Overall survival prediction in glioblastoma patients using structural magnetic resonance imaging (MRI): advanced radiomic features may compensate for lack of advanced MRI modalities

Abstract. Purpose: Glioblastoma, the most common and aggressive adult brain tumor, is considered noncurative at diagnosis, with 14 to 16 months median survival following treatment. There is increasing evidence that noninvasive integrative analysis of radiomic features can predict overall and progression-free survival, using advanced multiparametric magnetic resonance imaging (Adv-mpMRI). If successfully applicable, such noninvasive markers can considerably influence patient management. However, most patients prior to initiation of therapy typically undergo only basic structural mpMRI (Bas-mpMRI, i.e., T1, T1-Gd, T2, and T2-fluid-attenuated inversion recovery) preoperatively, rather than Adv-mpMRI that provides additional vascularization (dynamic susceptibility contrast-MRI) and cell-density (diffusion tensor imaging) related information. Approach: We assess a retrospective cohort of 101 glioblastoma patients with available Adv-mpMRI from a previous study, which has shown that an initial feature panel (IFP, i.e., intensity, volume, location, and growth model parameters) extracted from Adv-mpMRI can yield accurate overall survival stratification. We focus on demonstrating that equally accurate prediction models can be constructed using augmented radiomic feature panels (ARFPs, i.e., integrating morphology and textural descriptors) extracted solely from widely available Bas-mpMRI, obviating the need for using Adv-mpMRI. We extracted 1612 radiomic features from distinct tumor subregions to build multivariate models that stratified patients as long-, intermediate-, or short-survivors. Results: The classification accuracy of the model utilizing Adv-mpMRI protocols and the IFP was 72.77% and degraded to 60.89% when using only Bas-mpMRI. However, utilizing the ARFP on Bas-mpMRI improved the accuracy to 74.26%. Furthermore, Kaplan–Meier analysis demonstrated superior classification of subjects into short-, intermediate-, and long-survivor classes when using ARFP extracted from Bas-mpMRI. Conclusions: This quantitative evaluation indicates that accurate survival prediction in glioblastoma patients is feasible using solely Bas-mpMRI and integrative advanced radiomic features, which can compensate for the lack of Adv-mpMRI. Our finding holds promise for generalization across multiple institutions that may not have access to Adv-mpMRI and to better inform clinical decision-making about aggressive interventions and clinical trials.

[1]  H. Schlemmer,et al.  Clinical parameters outweigh diffusion- and perfusion-derived MRI parameters in predicting survival in newly diagnosed glioblastoma. , 2016, Neuro-oncology.

[2]  Teresa Wu,et al.  Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma , 2015, PloS one.

[3]  Scott N. Hwang,et al.  Outcome prediction in patients with glioblastoma by using imaging, clinical, and genomic biomarkers: focus on the nonenhancing component of the tumor. , 2014, Radiology.

[4]  Tej D. Azad,et al.  Magnetic resonance image features identify glioblastoma phenotypic subtypes with distinct molecular pathway activities , 2015, Science Translational Medicine.

[5]  Polina Golland,et al.  Probabilistic Modeling of Imaging, Genetics and Diagnosis , 2016, IEEE Transactions on Medical Imaging.

[6]  S. Plevritis,et al.  Glioblastoma multiforme: exploratory radiogenomic analysis by using quantitative image features. , 2014, Radiology.

[7]  Bilwaj Gaonkar,et al.  Multi-atlas skull-stripping. , 2013, Academic radiology.

[8]  A. Rutman,et al.  Radiogenomics: creating a link between molecular diagnostics and diagnostic imaging. , 2009, European journal of radiology.

[9]  R. Mirimanoff,et al.  Effects of radiotherapy with concomitant and adjuvant temozolomide versus radiotherapy alone on survival in glioblastoma in a randomised phase III study: 5-year analysis of the EORTC-NCIC trial. , 2009, The Lancet. Oncology.

[10]  Mark W. Woolrich,et al.  FSL , 2012, NeuroImage.

[11]  Bilwaj Gaonkar,et al.  GLISTRboost: Combining Multimodal MRI Segmentation, Registration, and Biophysical Tumor Growth Modeling with Gradient Boosting Machines for Glioma Segmentation , 2015, Brainles@MICCAI.

[12]  Mark W. Woolrich,et al.  Bayesian analysis of neuroimaging data in FSL , 2009, NeuroImage.

[13]  Sanjeev Chawla,et al.  Use of magnetic perfusion-weighted imaging to determine epidermal growth factor receptor variant III expression in glioblastoma. , 2012, Neuro-oncology.

[14]  William D. Dunn,et al.  MR imaging predictors of molecular profile and survival: multi-institutional study of the TCGA glioblastoma data set. , 2013, Radiology.

[15]  Xiaoou Tang,et al.  Texture information in run-length matrices , 1998, IEEE Trans. Image Process..

[16]  Christos Davatzikos,et al.  A robust framework for soft tissue simulations with application to modeling brain tumor mass effect in 3D MR images , 2007, Physics in medicine and biology.

[17]  Christos Davatzikos,et al.  NIMG-11. HIGHLY-EXPRESSED WILD-TYPE EGFR AND EGFRvIII MUTANT GLIOBLASTOMAS HAVE SIMILAR MRI SIGNATURE, CONSISTENT WITH DEEP PERITUMORAL INFILTRATION , 2016 .

[18]  Pieter Wesseling,et al.  cIMPACT‐NOW: a practical summary of diagnostic points from Round 1 updates , 2019, Brain pathology.

[19]  S Ekholm,et al.  Percentage Signal Recovery Derived from MR Dynamic Susceptibility Contrast Imaging Is Useful to Differentiate Common Enhancing Malignant Lesions of the Brain , 2011, American Journal of Neuroradiology.

[20]  Andre Dekker,et al.  Radiogenomics: radiobiology enters the era of big data and team science. , 2014, International journal of radiation oncology, biology, physics.

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

[22]  James F. Greenleaf,et al.  Use of gray value distribution of run lengths for texture analysis , 1990, Pattern Recognit. Lett..

[23]  Robert King,et al.  Textural features corresponding to textural properties , 1989, IEEE Trans. Syst. Man Cybern..

[24]  Christos Davatzikos,et al.  Brain Cancer Imaging Phenomics Toolkit (brain-CaPTk): An Interactive Platform for Quantitative Analysis of Glioblastoma , 2017, BrainLes@MICCAI.

[25]  Walter J Curran,et al.  Dose-dense temozolomide for newly diagnosed glioblastoma: a randomized phase III clinical trial. , 2013, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[26]  Luke Macyszyn,et al.  Pattern analysis of dynamic susceptibility contrast-enhanced MR imaging demonstrates peritumoral tissue heterogeneity. , 2014, Radiology.

[27]  Patrick Granton,et al.  Radiomics: extracting more information from medical images using advanced feature analysis. , 2012, European journal of cancer.

[28]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[29]  Luke Macyszyn,et al.  Imaging patterns predict patient survival and molecular subtype in glioblastoma via machine learning techniques. , 2016, Neuro-oncology.

[30]  Paul Kinahan,et al.  Radiomics: Images Are More than Pictures, They Are Data , 2015, Radiology.

[31]  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.

[32]  P. Lambin,et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach , 2014, Nature Communications.

[33]  Christos Davatzikos,et al.  An image-driven parameter estimation problem for a reaction–diffusion glioma growth model with mass effects , 2008, Journal of mathematical biology.

[34]  S. Bakas,et al.  Imaging signatures of glioblastoma molecular characteristics: A radiogenomics review , 2020, Journal of magnetic resonance imaging : JMRI.

[35]  B. O'neill,et al.  Glioblastoma survival in the United States before and during the temozolomide era , 2012, Journal of Neuro-Oncology.

[36]  Michael Brady,et al.  Improved Optimization for the Robust and Accurate Linear Registration and Motion Correction of Brain Images , 2002, NeuroImage.

[37]  Mark W. Woolrich,et al.  Advances in functional and structural MR image analysis and implementation as FSL , 2004, NeuroImage.

[38]  G. Collewet,et al.  Influence of MRI acquisition protocols and image intensity normalization methods on texture classification. , 2004, Magnetic resonance imaging.

[39]  Carol Proud,et al.  Radiogenomics: the promise of personalized treatment in radiation oncology? , 2014, Clinical journal of oncology nursing.

[40]  Peter Canoll,et al.  MRI-localized biopsies reveal subtype-specific differences in molecular and cellular composition at the margins of glioblastoma , 2014, Proceedings of the National Academy of Sciences.

[41]  A. Mahajan,et al.  Radiogenomics of glioblastoma: a window into its imaging and molecular variability , 2015, Cancer Imaging.

[42]  Steffen Löck,et al.  Image biomarker standardisation initiative , 2016 .

[43]  D.,et al.  Regression Models and Life-Tables , 2022 .

[44]  El Naqa,et al.  A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities , 2015 .

[45]  Christos Davatzikos,et al.  In Vivo Detection of EGFRvIII in Glioblastoma via Perfusion Magnetic Resonance Imaging Signature Consistent with Deep Peritumoral Infiltration: The ϕ-Index , 2017, Clinical Cancer Research.

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

[47]  Christos Davatzikos,et al.  Population-based MRI atlases of spatial distribution are specific to patient and tumor characteristics in glioblastoma , 2016, NeuroImage: Clinical.

[48]  Mary M. Galloway,et al.  Texture analysis using gray level run lengths , 1974 .

[49]  Christos Davatzikos,et al.  NIMG-20. IMAGING PATTERN ANALYSIS REVEALS THREE DISTINCT PHENOTYPIC SUBTYPES OF GBM WITH DIFFERENT SURVIVAL RATES , 2016 .

[50]  C. Jaffe Imaging and genomics: is there a synergy? , 2012, Radiology.

[51]  J. Friedman Greedy function approximation: A gradient boosting machine. , 2001 .

[52]  Joel Max,et al.  Quantizing for minimum distortion , 1960, IRE Trans. Inf. Theory.

[53]  H. Aerts Semantics Features : Phenotype Quantification by a Radiologist ’ s Expert Eye , 2016 .

[54]  Stephen M. Smith,et al.  A global optimisation method for robust affine registration of brain images , 2001, Medical Image Anal..

[55]  Christos Davatzikos,et al.  Cancer imaging phenomics toolkit: quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome , 2018, Journal of medical imaging.

[56]  Christos Davatzikos,et al.  Brain--Tumor Interaction Biophysical Models for Medical Image Registration , 2008, SIAM J. Sci. Comput..

[57]  Dimitrios Makris,et al.  Fast semi-automatic segmentation of focal liver lesions in contrast-enhanced ultrasound, based on a probabilistic model , 2017, Comput. methods Biomech. Biomed. Eng. Imaging Vis..

[58]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[59]  M. Mazurowski Radiogenomics: what it is and why it is important. , 2015, Journal of the American College of Radiology : JACR.

[60]  Olivier Gevaert,et al.  Addition of MR imaging features and genetic biomarkers strengthens glioblastoma survival prediction in TCGA patients. , 2015, Journal of neuroradiology. Journal de neuroradiologie.

[61]  M. Berger,et al.  Differentiation of Glioblastoma Multiforme and Single Brain Metastasis by Peak Height and Percentage of Signal Intensity Recovery Derived from Dynamic Susceptibility-Weighted Contrast-Enhanced Perfusion MR Imaging , 2007, American Journal of Neuroradiology.

[62]  Andre Dekker,et al.  Radiomics: the process and the challenges. , 2012, Magnetic resonance imaging.

[63]  Christos Davatzikos,et al.  Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features , 2017, Scientific Data.

[64]  Mauricio Reyes,et al.  Fully automatic GBM segmentation in the TCGA-GBM dataset: Prognosis and correlation with VASARI features , 2015, Scientific Reports.

[65]  Adolf Pfefferbaum,et al.  The SRI24 multichannel atlas of normal adult human brain structure , 2009, Human brain mapping.

[66]  Victor Alves,et al.  A hitchhiker's guide to diffusion tensor imaging , 2012, Front. Neurosci..

[67]  Christos Davatzikos,et al.  Segmentation of Gliomas in Pre-operative and Post-operative Multimodal Magnetic Resonance Imaging Volumes Based on a Hybrid Generative-Discriminative Framework , 2016, BrainLes@MICCAI.

[68]  David Bonekamp,et al.  Association of overall survival in patients with newly diagnosed glioblastoma with contrast‐enhanced perfusion MRI: Comparison of intraindividually matched T1‐ and T2*‐based bolus techniques , 2015, Journal of magnetic resonance imaging : JMRI.

[69]  Stephen M. Smith,et al.  SUSAN—A New Approach to Low Level Image Processing , 1997, International Journal of Computer Vision.

[70]  Benjamin M. Ellingson,et al.  Radiogenomics and Imaging Phenotypes in Glioblastoma: Novel Observations and Correlation with Molecular Characteristics , 2014, Current Neurology and Neuroscience Reports.

[71]  G. Reifenberger,et al.  The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary , 2016, Acta Neuropathologica.

[72]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[73]  K. Peck,et al.  T1-Weighted Dynamic Contrast-Enhanced MRI as a Noninvasive Biomarker of Epidermal Growth Factor Receptor vIII Status , 2015, American Journal of Neuroradiology.

[74]  John G. Griffiths,et al.  Least squares ellipsoid specific fitting , 2004, Geometric Modeling and Processing, 2004. Proceedings.

[75]  Jordan M. Malof,et al.  Imaging descriptors improve the predictive power of survival models for glioblastoma patients. , 2013, Neuro-oncology.

[76]  Dawit Assefa,et al.  Robust texture features for response monitoring of glioblastoma multiforme on T1-weighted and T2-FLAIR MR images: a preliminary investigation in terms of identification and segmentation. , 2010, Medical physics.

[77]  Belur V. Dasarathy,et al.  Image characterizations based on joint gray level-run length distributions , 1991, Pattern Recognit. Lett..

[78]  R. Steenbakkers,et al.  The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. , 2020, Radiology.

[79]  Olivier Gevaert,et al.  Abstract 5561: Radiogenomic analysis indicates MR images are potentially predictive of EGFR mutation status in glioblastoma multiforme , 2012 .

[80]  et al.,et al.  Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge , 2018, ArXiv.

[81]  Christos Davatzikos,et al.  MUSE: MUlti-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters, and locally optimal atlas selection , 2016, NeuroImage.

[82]  Bernard Fertil,et al.  Shape and Texture Indexes Application to Cell nuclei Classification , 2013, Int. J. Pattern Recognit. Artif. Intell..

[83]  G. Biros,et al.  Imaging Surrogates of Infiltration Obtained Via Multiparametric Imaging Pattern Analysis Predict Subsequent Location of Recurrence of Glioblastoma. , 2016, Neurosurgery.