Classification of brain stem glioma tumor grade based on MRI findings using support vector machine

authors:

avatar Zahra zolghadr , avatar Hamid Alavi Majd , * , avatar Fariborz Faeghi , avatar Farhad Niaghi , avatar Nastaran Hajizadeh


how to cite: zolghadr Z, Alavi Majd H, Faeghi F, Niaghi F, Hajizadeh N. Classification of brain stem glioma tumor grade based on MRI findings using support vector machine. koomesh. 2017;19(3):e152904. 

Abstract

Introduction: Brain stem glioma is one of the brain tumors forming 10 to 20 percentages of tumors in children and 2 percentages of tumors in adults. It has two grades including high grade and low grade. Relatively, grade diagnosis is done by biopsy. The goal of this study is presenting a classification model based on MRI findings in order to diagnose glioma tumor and also investigating the effect of MRI findings on tumor’s grade. Materials and Methods: In this cross-sectional study, we utilized MRI and pathological information of all 96 patients with glioma tumor in stereotactic biopsy ward of Shohadaye Tajrish hospital (Iran) between 2006-2012. For analysis of data, support vector machine as a precise classification model has fitted which is suitable for dataset with vast predictors or several class variables with low frequencies in some of them. This model has fitted in R software, 3.3.1 version. Results: The validation shows 93 percent total accuracy, 90 percent sensitivity and 93 percent specifity of support vector machine classifier model. Notably, the coefficients show positive correlation between headache, tumor spread in cord, homogeneous appearance, Cystlike appearance, ISO signal in T1 and T2 and low grade tumor and positive correlation between pons conflict, Tumor spread in thalamus, well defined appearance, necrosis appearance, hypersignal in T2 and heterogeneous enhancement with high grade tumor. Conclusion: Support vector machine classification model based on MRI has high accuracy in tumor grade diagnosis.

References

  • 1.

    Farwell JR, Dohrmann GJ, Flannery JT. Central nervous system tumors in children cns tumors in children. Cancer 1977; 40: 3123-3132.

  • 2.

    Donaldson SS, Laningham F, Fisher PG. Advances toward an understanding of brainstem gliomas. J Clin Oncol 2006; 24: 1266-1272.

  • 3.

    White HH. Brain stem tumors occurring in adults. Neurology 1963; 13: 292-300.

  • 4.

    Hargrave D, Bartels U, Bouffet E. Diffuse brainstem glioma in children: critical review of clinical trials. Lancet Oncol 2006; 7: 241-248.

  • 5.

    Jallo GI, Biser-Rohrbaugh A, Freed D. Brainstem gliomas. Childs Nerv Syst 2004; 20: 143-153.

  • 6.

    Guillamo JS, Monjour A, Taillandier L, Devaux B, Varlet P, Haie-Meder C, et al. Brainstem gliomas in adults: prognostic factors and classification. Brain 2001; 124: 2528-2539.

  • 7.

    States CBTRotU. Statistical report: primary brain tumors in the United States, 19982002. Hinsdale (Illinois): Central Brain Tumor Registry of the United States 2002.

  • 8.

    Fountas KN, Kapsalaki EZ, Gotsis SD, Kapsalakis JZ, Smisson Iii HF, Johnston KW, et al. In vivo proton magnetic resonance spectroscopy of brain tumors. Stereotact Funct Neurosurg 2000; 74: 83-94.

  • 9.

    Furuya S, Naruse S, Ide M, Morishita H, Kizu O, Ueda S, Maeda T. Evaluation of metabolic heterogeneity in brain tumors using 1Hchemical shift imaging method. NMR Biomed 1997; 10: 25-30.

  • 10.

    Hagberg G. From magnetic resonance spectroscopy to classification of tumors. A review of pattern recognition methods. NMR Biomed 1998; 11: 148-156.

  • 11.

    McKnight TR, Noworolski SM, Vigneron DB, rer Nat ND, Sarah J. An automated technique for the quantitative assessment of 3DMRSI data from patients with glioma. J Magn Reson Imaging 2001; 13: 167-177.

  • 12.

    Tate AR, Majs C, Moreno A, Howe FA, Griffiths JR, Ars C. Automated classification of short echo time in in vivo 1H brain tumor spectra: a multicenter study. Magn Reson Med 2003; 49: 29-36.

  • 13.

    Nishihara M, Sasayama T, Kudo H, Kohmura E. Morbidity of stereotactic biopsy for intracranial lesions. Kobe J Med Sci 2011; 56: E148-153.

  • 14.

    Parida S, Dehuri S. Review of fMRI Data Analysis: A Special Focus on Classification. Int J E-Health Med Commun 2014; 5: 1-26.

  • 15.

    Sanie Abadeh M, Mahmoodi S, Taherparvar M. Practical Data Mining. 2th ed. Tehran: Niaze Danesh; 2014.

  • 16.

    Montazeri MA, Mahdieh. Machine learning models for predicting the diagnosis of liver disease. Koomesh 2014; 16: 53-59.

  • 17.

    Zacharaki EI, Wang S, Chawla S, Soo Yoo D, Wolf R, Melhem ER, Davatzikos C. Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn Reson Med 2009; 62: 1609-1618.

  • 18.

    Mahshid N. Development of fuzzy regression models with categorical response data and it's application in medical studies [PhD dissertation]. School of Allied Medical Sciences. Shahid Beheshti Univ Med Sci 2013. (Persian).

  • 19.

    Farhad N. Assessment of Correlation between MRI findings of Brain stem Glioma and its histopathological grade [PhD dissertation]. School of Medicine. Shahid Beheshti Univ Med Sci 2012. (Persian).

  • 20.

    Chen K, Wang L. Trends in neural computation: Springer; 2006.

  • 21.

    Nitta T, Sato K. [A clinicopathological study of nine cases of midbrain glioma]. No Shinkei Geka 1995; 23: 405-410.##.