Abstract
Purpose
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.
Methods
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.
Results
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).
Conclusion
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.
Similar content being viewed by others
References
Svolos P, Tsolaki E, Kapsalaki E et al (2013) Investigating brain tumor differentiation with diffusion and perfusion metrics at 3T MRI using pattern recognition techniques. Magn Reson Imaging 31(9):1567–1577
Pan Y (2012) The study on detection of gliomas MIB-1 index based on MRI feature. Dissertation, Zhejiang University
Svolos P, Tsolaki E, Theodorou K et al (2013) Classification methods for the differentiation of atypical meningiomas using diffusion and perfusion techniques at 3-T MRI. Clin imaging 37(5):856–864
Reiche W, Schuchardt V, Hagen T, Il’yasov KA, Billmann P, Weber J (2010) Differential diagnosis of intracranial ring enhancing lesions-role of diffusion weighted imaging (DWI) and diffusion-tensor imaging (DTI). Clin Neurol Neurosurg 112(3):218–225
Beppu T, Inoue T, Shibata Y, Kurose A, Arai H, Ogasawara A, Ogawa A, Nakamura S, Kabasawa H (2003) Measurement of fractional anisotropy using diffusion tensor MRI in supratentorial astrocytic tumors. J Neurooncol 63(2):109–16
Liu X, Tian W, Kolar B, Yeaney GA, Qiu X, Johnson MD, Ekholm S (2011) MR diffusion tensor and perfusion-weighted imaging in preoperative grading of supratentorial nonenhancing gliomas. Neuro Oncol 13(4):447–55
De Belder FE, Oot AR, Van Hecke W, Venstermans C, Menovsky T, Van Marck V, Van Goethem J, Van den Hauwe L, Vandekerckhove M, Parizel PM (2012) Diffusion tensor imaging provides an insight into the microstructure of meningiomas, high-grade gliomas, and peritumoral edema. Comput Assist Tomogr 36(5):577–82
Tsougos I, Svolos P, Kousi E, Fountas K, Theodorou K, Fezoulidis I, Kapsalaki E (2012) Differentiation of glioblastoma multiforme from metastatic brain tumor using proton magnetic resonance spectroscopy, diffusion and perfusion metrics at 3 T. Cancer Imaging 12:423–36
Jiang Z, Krainik A, David O et al (2010) Impaired fMRI activation in patients with primary brain tumors. Neuroimage 52(2):538–548
Chang EF, Clark A, Smith JS et al (2011) Functional mapping-guided resection of low-grade gliomas in eloquent areas of the brain: improvement of long-term survival: clinical article. J Neurosurg 114(3):566–573
Zacharaki EI, Kanas VG, Davatzikos C (2011) Investigating machine learning techniques for MRI-based classification of brain neoplasms. Int J Comput Assist Radiol Surg 6(6):821–828
Tsolaki E, Svolos P, Kousi E et al (2013) Automated differentiation of glioblastomas from intracranial metastases using 3T MR spectroscopic and perfusion data. Int J Comput Assist Radiol Surg 8(5):751–761
Zacharaki EI, Wang S, Chawla S, Soo Yoo D, Wolf R, Melhem ER, Davatzikos C (2009) Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn Reson Med 62(6):1609–1618
Dimou I, Tsougos I, Tsolaki E, Kousi E, Kapsalaki E, Theodorou K, Kounelakis M, Zervakis M (2011) Brain lesion classification using 3 T MRS spectra and paired SVM kernels. Biomed Signal Process 6(3):314–320
Louis DN, Ohgaki H, Wiestler OD et al (2007) The 2007 WHO classification of tumors of the central nervous system. Acta Neuropathol 114(2):97–109
Connie M, Chen CM, Hou BL, Holodny AI (2008) Effect of age and tumor grade on BOLD functional MR imaging in preoperative assessment of patients with Glioma1. Radiology 248(3):971–978
Esposito R, Mattei PA, Briganti C et al (2012) Modifications of default-mode network connectivity in patients with cerebral glioma. PloS One 7(7):e40231
Zou QH, Zhu CZ, Yang Y et al (2008) An improved approach to detection of amplitude of low-frequency fluctuation (ALFF) for resting-state fMRI: fractional ALFF. J Neurosci Methods 172(1):137–141
Zang YF, He Y, Zhu CZ, Cao QJ, Sui MQ, Liang M et al (2007) Altered baseline brain activity in children with ADHD revealed by resting-state functional MRI. Brain Dev 29:83–91
Liu D, Yan C, Ren J et al (2010) Using coherence to measure regional homogeneity of resting-state fMRI signal. Front Syst Neurosci 4:24
Long XY, Zuo XN, Kiviniemi V, Yang Y, Zou QH, Zhu CZ, Jiang TZ, Yang H, Gong QY, Wang L, Li KC, Xie S, Zang YF (2008) Default mode network as revealed with multiple methods for resting state functional MRI analysis. J Neurosci Methods 171:349–355
Song XW, Dong ZY, Long XY, Li SF, Zuo XN et al (2011) REST: a toolkit for resting-state functional magnetic resonance imaging data processing. PLoS One 6(9):e25031
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
Scholkopf B, Sung KK, Burges CJC et al (1997) Comparing support vector machines with Gaussian kernels to radial basis function classifiers. Trans Signal Process 45(11):2758–2765
Hsu CW, Chang CC, Lin CJ (2003) A practical guide to support vector classification
Metz CE (1989) Some practical issues of experimental design and data analysis in radiological ROC analysis. Invest Radiol 24(3):234–245
Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27(8):861–874
Lüdemann L, Förschler A, Grieger W et al (2006) BOLD signal in the motor cortex shows a correlation with the blood volume of brain tumors. J Magn Reson Imaging 23(4):435–443
olodny AI, Schulder M, Liu WC et al (2000) The effect of brain tumors on BOLD functional MR imaging activation in the adjacent motor cortex: implications for image-guided neurosurgery. Am J Neuroradiol 21(8):1415–1422
Schreiber A, Hubbe U, Ziyeh S et al (2000) The influence of gliomas and nonglial space-occupying Lesions on Blood-oxygen-level-dependent contrast enhancement. Am J Neuroradiol 21(6):1055–1063
Liu WC, Feldman SC, Schulder M et al (2005) The effect of tumour type and distance on activation in the motor cortex. Neuroradiol 47(11):813–819
Price SJ (2010) Advances in imaging low-grade gliomas. In: Low-grade gliomas. Springer, Berlin, pp 1–34
Zonari P, Baraldi P, Crisi G (2007) Multimodal MRI in the characterization of glial neoplasms: the combined role of single-voxel MR spectroscopy, diffusion imaging and echo-planar perfusion imaging. Neuroradiol 49(10):795–803
Biswal BB, Mennes M, Zuo XN et al (2010) Toward discovery science of human brain function. Proc Natl Acad Sci 107(10):4734–4739
Shehzad Z, Kelly AMC, Reiss PT et al (2009) The resting brain: unconstrained yet reliable. Cereb cortex 19(10):2209–2229
Zhang D, Raichle ME (2010) Disease and the brain’s dark energy. Nat Rev Neurol 6(1):15–28
Batjer HH, Loftus CM (2002) Textbook of neurological surgery: principles and practice. Lippincott Williams & Wilkins, New York
Cao Q, Zang Y, Sun L, Sui M, Long X, Zou Qand Wang Y (2006) Abnormal neural activity in children with attention deficit hyperactivity disorder: a resting-state functional magnetic resonance imaging study. Neuroreport 17(10):1033–1036
Cheng W, Ji X, Zhang J et al (2012) Individual classification of ADHD patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniques. Front Syst Neurosci 6:58
He Y, Wang L, Zang Y, Tian L, Zhang X, Li K, Jiang T (2007) Regional coherence changes in the early stages of Alzheimer’s disease: a combined structural and resting-state functional MRI study. Neuroimage 35(2):488–500
Wu T, Long X, Zang Y, Wang L, Hallett M, Li K, Chan P (2009) Regional homogeneity changes in patients with Parkinson’s disease. Hum Brain Mapp 30(5):1502–1510
He Z, Deng W, Li M et al (2012) Aberrant intrinsic brain activity and cognitive deficit in first-episode treatment-naive patients with schizophrenia. Psychol Med 43:769–780
Liu CB, Pan Y, Zhang HS et al (2012) Detecting MGMT expression status of glioma with magnetic resonance image. J Zhejiang Univ Eng Sci 46(1):170–176
Emblem KE, Zoellner FG, Tennoe B et al (2008) Predictive modeling in glioma grading from MR perfusion images using support vector machines. Magn Reson Med 60(4):945–52
Gómez C, Stam CJ, Hornero R et al (2009) Disturbed beta band functional connectivity in patients with mild cognitive impairment: an MEG study. IEEE Trans Biomed Eng 56(6):1683–1690
Bhardwaj RD, Mahmoodabadi SZ, Otsubo H et al (2010) Diffusion tensor tractography detection of functional pathway for the spread of epileptiform activity between temporal lobe and Rolandic region. Childs Nerv Syst 26(2):185–190
Nucifora PGP, Verma R, Lee SK et al (2007) Diffusion-tensor MR imaging and tractography: exploring brain microstructure and connectivity. Radiology 245(2):367–84
Lee MH, Smyser CD, Shimony JS (2013) Resting-state fMRI: a review of methods and clinical applications. Am J Neuroradiol 34(10):1866–1872
Acknowledgments
This research was supported by the Natural Science Foundation of China (Grant No: 61075107), the Special Project of Clinical medical science and technology in Jiangsu Province (BL201204).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wu, J., Qian, Z., Tao, L. et al. Resting state fMRI feature-based cerebral glioma grading by support vector machine. Int J CARS 10, 1167–1174 (2015). https://doi.org/10.1007/s11548-014-1111-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-014-1111-z