Resting state fMRI feature-based cerebral glioma grading by support vector machine
- 17 September 2014
- journal article
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 10 (7) , 1167-1174
Abstract
Tumor grading plays an essential role in the optimal selection of solid tumor treatment. Noninvasive methods are needed for clinical grading of tumors. This study aimed to extract parameters of resting state blood oxygenation level-dependent functional magnetic resonance imaging (RS-fMRI) in the region of glioma and use the extracted features for tumor grading. Tumor segmentation was performed with both conventional MRI and RS-fMRI. Four typical parameters, signal intensity difference ratio, signal intensity correlation (SIC), fractional amplitude of low-frequency fluctuation (fALFF) and regional homogeneity (ReHo), were defined to analyze tumor regions. Mann–Whitney \(U\) test was employed to identify statistical difference of these four parameters between low-grade glioma (LGG) and high-grade glioma (HGG), respectively. Support vector machine (SVM) was employed to assess the diagnostic contributions of these parameters. Compared with LGG, HGG had more complex anatomical morphology and BOLD-fMRI features in the tumor region. SIC \((p<0.001)\) , fALFF ( \(p=0.02\) ) and ReHo ( \(p=0.17\) ) were selected as features for classification according to the test \(p\) value. The accuracy, sensitivity and specificity of SVM classification were better than 80, where SIC had the best classification accuracy (89). Parameters of RS-fMRI are effective to classify the tumor grade in glioma cases. The results indicate that this technique has clinical potential to serve as a complementary diagnostic tool.
Keywords
This publication has 43 references indexed in Scilit:
- Automated differentiation of glioblastomas from intracranial metastases using 3T MR spectroscopic and perfusion dataInternational Journal of Computer Assisted Radiology and Surgery, 2013
- Modifications of Default-Mode Network Connectivity in Patients with Cerebral GliomaPLOS ONE, 2012
- Individual classification of ADHD patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniquesFrontiers in Systems Neuroscience, 2012
- REST: A Toolkit for Resting-State Functional Magnetic Resonance Imaging Data ProcessingPLOS ONE, 2011
- MR diffusion tensor and perfusion-weighted imaging in preoperative grading of supratentorial nonenhancing gliomasNeuro-Oncology, 2011
- Toward discovery science of human brain functionProceedings of the National Academy of Sciences, 2010
- Using coherence to measure regional homogeneity of resting-state fMRI signalFrontiers in Systems Neuroscience, 2010
- Classification of brain tumor type and grade using MRI texture and shape in a machine learning schemeMagnetic Resonance in Medicine, 2009
- The 2007 WHO Classification of Tumours of the Central Nervous SystemActa Neuropathologica, 2007
- Altered baseline brain activity in children with ADHD revealed by resting-state functional MRIBrain and Development, 2007