Noninvasive assessment of Ki-67 labeling index in glioma patients based on multi-parameters derived from advanced MR...

To investigate the predictive value of multi-parameters derived from advanced MR imaging for Ki-67 labeling index (LI) in glioma patients.

One hundred and nine patients with histologically confirmed gliomas were evaluated retrospectively. These patients underwent advanced MR imaging, including dynamic susceptibility-weighted contrast enhanced MR imaging (DSC), MR spectroscopy imaging (MRS), diffusion-weighted imaging (DWI) and diffusion-tensor imaging (DTI), before treatment. Twenty-one parameters were extracted, including the maximum, minimum and mean values of relative cerebral blood flow (rCBF), relative cerebral blood volume (rCBV), relative mean transit time (rMTT), relative apparent diffusion coefficient (rADC), relative fractional anisotropy (rFA) and relative mean diffusivity (rMD) respectively, and ration of choline (Cho)/creatine (Cr), Cho/N-acetylaspartate (NAA) and NAA/Cr. Stepwise multivariate regression was performed to build multivariate models to predict Ki-67 LI. Pearson correlation analysis was used to investigate the correlation between imaging parameters and the grade of glioma. One-way analysis of variance (ANOVA) was used to explore the differences of the imaging parameters among the gliomas of grade II, III, and IV.

The multivariate regression showed that the model of five parameters, including rCBV_max (RC=0.282), rCBF_max (RC=0.151), rADC_min (RC= -0.14), rFA_max (RC=0.325) and Cho/Cr ratio (RC=0.157) predicted the Ki-67 LI with a root mean square (RMS) error of 0. 0679 (R² = 0.8025).The regression check of this model showed that there were no multicollinearity problem (variance inflation factor: rCBV_max, 3.22; rCBF_max, 3.14; rADC_min, 1.96; rFA_max, 2.51; Cho/Cr ratio, 1.64), and the functional form of this model was appropriate (F test: p=0.682). The results of Pearson correlation analysis showed that the rCBV_max, rCBF_max, rFA_max, the ratio of Cho/Cr and Cho/NAA were positively correlated with Ki-67 LI and the grade of glioma, while the rADC_min and rMD_min were negatively correlated with Ki-67 LI and the grade of glioma.

Combining multiple parameters derived from DSC, DTI, DWI and MRS can precisely predict the Ki-67 LI in glioma patients.