Manifold Learning in MR spectroscopy using nonlinear dimensionality reduction and unsupervised clustering

作者：Yang Guang^*; Raschke Felix; Barrick Thomas R; Howe Franklyn A

来源：Magnetic Resonance in Medicine, 2015, 74(3): 868-878.

DOI：10.1002/mrm.25447

• pattern recognition
• dimensionality reduction
• Laplacian eigenmaps
• magnetic resonance spectroscopy
• magnetic resonance spectroscopic imaging

PurposeTo investigate whether nonlinear dimensionality reduction improves unsupervised classification of H-1 MRS brain tumor data compared with a linear method.
MethodsIn vivo single-voxel H-1 magnetic resonance spectroscopy (55 patients) and H-1 magnetic resonance spectroscopy imaging (MRSI) (29 patients) data were acquired from histopathologically diagnosed gliomas. Data reduction using Laplacian eigenmaps (LE) or independent component analysis (ICA) was followed by k-means clustering or agglomerative hierarchical clustering (AHC) for unsupervised learning to assess tumor grade and for tissue type segmentation of MRSI data.
ResultsAn accuracy of 93% in classification of glioma grade II and grade IV, with 100% accuracy in distinguishing tumor and normal spectra, was obtained by LE with unsupervised clustering, but not with the combination of k-means and ICA. With H-1 MRSI data, LE provided a more linear distribution of data for cluster analysis and better cluster stability than ICA. LE combined with k-means or AHC provided 91% accuracy for classifying tumor grade and 100% accuracy for identifying normal tissue voxels. Color-coded visualization of normal brain, tumor core, and infiltration regions was achieved with LE combined with AHC.
ConclusionThe LE method is promising for unsupervised clustering to separate brain and tumor tissue with automated color-coding for visualization of H-1 MRSI data after cluster analysis. Magn Reson Med 74:868-878, 2015.

• 出版日期2015-9