Classifying Glioblastoma Multiforme Follow-Up Progressive vs. Responsive Forms Using Multi-Parametric MRI Features

Purpose: The purpose of this paper is discriminating between tumor progression and response to treatment based on follow-up multi-parametric magnetic resonance imaging (MRI) data retrieved from glioblastoma multiforme (GBM) patients. Materials and Methods: Multi-parametric MRI data consisting of conventional MRI (cMRI) and advanced MRI [i.e., perfusion weighted MRI (PWI) and diffusion kurtosis MRI (DKI)] were acquired from 29 GBM patients treated with adjuvant therapy after surgery. We propose an automatic pipeline for processing advanced MRI data and extracting intensity-based histogram features and 3-D texture features using manually and semi-manually delineated regions of interest (ROIs). Classifiers are trained using a leave-one-patient-out cross validation scheme on complete MRI data. Balanced accuracy rate (BAR)–values are computed and compared between different ROIs, MR modalities, and classifiers, using non-parametric multiple comparison tests. Results: Maximum BAR–values using manual delineations are 0.956, 0.85, 0.879, and 0.932, for cMRI, PWI, DKI, and all three MRI modalities combined, respectively. Maximum BAR–values using semi-manual delineations are 0.932, 0.894, 0.885, and 0.947, for cMRI, PWI, DKI, and all three MR modalities combined, respectively. After statistical testing using Kruskal-Wallis and post-hoc Dunn-Šidák analysis we conclude that training a RUSBoost classifier on features extracted using semi-manual delineations on cMRI or on all MRI modalities combined performs best. Conclusions: We present two main conclusions: (1) using T1 post-contrast (T1pc) features extracted from manual total delineations, AdaBoost achieves the highest BAR–value, 0.956; (2) using T1pc-average, T1pc-90th percentile, and Cerebral Blood Volume (CBV) 90th percentile extracted from semi-manually delineated contrast enhancing ROIs, SVM-rbf, and RUSBoost achieve BAR–values of 0.947 and 0.932, respectively. Our findings show that AdaBoost, SVM-rbf, and RUSBoost trained on T1pc and CBV features can differentiate progressive from responsive GBM patients with very high accuracy.

[1]  Mayur Sharma,et al.  Updated response assessment criteria for high-grade glioma: beyond the MacDonald criteria. , 2017, Chinese clinical oncology.

[2]  Xiaobo Zhou,et al.  Pseudo progression identification of glioblastoma with dictionary learning , 2016, Comput. Biol. Medicine.

[3]  N. Magné,et al.  Identification of a candidate biomarker from perfusion MRI to anticipate glioblastoma progression after chemoradiation , 2016, European Radiology.

[4]  T. Kazda,et al.  The Diagnostic Ability of Follow-Up Imaging Biomarkers after Treatment of Glioblastoma in the Temozolomide Era: Implications from Proton MR Spectroscopy and Apparent Diffusion Coefficient Mapping , 2015, BioMed research international.

[5]  Sabine Van Huffel,et al.  Tumour Relapse Prediction Using Multiparametric MR Data Recorded during Follow-Up of GBM Patients , 2015, BioMed research international.

[6]  M. Siker,et al.  Evaluation of absolute and normalized apparent diffusion coefficient (ADC) values within the post-operative T2/FLAIR volume as adverse prognostic indicators in glioblastoma , 2015, Journal of Neuro-Oncology.

[7]  Sabine Van Huffel,et al.  Integrating diffusion kurtosis imaging, dynamic susceptibility-weighted contrast-enhanced MRI, and short echo time chemical shift imaging for grading gliomas. , 2014, Neuro-oncology.

[8]  S. Huffel,et al.  Integrating Diffusion Kurtosis Imaging , Dynamic Susceptibility-Weighted MR imaging and short echo time Chemical Shift Imaging for grading gliomas , 2014 .

[9]  G. Tedeschi,et al.  Recurrent glioblastoma multiforme versus radiation injury: a multiparametric 3-T MR approach , 2014, La radiologia medica.

[10]  C. Raftopoulos,et al.  Immediate post-operative MRI suggestive of the site and timing of glioblastoma recurrence after gross total resection: a retrospective longitudinal preliminary study , 2013, European Radiology.

[11]  J. Keller,et al.  Long-term survival of patients suffering from glioblastoma multiforme treated with tumor-treating fields , 2012, World Journal of Surgical Oncology.

[12]  Leland S. Hu,et al.  Reevaluating the imaging definition of tumor progression: perfusion MRI quantifies recurrent glioblastoma tumor fraction, pseudoprogression, and radiation necrosis to predict survival , 2012, Neuro-oncology.

[13]  Jan Sijbers,et al.  Gliomas: diffusion kurtosis MR imaging in grading. , 2012, Radiology.

[14]  B. Shadbolt,et al.  Increasing incidence of glioblastoma multiforme and meningioma, and decreasing incidence of Schwannoma (2000–2008): Findings of a multicenter Australian study , 2011, Surgical neurology international.

[15]  Stephen T. C. Wong,et al.  Support vector machine multiparametric MRI identification of pseudoprogression from tumor recurrence in patients with resected glioblastoma , 2011, Journal of magnetic resonance imaging : JMRI.

[16]  Víctor Urrea,et al.  Letter to the Editor: Stability of Random Forest importance measures , 2011, Briefings Bioinform..

[17]  Uwe Himmelreich,et al.  MR perfusion and diffusion imaging in the follow-up of recurrent glioblastoma treated with dendritic cell immunotherapy: a pilot study , 2011, Neuroradiology.

[18]  Susan M. Chang,et al.  Updated response assessment criteria for high-grade gliomas: response assessment in neuro-oncology working group. , 2010, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[19]  Eric Achten,et al.  Optimal Experimental Design for Diffusion Kurtosis Imaging , 2010, IEEE Transactions on Medical Imaging.

[20]  Jan Goffin,et al.  Integration of autologous dendritic cell-based immunotherapy in the primary treatment for patients with newly diagnosed glioblastoma multiforme: a pilot study , 2010, Journal of Neuro-Oncology.

[21]  J. Debbins,et al.  Optimized Preload Leakage-Correction Methods to Improve the Diagnostic Accuracy of Dynamic Susceptibility-Weighted Contrast-Enhanced Perfusion MR Imaging in Posttreatment Gliomas , 2010, American Journal of Neuroradiology.

[22]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[23]  M. Berger,et al.  Differentiation of recurrent glioblastoma multiforme from radiation necrosis after external beam radiation therapy with dynamic susceptibility-weighted contrast-enhanced perfusion MR imaging. , 2009, Radiology.

[24]  S. Van Cauter,et al.  Dendritic Cell Therapy of High‐Grade Gliomas , 2009, Brain pathology.

[25]  Taghi M. Khoshgoftaar,et al.  RUSBoost: Improving classification performance when training data is skewed , 2008, 2008 19th International Conference on Pattern Recognition.

[26]  Ed X. Wu,et al.  Towards better MR characterization of neural tissues using directional diffusion kurtosis analysis , 2008, NeuroImage.

[27]  R. Sciot,et al.  Postoperative Adjuvant Dendritic Cell–Based Immunotherapy in Patients with Relapsed Glioblastoma Multiforme , 2008, Clinical Cancer Research.

[28]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[29]  R M Weisskoff,et al.  Relative cerebral blood volume maps corrected for contrast agent extravasation significantly correlate with glioma tumor grade, whereas uncorrected maps do not. , 2006, AJNR. American journal of neuroradiology.

[30]  K. Schmainda,et al.  Using rCBV to Distinguish Radiation Necrosis from Tumor Recurrence in Malignant Gliomas , 2005 .

[31]  J. Helpern,et al.  Diffusional kurtosis imaging: The quantification of non‐gaussian water diffusion by means of magnetic resonance imaging , 2005, Magnetic resonance in medicine.

[32]  Zixiang Xiong,et al.  Optimal number of features as a function of sample size for various classification rules , 2005, Bioinform..

[33]  Martin J. van den Bent,et al.  Radiotherapy plus concomitant and adjuvant temozolomide for glioblastoma. , 2005, The New England journal of medicine.

[34]  P. Flamen,et al.  Surgery and adjuvant dendritic cell-based tumour vaccination for patients with relapsed malignant glioma, a feasibility study , 2004, British Journal of Cancer.

[35]  Rainer Breitling,et al.  Rank products: a simple, yet powerful, new method to detect differentially regulated genes in replicated microarray experiments , 2004, FEBS letters.

[36]  R. Sciot,et al.  Transient local response and persistent tumor control in a child with recurrent malignant glioma: treatment with combination therapy including dendritic cell therapy. Case report. , 2004, Journal of neurosurgery.

[37]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[38]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[39]  Marko Robnik-Sikonja,et al.  Overcoming the Myopia of Inductive Learning Algorithms with RELIEFF , 2004, Applied Intelligence.

[40]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[41]  J. Rees.  Advances in magnetic resonance imaging of brain tumours , 2003, Current opinion in neurology.

[42]  Chris H. Q. Ding,et al.  Minimum redundancy feature selection from microarray gene expression data , 2003, Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003.

[43]  Soonmee Cha,et al.  Imaging Glioblastoma Multiforme , 2003, Cancer journal.

[44]  Stephen M Smith,et al.  Fast robust automated brain extraction , 2002, Human brain mapping.

[45]  Sébastien Ourselin,et al.  Robust Registration of Multi-modal Images: Towards Real-Time Clinical Applications , 2002, MICCAI.

[46]  J. Friedman.  Stochastic gradient boosting , 2002 .

[47]  David A Clausi.  An analysis of co-occurrence texture statistics as a function of grey level quantization , 2002 .

[48]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[49]  Leen-Kiat Soh,et al.  Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices , 1999, IEEE Trans. Geosci. Remote. Sens..

[50]  Yiming Yang,et al.  A Comparative Study on Feature Selection in Text Categorization , 1997, ICML.

[51]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[52]  C R Bird,et al.  Gliomas: classification with MR imaging. , 1990, Radiology.

[53]  R L Ehman,et al.  Cerebral astrocytomas: histopathologic correlation of MR and CT contrast enhancement with stereotactic biopsy. , 1988, Radiology.

[54]  S. Green,et al.  Glioblastoma multiforme and anaplastic astrocytoma pathologic criteria and prognostic implications , 1985, Cancer.

[55]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[56]  Z. Šidák.  Rectangular Confidence Regions for the Means of Multivariate Normal Distributions , 1967 .

[57]  O. J. Dunn.  Multiple Comparisons Using Rank Sums , 1964 .

[58]  Richard Bellman,et al.  Adaptive Control Processes: A Guided Tour , 1961, The Mathematical Gazette.

[59]  W. Kruskal,et al.  Use of Ranks in One-Criterion Variance Analysis , 1952 .

[60]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .