Abstract
Objective
To differentiate brain pilocytic astrocytoma (PA) from glioblastoma (GBM) using contrast-enhanced magnetic resonance imaging (MRI) quantitative radiomic features by a decision tree model.
Methods
Sixty-six patients from two centres (PA, n = 31; GBM, n = 35) were randomly divided into training and validation data sets (about 2:1). Quantitative radiomic features of the tumours were extracted from contrast-enhanced MR images. A subset of features was selected by feature stability and Boruta algorithm. The selected features were used to build a decision tree model. Predictive accuracy, sensitivity and specificity were used to assess model performance. The classification outcome of the model was combined with tumour location, age and gender features, and multivariable logistic regression analysis and permutation test using the entire data set were performed to further evaluate the decision tree model.
Results
A total of 271 radiomic features were successfully extracted for each tumour. Twelve features were selected as input variables to build the decision tree model. Two features S(1, -1) Entropy and S(2, -2) SumAverg were finally included in the model. The model showed an accuracy, sensitivity and specificity of 0.87, 0.90 and 0.83 for the training data set and 0.86, 0.80 and 0.91 for the validation data set. The classification outcome of the model related to the actual tumour types and did not rely on the other three features (p < 0.001).
Conclusions
A decision tree model with two features derived from the contrast-enhanced MR images performed well in differentiating PA from GBM.
Key Points
• MRI findings of PA and GBM are sometimes very similar.
• Radiomics provides much more quantitative information about tumours.
• Radiomic features can help to distinguish PA from GBM.
Similar content being viewed by others
Abbreviations
- CI:
-
Confidence interval
- CNS:
-
Central nervous system
- CP:
-
Complexity parameter
- GBM:
-
Glioblastoma
- ICC:
-
Intraclass correlation coefficient
- MRI:
-
Magnetic resonance imaging
- PA:
-
Pilocytic astrocytoma
- ROI:
-
Regions of interest
- SD:
-
Standard deviation
References
Gaudino S, Martucci M, Russo R et al (2017) MR imaging of brain pilocytic astrocytoma: beyond the stereotype of benign astrocytoma. Childs Nerv Syst 33:35–54
Thorne AH, Zanca C, Furnari F (2016) Epidermal growth factor receptor targeting and challenges in glioblastoma. Neuro Oncol 18:914–918
Alifieris C, Trafalis DT (2015) Glioblastoma multiforme: pathogenesis and treatment. Pharmacol Ther 152:63–82
Alford R, Gargan L, Bowers DC, Klesse LJ, Weprin B, Koral K (2016) Postoperative surveillance of pediatric cerebellar pilocytic astrocytoma. J Neurooncol 130:149–154
Cykowski MD, Allen RA, Kanaly AC et al (2013) The differential diagnosis of pilocytic astrocytoma with atypical features and malignant glioma: an analysis of 16 cases with emphasis on distinguishing molecular features. J Neurooncol 115:477–486
Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577
Yip SS, Aerts HJ (2016) Applications and limitations of radiomics. Phys Med Biol 61:R150–R166
Rau CS, Wu SC, Chien PC et al (2018) Identification of pancreatic injury in patients with elevated amylase or lipase level using a decision tree classifier: a cross-sectional retrospective analysis in a level I trauma center. Int J Environ Res Public Health. https://doi.org/10.3390/ijerph15020277
El Hentour K, Millet I, Pages-Bouic E, Curros-Doyon F, Molinari N, Taourel P (2018) How to differentiate acute pelvic inflammatory disease from acute appendicitis ? A decision tree based on CT findings. Eur Radiol 28:673–682
Zimmerman RK, Balasubramani GK, Nowalk MP et al (2016) Classification and regression tree (CART) analysis to predict influenza in primary care patients. BMC Infect Dis 16:503
Strzelecki M, Szczypinski P, Materka A, Klepaczko A (2013) A software tool for automatic classification and segmentation of 2D/3D medical images. Nucl Instrum Methods Phys Res 702:137–140
Szczypiński PM, Strzelecki M, Materka A, Klepaczko A (2009) MaZda–a software package for image texture analysis. Comput Methods Programs Biomed 94:66–76
Szczypiński PM, Strzelecki M, Materka A (2007) MaZda–a software for texture analysis. Proc of ISITC, Republic of Korea, p 245–249
Baessler B, Mannil M, Oebel S, Maintz D, Alkadhi H, Manka R (2018) Subacute and chronic left ventricular myocardial scar: accuracy of texture analysis on nonenhanced cine MR images. Radiology 286:103–112
Yuan M, Zhang YD, Pu XH et al (2017) Comparison of a radiomic biomarker with volumetric analysis for decoding tumour phenotypes of lung adenocarcinoma with different disease-specific survival. Eur Radiol 27:4857–4865
Kursa MB, Rudnicki WR (2010) Feature selection with the Boruta package. J Stat Softw 36:1–13
Khalkhali HR, Lotfnezhad Afshar H, Esnaashari O, Jabbari N (2016) Applying data mining techniques to extract hidden patterns about breast cancer survival in an Iranian cohort study. J Res Health Sci 16:31–35
Tempany CM, Zou KH, Silverman SG, Brown DL, Kurtz AB, McNeil BJ (2000) Staging of advanced ovarian cancer: comparison of imaging modalities–report from the Radiological Diagnostic Oncology Group. Radiology 215:761–767
Collins VP, Jones DT, Giannini C (2015) Pilocytic astrocytoma: pathology, molecular mechanisms and markers. Acta Neuropathol 129:775–788
Sato K, Rorke LB (1989) Vascular bundles and wickerworks in childhood brain tumors. Pediatr Neurosci 15:105–110
Smirniotopoulos JG, Murphy FM, Rushing EJ, Rees JH, Schroeder JW (2007) Patterns of contrast enhancement in the brain and meninges. Radiographics 27:525–551
Aldape K, Zadeh G, Mansouri S, Reifenberger G, von Deimling A (2015) Glioblastoma: pathology, molecular mechanisms and markers. Acta Neuropathol 129:829–848
Crespo I, Vital AL, Gonzalez-Tablas M et al (2015) Molecular and genomic alterations in glioblastoma multiforme. Am J Pathol 185:1820–1833
Wirsching HG, Galanis E, Weller M (2016) Glioblastoma. Handb Clin Neurol 134:381–397
Johnson DR, Brown PD, Galanis E, Hammack JE (2012) Pilocytic astrocytoma survival in adults: analysis of the Surveillance, Epidemiology, and End Results Program of the National Cancer Institute. J Neurooncol 108:187–193
Cyrine S, Sonia Z, Mounir T et al (2013) Pilocytic astrocytoma: a retrospective study of 32 cases. Clin Neurol Neurosurg 115:1220–1225
Murray RD, Penar PL, Filippi CG, Tarasiewicz I (2011) Radiographically distinct variant of pilocytic astrocytoma: a case series. J Comput Assist Tomogr 35:495–497
Zhou M, Scott J, Chaudhury B et al (2018) Radiomics in brain tumor: image assessment, quantitative feature descriptors, and machine-learning approaches. AJNR Am J Neuroradiol 39:208–216
Narang S, Lehrer M, Yang D, Lee J, Rao A (2016) Radiomics in glioblastoma: current status, challenges and potential opportunities. Transl Cancer Res 5:383–397
Avanzo M, Stancanello J, El Naqa I (2017) Beyond imaging: the promise of radiomics. Phys Med 38:122–139
Shofty B, Artzi M, Ben Bashat D et al (2018) MRI radiomics analysis of molecular alterations in low-grade gliomas. Int J Comput Assist Radiol Surg 13:563–571
Li ZC, Bai H, Sun Q et al (2018) Multiregional radiomics features from multiparametric MRI for prediction of MGMT methylation status in glioblastoma multiforme: a multicentre study. Eur Radiol. https://doi.org/10.1007/s00330-017-5302-1
Zhang Z, Yang J, Ho A et al (2018) A predictive model for distinguishing radiation necrosis from tumour progression after gamma knife radiosurgery based on radiomic features from MR images. Eur Radiol 28:2255–2263
Li Y, Liu X, Qian Z et al (2018) Genotype prediction of ATRX mutation in lower-grade gliomas using an MRI radiomics signature. Eur Radiol 28:2960–2968
Zhang X, Tian Q, Wang L et al (2018) Radiomics strategy for molecular subtype stratification of lower-grade glioma: detecting IDH and TP53 Mutations based on multimodal MRI. J Magn Reson Imaging. https://doi.org/10.1002/jmri.25960
Prasanna P, Tiwari P, Madabhushi A (2014) Co-occurrence of local anisotropic gradient orientations (CoLIAGe): distinguishing tumor confounders and molecular subtypes on MRI. Med Image Comput Comput Assist Interv 17:73–80
Funding
This study has received funding by the medicine and health scientific and technological program of Zhejiang province, China (2016KYA104 and 2017KY374)
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Guarantor
The scientific guarantor of this publication is Minming Zhang.
Conflict of interest
The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.
Statistics and biometry
One of the authors has significant statistical expertise.
Informed consent
Written informed consent was not required for this study because this is a retrospective study on the images.
Ethical approval
Institutional review board approval was obtained.
Methodology
• retrospective
• diagnostic or prognostic study
• multicentre study
Rights and permissions
About this article
Cite this article
Dong, F., Li, Q., Xu, D. et al. Differentiation between pilocytic astrocytoma and glioblastoma: a decision tree model using contrast-enhanced magnetic resonance imaging-derived quantitative radiomic features. Eur Radiol 29, 3968–3975 (2019). https://doi.org/10.1007/s00330-018-5706-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-018-5706-6