Classification of Brain Tumor Type and Grade Using MRI Texture and Shape in a Machine Learning Scheme

Overview

Journal Magn Reson Med

Publisher Wiley

Specialty Radiology

Date 2009 Oct 28

PMID 19859947

Citations 197

Authors

Evangelia I Zacharaki

Sumei Wang

Sanjeev Chawla

Dong Soo Yoo

Ronald Wolf

Elias R Melhem

Christos Davatzikos

Affiliations

Soon will be listed here.

Abstract

The objective of this study is to investigate the use of pattern classification methods for distinguishing different types of brain tumors, such as primary gliomas from metastases, and also for grading of gliomas. The availability of an automated computer analysis tool that is more objective than human readers can potentially lead to more reliable and reproducible brain tumor diagnostic procedures. A computer-assisted classification method combining conventional MRI and perfusion MRI is developed and used for differential diagnosis. The proposed scheme consists of several steps including region-of-interest definition, feature extraction, feature selection, and classification. The extracted features include tumor shape and intensity characteristics, as well as rotation invariant texture features. Feature subset selection is performed using support vector machines with recursive feature elimination. The method was applied on a population of 102 brain tumors histologically diagnosed as metastasis (24), meningiomas (4), gliomas World Health Organization grade II (22), gliomas World Health Organization grade III (18), and glioblastomas (34). The binary support vector machine classification accuracy, sensitivity, and specificity, assessed by leave-one-out cross-validation, were, respectively, 85%, 87%, and 79% for discrimination of metastases from gliomas and 88%, 85%, and 96% for discrimination of high-grade (grades III and IV) from low-grade (grade II) neoplasms. Multiclass classification was also performed via a one-vs-all voting scheme.

Citing Articles

Simplifying Radiomics Workflow for Predicting Grade of Glioma: An Approach for Rapid and Reproducible Radiomics.

Soleymani Y, Sheikhzadeh P, Mohammadzadeh M, Khezerloo D J Biomed Phys Eng. 2025; 15(1):27-36.

PMID: 39975526 PMC: 11833161. DOI: 10.31661/jbpe.v0i0.2208-1525.

AI-guided virtual biopsy: Automated differentiation of cerebral gliomas from other benign and malignant MRI findings using deep learning.

Holtkamp M, Parmar V, Hosch R, Salhofer L, Styczen H, Li Y Neurooncol Adv. 2025; 7(1):vdae225.

PMID: 39877747 PMC: 11773384. DOI: 10.1093/noajnl/vdae225.

Enhanced brain tumor diagnosis using combined deep learning models and weight selection technique.

Gasmi K, Ben Aoun N, Alsalem K, Ltaifa I, Alrashdi I, Ben Ammar L Front Neuroinform. 2024; 18:1444650.

PMID: 39659489 PMC: 11628532. DOI: 10.3389/fninf.2024.1444650.

Evaluation of an Image-based Classification Model to Identify Glioma Subtypes Using Arterial Spin Labeling Perfusion MRI On the Publicly Available UCSF Glioma Dataset.

Amador K, Kniep H, Fiehler J, Forkert N, Lindner T Clin Neuroradiol. 2024; 35(1):151-158.

PMID: 39419847 DOI: 10.1007/s00062-024-01465-5.

A Comprehensive Review on the Role of MRI in the Assessment of Supratentorial Neoplasms: Comparative Insights Into Adult and Pediatric Cases.

Bhangale P, Kashikar S, Kasat P, Shrivastava P, Kumari A Cureus. 2024; 16(8):e67553.

PMID: 39310617 PMC: 11416707. DOI: 10.7759/cureus.67553.

References

SELBY D, WOODARD C, Henry M, Bernstein J . Are endothelial cell patterns of astrocytomas indicative of grade?. In Vivo. 1998; 11(5):371-5. View

Emblem K, Zoellner F, Tennoe B, Nedregaard B, Nome T, Due-Tonnessen P . Predictive modeling in glioma grading from MR perfusion images using support vector machines. Magn Reson Med. 2008; 60(4):945-52. DOI: 10.1002/mrm.21736. View

Goldbrunner R, Pietsch T, Vince G, Bernstein J, Wagner S, Hageman H . Different vascular patterns of medulloblastoma and supratentorial primitive neuroectodermal tumors. Int J Dev Neurosci. 1999; 17(5-6):593-9. DOI: 10.1016/s0736-5748(99)00025-8. View

Zacharaki E, Hogea C, Shen D, Biros G, Davatzikos C . Non-diffeomorphic registration of brain tumor images by simulating tissue loss and tumor growth. Neuroimage. 2009; 46(3):762-74. PMC: 2929986. DOI: 10.1016/j.neuroimage.2009.01.051. View

Mayerhoefer M, Szomolanyi P, Jirak D, Materka A, Trattnig S . Effects of MRI acquisition parameter variations and protocol heterogeneity on the results of texture analysis and pattern discrimination: an application-oriented study. Med Phys. 2009; 36(4):1236-43. DOI: 10.1118/1.3081408. View

Majos C, Julia-Sape M, Alonso J, Serrallonga M, Aguilera C, Acebes J . Brain tumor classification by proton MR spectroscopy: comparison of diagnostic accuracy at short and long TE. AJNR Am J Neuroradiol. 2004; 25(10):1696-704. PMC: 8148728. View

Smith S, Jenkinson M, Woolrich M, Beckmann C, Behrens T, Johansen-Berg H . Advances in functional and structural MR image analysis and implementation as FSL. Neuroimage. 2004; 23 Suppl 1:S208-19. DOI: 10.1016/j.neuroimage.2004.07.051. View

Provenzale J, Mukundan S, Barboriak D . Diffusion-weighted and perfusion MR imaging for brain tumor characterization and assessment of treatment response. Radiology. 2006; 239(3):632-49. DOI: 10.1148/radiol.2393042031. View

Lu C, Devos A, Suykens J, Arus C, Van Huffel S . Bagging linear sparse Bayesian learning models for variable selection in cancer diagnosis. IEEE Trans Inf Technol Biomed. 2007; 11(3):338-47. DOI: 10.1109/titb.2006.889702. View

10.

Georgiadis P, Cavouras D, Kalatzis I, Daskalakis A, Kagadis G, Sifaki K . Improving brain tumor characterization on MRI by probabilistic neural networks and non-linear transformation of textural features. Comput Methods Programs Biomed. 2007; 89(1):24-32. DOI: 10.1016/j.cmpb.2007.10.007. View

11.

Verma R, Zacharaki E, Ou Y, Cai H, Chawla S, Lee S . Multiparametric tissue characterization of brain neoplasms and their recurrence using pattern classification of MR images. Acad Radiol. 2008; 15(8):966-77. PMC: 2596598. DOI: 10.1016/j.acra.2008.01.029. View

12.

Tate A, Majos C, Moreno A, Howe F, Griffiths J, Arus C . Automated classification of short echo time in in vivo 1H brain tumor spectra: a multicenter study. Magn Reson Med. 2003; 49(1):29-36. DOI: 10.1002/mrm.10315. View

13.

Ambroise C, McLachlan G . Selection bias in gene extraction on the basis of microarray gene-expression data. Proc Natl Acad Sci U S A. 2002; 99(10):6562-6. PMC: 124442. DOI: 10.1073/pnas.102102699. View

14.

Kruizinga P, Petkov N . Nonlinear operator for oriented texture. IEEE Trans Image Process. 2008; 8(10):1395-407. DOI: 10.1109/83.791965. View

15.

Krabbe K, Gideon P, Wagn P, Hansen U, Thomsen C, Madsen F . MR diffusion imaging of human intracranial tumours. Neuroradiology. 1997; 39(7):483-9. DOI: 10.1007/s002340050450. View

16.

Cho Y, Choi G, Lee S, Kim J . (1)H-MRS metabolic patterns for distinguishing between meningiomas and other brain tumors. Magn Reson Imaging. 2003; 21(6):663-72. DOI: 10.1016/s0730-725x(03)00097-3. View

17.

Lev M, Ozsunar Y, Henson J, Rasheed A, Barest G, Harsh 4th G . Glial tumor grading and outcome prediction using dynamic spin-echo MR susceptibility mapping compared with conventional contrast-enhanced MR: confounding effect of elevated rCBV of oligodendrogliomas [corrected]. AJNR Am J Neuroradiol. 2004; 25(2):214-21. PMC: 7974605. View

18.

Daugman J . Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. J Opt Soc Am A. 1985; 2(7):1160-9. DOI: 10.1364/josaa.2.001160. View

19.

Kremer S, Grand S, Remy C, Esteve F, Lefournier V, Pasquier B . Cerebral blood volume mapping by MR imaging in the initial evaluation of brain tumors. J Neuroradiol. 2002; 29(2):105-13. View

20.

Glotsos D, Tohka J, Ravazoula P, Cavouras D, Nikiforidis G . Automated diagnosis of brain tumours astrocytomas using probabilistic neural network clustering and support vector machines. Int J Neural Syst. 2005; 15(1-2):1-11. DOI: 10.1142/S0129065705000013. View