Deep learning can differentiate IDH-mutant from IDH-wild type GBM

1Neuroradiology Unit, NESMOS Department, Sant’Andrea Hospital, La Sapienza University, Via di Grottarossa 1035, Rome 00189, Italy 2Neuroradiology Unit, Radiology Department, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY 10065, USA 3Medical Physics Department, Bambino Gesù Children's Hospital, IRCCS, Piazza di Sant'Onofrio, 4, Rome 00165, Italy 4Radiology and Diagnostic Imaging Department, Regina Elena National Cancer Institute, IRCCS, Via Elio Chianesi 53, Rome 00144, Italy 5Department of Clinical and Molecular Medicine, Surgical Pathology Unit, Sant’Andrea Hospital, La Sapienza University, Via di Grottarossa 1035, Rome 00189, Italy * Authors contributed equally to this work.

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

[2]  Yan Wang,et al.  Multimodal 3D DenseNet for IDH Genotype Prediction in Gliomas , 2018, Genes.

[3]  F. Ducray,et al.  IDH1 and IDH2 mutations in gliomas. , 2009, The New England journal of medicine.

[4]  P. Baldi,et al.  Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas , 2018, American Journal of Neuroradiology.

[5]  H. Aydin,et al.  R132H Mutation in IDH1 Gene is Associated with Increased Tumor HIF1‐Alpha and Serum VEGF Levels in Primary Glioblastoma Multiforme , 2017, Annals of clinical and laboratory science.

[6]  R. Beroukhim,et al.  Clinical multiplexed exome sequencing distinguishes adult oligodendroglial neoplasms from astrocytic and mixed lineage gliomas , 2014, Oncotarget.

[7]  Jie Hao,et al.  PASNet: pathway-associated sparse deep neural network for prognosis prediction from high-throughput data , 2018, BMC Bioinformatics.

[8]  Yang Liu,et al.  IDH mutation in glioma: molecular mechanisms and potential therapeutic targets , 2020, British Journal of Cancer.

[9]  A. Bozzao,et al.  Apparent diffusion coefficient obtained by magnetic resonance imaging as a prognostic marker in glioblastomas: correlation with MGMT promoter methylation status , 2013, European Radiology.

[10]  C. Russo,et al.  Radiomics in gliomas: clinical implications of computational modeling and fractal-based analysis , 2020, Neuroradiology.

[11]  G. Reifenberger,et al.  Patients with IDH 1 wild type anaplastic astrocytomas exhibit worse prognosis than IDH 1-mutated glioblastomas , and IDH 1 mutation status accounts for the unfavorable prognostic effect of higher age : implications for classification of gliomas , 2010 .

[12]  L. Mazzoni,et al.  Relationship between Apparent Diffusion Coefficients and MR Spectroscopy Findings in High‐Grade Gliomas , 2017, Journal of neuroimaging : official journal of the American Society of Neuroimaging.

[13]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[14]  Annette M. Molinaro,et al.  Genetic and molecular epidemiology of adult diffuse glioma , 2019, Nature Reviews Neurology.

[15]  Ru-Fang Yeh,et al.  Glioblastoma multiforme regional genetic and cellular expression patterns: influence on anatomic and physiologic MR imaging. , 2010, Radiology.

[16]  P. Kleihues,et al.  IDH1 Mutations as Molecular Signature and Predictive Factor of Secondary Glioblastomas , 2009, Clinical Cancer Research.

[17]  Xiaoyue Zhou,et al.  Vascular habitat analysis based on dynamic susceptibility contrast perfusion MRI predicts IDH mutation status and prognosis in high-grade gliomas , 2020, European Radiology.

[18]  Dinggang Shen,et al.  Multi-Channel 3D Deep Feature Learning for Survival Time Prediction of Brain Tumor Patients Using Multi-Modal Neuroimages , 2019, Scientific Reports.

[19]  L. Liau,et al.  Cancer-associated IDH1 mutations produce 2-hydroxyglutarate , 2009, Nature.

[20]  R. Mirimanoff,et al.  MGMT gene silencing and benefit from temozolomide in glioblastoma. , 2005, The New England journal of medicine.

[21]  Mitchel S Berger,et al.  Regional variation in histopathologic features of tumor specimens from treatment-naive glioblastoma correlates with anatomic and physiologic MR Imaging. , 2012, Neuro-oncology.

[22]  S. Heiland,et al.  IDH mutation status is associated with a distinct hypoxia/angiogenesis transcriptome signature which is non-invasively predictable with rCBV imaging in human glioma , 2015, Scientific Reports.

[23]  Taghi M. Khoshgoftaar,et al.  A survey on Image Data Augmentation for Deep Learning , 2019, Journal of Big Data.

[24]  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.

[25]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[26]  M. J. van den Bent,et al.  Imaging Correlates of Adult Glioma Genotypes. , 2017, Radiology.

[27]  A. Bozzao,et al.  Prediction of survival in patients affected by glioblastoma: histogram analysis of perfusion MRI , 2018, Journal of Neuro-Oncology.

[28]  J. Grinband,et al.  Optimizing Neuro-Oncology Imaging: A Review of Deep Learning Approaches for Glioma Imaging , 2019, Cancers.

[29]  A. Viale,et al.  The Many Facets of Tumor Heterogeneity: Is Metabolism Lagging Behind? , 2019, Cancers.

[30]  Chung-Ming Lo,et al.  Radiomic model for predicting mutations in the isocitrate dehydrogenase gene in glioblastomas , 2017, Oncotarget.

[31]  Raymond Y Huang,et al.  Multimodal MRI features predict isocitrate dehydrogenase genotype in high-grade gliomas , 2017, Neuro-oncology.

[32]  B. Rosen,et al.  High resolution measurement of cerebral blood flow using intravascular tracer bolus passages. Part I: Mathematical approach and statistical analysis , 1996, Magnetic resonance in medicine.

[33]  Philippe Lambin,et al.  Quantitative radiomics studies for tissue characterization: a review of technology and methodological procedures , 2017, The British journal of radiology.

[34]  A. Tamimi,et al.  Epidemiology and Outcome of Glioblastoma , 2017 .

[35]  Keith L. Ligon,et al.  Somatic mutations associated with MRI-derived volumetric features in glioblastoma , 2015, Neuroradiology.

[36]  F. Meier,et al.  Clinical impact and frequency of anatomic pathology errors in cancer diagnoses , 2005, Cancer.

[37]  Glyn Johnson,et al.  Comparison of cerebral blood volume and vascular permeability from dynamic susceptibility contrast-enhanced perfusion MR imaging with glioma grade. , 2004, AJNR. American journal of neuroradiology.

[38]  C. Bettegowda,et al.  Genomic discoveries in adult astrocytoma. , 2015, Current opinion in genetics & development.

[39]  Mauricio Reyes,et al.  Deep Learning versus Classical Regression for Brain Tumor Patient Survival Prediction , 2018, BrainLes@MICCAI.

[40]  Peter Chang,et al.  Imaging Genetic Heterogeneity in Glioblastoma and Other Glial Tumors: Review of Current Methods and Future Directions. , 2018, AJR. American journal of roentgenology.

[41]  P. Lambin,et al.  Machine Learning methods for Quantitative Radiomic Biomarkers , 2015, Scientific Reports.

[42]  J. Grinband,et al.  Glioblastoma Induces Vascular Dysregulation in Nonenhancing Peritumoral Regions in Humans. , 2016, AJR. American journal of roentgenology.

[43]  P. LaViolette,et al.  Precise ex vivo histological validation of heightened cellularity and diffusion-restricted necrosis in regions of dark apparent diffusion coefficient in 7 cases of high-grade glioma. , 2014, Neuro-oncology.

[44]  Maulik R. Kamdar,et al.  MRI to MGMT: Predicting methylation status in glioblastoma patients using convolutional recurrent neural networks , 2018, PSB.

[45]  Raymond Y Huang,et al.  Residual Convolutional Neural Network for the Determination of IDH Status in Low- and High-Grade Gliomas from MR Imaging , 2017, Clinical Cancer Research.

[46]  S. Berger,et al.  IDH mutation impairs histone demethylation and results in a block to cell differentiation , 2012, Nature.