP;VELTHUIZEN, RP;SILBIGER, M
三个家庭的模式识别技术的监督分割方法被用来分割多光谱MRI数据。研究了最大似然法（MLM），k-近邻（k-NN），和反向传播人工神经网络（ANN）。在执行速度和训练数据选择的稳定性方面测量性能，即感兴趣区域（ROI）选择以及切片间和患者间分类。MLM被证明具有最小的执行时间，但表现出最少的稳定性。k-NN在训练数据选择方面表现出最好的稳定性。为了评估分割技术，使用了正常志愿者和胶质瘤患者的多光谱图像，后者有和没有MR对比材料。应用的所有措施表明，k-NN提供了最好的结果。
Supervised segmentation methods from three families of pattern recognition techniques were used to segment multispectral MRI data. Studied were the maximum likelihood method (MLM), k-nearest neighbors (k-NN), and a back-propagation artificial neural net (ANN). Performance was measured in terms of execution speed, and stability for the selection of training data, namely, region of interest (ROI) selection, and interslice and interpatient classifications. MLM proved to have the smallest execution times, but demonstrated the least stability. k-NN showed the best stability for training data selection. To evaluste the segmentation techniques, multispectral images were used of normal volunteers and patients with gliomas, the latter with and without MR contrast material. All measures applied indicated that k-NN provides the best results.