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

다국어 초록 (Multilingual Abstract)

ObjectiveTo 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 MethodsTwo-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.
ResultsThe 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).
ConclusionRadiomics 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.

참고문헌 (Reference)

1 Park YW, "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" 39 : 693-698, 2018

2 Hilario A, "The added value of apparent diffusion coefficient to cerebral blood volume in the preoperative grading of diffuse gliomas" 33 : 701-707, 2012

3 Louis DN, "The 2016 World Health Organization classification of tumors of the central nervous system: a summary" 131 : 803-820, 2016

4 Yu X, "Stereotactic biopsy for intracranial space-occupying lesions: clinical analysis of 550 cases" 75 : 103-108, 2000

5 Shinohara RT, "Statistical normalization techniques for magnetic resonance imaging" 6 : 9-19, 2014

6 Chawla NV, "SMOTE:synthetic minority over-sampling technique" 16 : 321-357, 2002

7 Kickingereder P, "Radiomic profiling of glioblastoma: identifying an imaging predictor of patient survival with improved performance over established clinical and radiologic risk models" 280 : 880-889, 2016

8 이명은, "Quality of Radiomic Features in Glioblastoma Multiforme: Impact of Semi-Automated Tumor Segmentation Software" 대한영상의학회 18 (18): 498-509, 2017

9 Lee EJ, "Preoperative grading of presumptive low-grade astrocytomas on MR imaging: diagnostic value of minimum apparent diffusion coefficient" 29 : 1872-1877, 2008

10 Stadlbauer A, "Preoperative grading of gliomas by using metabolite quantification with high-spatial-resolution proton MR spectroscopic imaging" 238 : 958-969, 2006

11 Wong JC, "Perfusion MR imaging of brain neoplasms" 174 : 1147-1157, 2000

12 SungKiCho, "Perfusion MR Imaging: Clinical Utility for the Differential Diagnosis of Various Brain Tumors" 대한영상의학회 3 (3): 4-179, 2002

13 Yu J, "Noninvasive IDH1 mutation estimation based on a quantitative radiomics approach for grade II glioma" 27 : 3509-3522, 2017

14 Mihara F, "Non-enhancing supratentorial malignant astrocytomas: MR features and possible mechanisms" 13 : 11-17, 1995

15 Killela PJ, "Mutations in IDH1, IDH2, and in the TERT promoter define clinically distinct subgroups of adult malignant gliomas" 5 : 1515-1525, 2014

16 Ceccarelli M, "Molecular profiling reveals biologically discrete subsets and pathways of progression in diffuse glioma" 164 : 550-563, 2016

17 Zhou H, "MRI features predict survival and molecular markers in diffuse lower-grade gliomas" 19 : 862-870, 2017

18 Tynninen O, "MRI enhancement and microvascular density in gliomas. Correlation with tumor cell proliferation" 34 : 427-434, 1999

19 Liu X, "MR diffusion tensor and perfusion-weighted imaging in preoperative grading of supratentorial nonenhancing gliomas" 13 : 447-455, 2011

20 Maia AC Jr, "MR cerebral blood volume maps correlated with vascular endothelial growth factor expression and tumor grade in nonenhancing gliomas" 26 : 777-783, 2005

21 van den Bent MJ, "Interobserver variation of the histopathological diagnosis in clinical trials on glioma: a clinician’s perspective" 120 : 297-304, 2010

22 Kim JY, "Incorporating diffusion- and perfusion-weighted MRI into a radiomics model improves diagnostic performance for pseudoprogression in glioblastoma patients" 21 : 404-414, 2019

23 Olar A, "IDH mutation status and role of WHO grade and mitotic index in overall survival in grade II-III diffuse gliomas" 129 : 585-596, 2015

24 Reuss DE, "IDH mutant diffuse and anaplastic astrocytomas have similar age at presentation and little difference in survival: a grading problem for WHO" 129 : 867-873, 2015

25 Scott JN, "How often are nonenhancing supratentorial gliomas malignant? A population study" 59 : 947-949, 2002

26 Takano K, "Diagnostic and prognostic value of 11C-methionine PET for nonenhancing gliomas" 37 : 44-50, 2016

27 Butler AR, "Computed tomography in astrocytomas. A statistical analysis of the parameters of malignancy and the positive contrastenhanced CT scan" 129 : 433-439, 1978

28 van Griethuysen JJM, "Computational radiomics system to decode the radiographic phenotype" 77 : e104-e107, 2017

29 Cancer Genome Atlas Research Network, "Comprehensive, integrative genomic analysis of diffuse lowergrade gliomas" 372 : 2481-2498, 2015

30 Field M, "Comprehensive assessment of hemorrhage risks and outcomes after stereotactic brain biopsy" 94 : 545-551, 2001

31 Lüdemann L, "Comparison of dynamic contrast-enhanced MRI with WHO tumor grading for gliomas" 11 : 1231-1241, 2001

32 Rollin N, "Clinical relevance of diffusion and perfusion magnetic resonance imaging in assessing intra-axial brain tumors" 48 : 150-159, 2006

33 White ML, "Can tumor contrast enhancement be used as a criterion for differentiating tumor grades of oligodendrogliomas?" 26 : 784-790, 2005

34 Kuhn M, "Building predictive models in R using the caret package" 28 : 1-26, 2008

35 Davnall F, "Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice?" 3 : 573-589, 2012

36 Barker FG 2nd, "Age and the risk of anaplasia in magnetic resonance-nonenhancing supratentorial cerebral tumors" 80 : 936-941, 1997

37 Bakas S, "Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features" 4 : 170117-, 2017

38 Feiden W, "Accuracy of stereotactic brain tumor biopsy: comparison of the histologic findings in biopsy cylinders and resected tumor tissue" 14 : 51-56, 1991