singular value decomposition

Glioma grading is an important clinical procedure that determines the procedure of the patient's treatment. There is an increasing interest in other complementary techniques in addition to histo-pathological evaluation as the gold standard method. Perfusion indices have shown promising correlations with histo-pathological grades and neovascularization degrees in gliomas. In this study, the processing times and classification performances of cerebral blood flow (CBF) parameters calculated using singular value decomposition (SVD) and Fourier deconvolution methods were evaluated.

The statistical differences between the CBF magnitudes of the high- and low-grade gliomas were evaluated for eighteen patients with pathologically proven gliomas (Low-grade gliomas, 5; High-grade gliomas, 13). The classification performances of the calculated indices were evaluated using the receiver operating curve analysis.

The deconvolution processing times for the SVD method were significantly higher than those of the Fourier deconvolution method (about ~9 times). There were statistically significant differences in both CBF indices between the high- and low-grade gliomas (P<0.05). In ROC curve analysis, CBF indices calculated by the SVD method had a higher area under the curve (about 8538.5 vs. 8153.8).

Based on the study, the glioma grade might be determined using the Fourier-based CBF index with an almost similar grading efficiency and a much lower processing time than the CBF index calculated by the SVD method.