Korean J Radiol.  2019 Sep;20(9):1381-1389. 10.3348/kjr.2018.0814.

Radiomics MRI Phenotyping with Machine Learning to Predict the Grade of Lower-Grade Gliomas: A Study Focused on Nonenhancing Tumors

• Park YW
• Choi YS
• Ahn SS
• Chang JH
• Kim SH
• Lee SK

• KMID: 2455766
• DOI: http://doi.org/10.3348/kjr.2018.0814

Abstract

OBJECTIVE
To assess whether radiomics features derived from multiparametric MRI can predict the tumor grade of lower-grade gliomas (LGGs; World Health Organization grade II and grade III) and the nonenhancing LGG subgroup.
MATERIALS AND METHODS
Two-hundred four patients with LGGs from our institutional cohort were allocated to training (n = 136) and test (n = 68) sets. Postcontrast T1-weighted images, T2-weighted images, and fluid-attenuated inversion recovery images were analyzed to extract 250 radiomics features. Various machine learning classifiers were trained using the radiomics features to predict the glioma grade. The trained classifiers were internally validated on the institutional test set and externally validated on a separate cohort (n = 99) from The Cancer Genome Atlas (TCGA). Classifier performance was assessed by determining the area under the curve (AUC) from receiver operating characteristic curve analysis. An identical process was performed in the nonenhancing LGG subgroup (institutional training set, n = 73; institutional test set, n = 37; and TCGA cohort, n = 37) to predict the glioma grade.
RESULTS
The performance of the best classifier was good in the internal validation set (AUC, 0.85) and fair in the external validation set (AUC, 0.72) to predict the LGG grade. For the nonenhancing LGG subgroup, the performance of the best classifier was good in the internal validation set (AUC, 0.82), but poor in the external validation set (AUC, 0.68).
CONCLUSION
Radiomics feature-based classifiers may be useful to predict LGG grades. However, radiomics classifiers may have a limited value when applied to the nonenhancing LGG subgroup in a TCGA cohort.

Keyword

Grade; Lower-grade glioma; Magnetic resonance imaging; Radiomics; The Cancer Genome Atlas

MeSH Terms

Cohort Studies
Genome
Glioma*
Humans
Machine Learning*
Magnetic Resonance Imaging*
ROC Curve
World Health Organization

Figure

• 

  Fig. 1 Patient enrollment process for entire LGG group and nonenhancing LGG subgroup in (A) institutional cohort and (B) TCGA cohort.FLAIR = fluid-attenuated inversion recovery, LGG = lower-grade glioma, TCGA = The Cancer Genome Atlas, TCIA = The Cancer Imaging Archive, T1C = contrast-enhanced T1-weighted

• 

  Fig. 2 Workflow of image processing, radiomics feature extraction, and machine learning.GLCM = gray level co-occurrence matrix, GLRLM = gray level run-length matrix, GLSZM = gray level size zone matrix, ROC = receiver operating characteristic

• 

  Fig. 3 Heatmap of AUC values.Heat map of AUC values from machine learning classifier to predict grade (A) in entire LGG group in internal validation for institutional test set (n = 136) after training on institutional training set (n = 68) and entire LGG group in external validation for TCGA validation set (n = 99) after training on entire institutional cohort (n = 204); and (B) in nonenhancing LGG subgroup in internal validation for institutional test set (n = 73) after training on institutional training set (n = 37) and nonenhancing LGG subgroup in external validation on TCGA cohort (n = 37) after training on entire nonenhancing institutional cohort (n = 110). AUC = area under curve, GBM = gradient boosting machine, LDA = linear discriminant analysis, RF = random forest, RFE = recursive feature elimination, ROSE = random over-sampling examples, SMOTE = synthetic minority over-sampling technique

Reference

1. Cancer Genome Atlas Research Network. Brat DJ, Verhaak RG, Aldape KD, Yung WK, Salama SR, Cooper LA, et al. Comprehensive, integrative genomic analysis of diffuse lower-grade gliomas. N Engl J Med. 2015; 372:2481–2498. PMID: 26061751.

2. Louis DN, Perry A, Reifenberger G, von Deimling A, Figarella-Branger D, Cavenee WK, et al. The 2016 World Health Organization classification of tumors of the central nervous system: a summary. Acta Neuropathol. 2016; 131:803–820. PMID: 27157931.

3. Rollin N, Guyotat J, Streichenberger N, Honnorat J, Tran Minh VA, Cotton F. Clinical relevance of diffusion and perfusion magnetic resonance imaging in assessing intra-axial brain tumors. Neuroradiology. 2006; 48:150–159. PMID: 16470375.

4. Lee EJ, Lee SK, Agid R, Bae JM, Keller A, Terbrugge K. Preoperative grading of presumptive low-grade astrocytomas on MR imaging: diagnostic value of minimum apparent diffusion coefficient. AJNR Am J Neuroradiol. 2008; 29:1872–1877. PMID: 18719036.

5. Olar A, Wani KM, Alfaro-Munoz KD, Heathcock LE, van Thuijl HF, Gilbert MR, et al. IDH mutation status and role of WHO grade and mitotic index in overall survival in grade II–III diffuse gliomas. Acta Neuropathol. 2015; 129:585–596. PMID: 25701198.

6. Reuss DE, Mamatjan Y, Schrimpf D, Capper D, Hovestadt V, Kratz A, et al. IDH mutant diffuse and anaplastic astrocytomas have similar age at presentation and little difference in survival: a grading problem for WHO. Acta Neuropathol. 2015; 129:867–873. PMID: 25962792.

7. Killela PJ, Pirozzi CJ, Healy P, Reitman ZJ, Lipp E, Rasheed BA, et al. Mutations in IDH1, IDH2, and in the TERT promoter define clinically distinct subgroups of adult malignant gliomas. Oncotarget. 2014; 5:1515–1525. PMID: 24722048.

8. Wong JC, Provenzale JM, Petrella JR. Perfusion MR imaging of brain neoplasms. AJR Am J Roentgenol. 2000; 174:1147–1157. PMID: 10749268.

9. Cho SK, Na DG, Ryoo JW, Roh HG, Moon CH, Byun HS, et al. Perfusion MR imaging: clinical utility for the differential diagnosis of various brain tumors. Korean J Radiol. 2002; 3:171–179. PMID: 12271162.

10. Feiden W, Steude U, Bise K, Gündisch O. Accuracy of stereotactic brain tumor biopsy: comparison of the histologic findings in biopsy cylinders and resected tumor tissue. Neurosurg Rev. 1991; 14:51–56. PMID: 2030827.

11. Yu X, Liu Z, Tian Z, Li S, Huang H, Xiu B, et al. Stereotactic biopsy for intracranial space-occupying lesions: clinical analysis of 550 cases. Stereotact Funct Neurosurg. 2000; 75:103–108. PMID: 11740177.

12. Field M, Witham TF, Flickinger JC, Kondziolka D, Lunsford LD. Comprehensive assessment of hemorrhage risks and outcomes after stereotactic brain biopsy. J Neurosurg. 2001; 94:545–551. PMID: 11302651.

13. Takano K, Kinoshita M, Arita H, Okita Y, Chiba Y, Kagawa N, et al. Diagnostic and prognostic value of 11C-methionine PET for nonenhancing gliomas. AJNR Am J Neuroradiol. 2016; 37:44–50. PMID: 26381556.

14. Tynninen O, Aronen HJ, Ruhala M, Paetau A, Von Boguslawski K, Salonen O, et al. MRI enhancement and microvascular density in gliomas. Correlation with tumor cell proliferation. Invest Radiol. 1999; 34:427–443. PMID: 10353036.

15. Lüdemann L, Grieger W, Wurm R, Budzisch M, Hamm B, Zimmer C. Comparison of dynamic contrast-enhanced MRI with WHO tumor grading for gliomas. Eur Radiol. 2001; 11:1231–1241. PMID: 11471617.

16. Butler AR, Horii SC, Kricheff II, Shannon MB, Budzilovich GN. Computed tomography in astrocytomas. A statistical analysis of the parameters of malignancy and the positive contrast-enhanced CT scan. Radiology. 1978; 129:433–443. PMID: 212778.

17. White ML, Zhang Y, Kirby P, Ryken TC. Can tumor contrast enhancement be used as a criterion for differentiating tumor grades of oligodendrogliomas? AJNR Am J Neuroradiol. 2005; 26:784–790. PMID: 15814921.

18. Maia AC Jr, Malheiros SM, da Rocha AJ, da Silva CJ, Gabbai AA, Ferraz FA, et al. MR cerebral blood volume maps correlated with vascular endothelial growth factor expression and tumor grade in nonenhancing gliomas. AJNR Am J Neuroradiol. 2005; 26:777–783. PMID: 15814920.

19. Scott JN, Brasher PM, Sevick RJ, Rewcastle NB, Forsyth PA. How often are nonenhancing supratentorial gliomas malignant? A population study. Neurology. 2002; 59:947–994. PMID: 12297589.

20. Barker FG 2nd, Chang SM, Huhn SL, Davis RL, Gutin PH, McDermott MW, et al. Age and the risk of anaplasia in magnetic resonance-nonenhancing supratentorial cerebral tumors. Cancer. 1997; 80:936–941. PMID: 9307194.

21. Liu X, Tian W, Kolar B, Yeaney GA, Qiu X, Johnson MD, et al. MR diffusion tensor and perfusion-weighted imaging in preoperative grading of supratentorial nonenhancing gliomas. Neuro Oncol. 2011; 13:447–455. PMID: 21297125.

22. Davnall F, Yip CS, Ljungqvist G, Selmi M, Ng F, Sanghera B, et al. Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice? Insights Imaging. 2012; 3:573–589. PMID: 23093486.

23. Zhou H, Vallières M, Bai HX, Su C, Tang H, Oldridge D, et al. MRI features predict survival and molecular markers in diffuse lower-grade gliomas. Neuro Oncol. 2017; 19:862–870. PMID: 28339588.

24. Kickingereder P, Burth S, Wick A, Götz M, Eidel O, Schlemmer HP, et al. Radiomic profiling of glioblastoma: identifying an imaging predictor of patient survival with improved performance over established clinical and radiologic risk models. Radiology. 2016; 280:880–889. PMID: 27326665.

25. Ceccarelli M, Barthel FP, Malta TM, Sabedot TS, Salama SR, Murray BA, et al. Molecular profiling reveals biologically discrete subsets and pathways of progression in diffuse glioma. Cell. 2016; 164:550–563. PMID: 26824661.

26. Bakas S, Akbari H, Sotiras A, Bilello M, Rozycki M, Kirby JS, et al. Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci Data. 2017; 4:170117. PMID: 28872634.

27. Shinohara RT, Sweeney EM, Goldsmith J, Shiee N, Mateen FJ, Calabresi PA, et al. Australian Imaging Biomarkers Lifestyle Flagship Study of Ageing. Alzheimer's Disease Neuroimaging Initiative. Statistical normalization techniques for magnetic resonance imaging. Neuroimage Clin. 2014; 6:9–19. PMID: 25379412.

28. van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017; 77:e104–e107. PMID: 29092951.

29. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002; 16:321–357.

30. Kuhn M. Building predictive models in R using the caret package. J Stat Softw. 2008; 28:1–26. PMID: 27774042.

31. Hilario A, Ramos A, Perez-Nuñez A, Salvador E, Millan JM, Lagares A, et al. The added value of apparent diffusion coefficient to cerebral blood volume in the preoperative grading of diffuse gliomas. AJNR Am J Neuroradiol. 2012; 33:701–707. PMID: 22207304.

32. Stadlbauer A, Gruber S, Nimsky C, Fahlbusch R, Hammen T, Buslei R, et al. Preoperative grading of gliomas by using metabolite quantification with high-spatial-resolution proton MR spectroscopic imaging. Radiology. 2006; 238:958–969. PMID: 16424238.

33. Yu J, Shi Z, Lian Y, Li Z, Liu T, Gao Y, et al. Noninvasive IDH1 mutation estimation based on a quantitative radiomics approach for grade II glioma. Eur Radiol. 2017; 27:3509–3522. PMID: 28004160.

34. Park YW, Han K, Ahn SS, Choi YS, Chang JH, Kim SH, et al. Whole-tumor histogram and texture analyses of DTI for evaluation of IDH1-mutation and 1p/19q-codeletion status in World Health Organization grade II gliomas. AJNR Am J Neuroradiol. 2018; 39:693–698. PMID: 29519794.

35. Mihara F, Numaguchi Y, Rothman M, Kristt D, Fiandaca M, Swallow L. Non-enhancing supratentorial malignant astrocytomas: MR features and possible mechanisms. Radiat Med. 1995; 13:11–17. PMID: 7597198.

36. van den Bent MJ. Interobserver variation of the histopathological diagnosis in clinical trials on glioma: a clinician's perspective. Acta Neuropathol. 2010; 120:297–304. PMID: 20644945.

37. Kim JY, Park JE, Jo Y, Shim WH, Nam SJ, Kim JH, et al. Incorporating diffusion- and perfusion-weighted MRI into a radiomics model improves diagnostic performance for pseudoprogression in glioblastoma patients. Neuro Oncol. 2019; 21:404–414. PMID: 30107606.

38. Lee M, Woo B, Kuo MD, Jamshidi N, Kim JH. Quality of radiomic features in glioblastoma multiforme: impact of semi-automated tumor segmentation software. Korean J Radiol. 2017; 18:498–509. PMID: 28458602.