Machine-learning based classification of glioblastoma using delta-radiomic features derived from dynamic susceptibility contrast enhanced magnetic resonance images

Glioblastomas (GBMs) are the most aggressive and lethal brain tumors. Lower grade gliomas [based on the 2007 World Health Organization (WHO) grading scale] have an average relative 2-year survival rate of 80%, while the relative 2-year survival rate for grade IV gliomas drops to only 30% with a median overall survival rate of 12–15 months (1,2). The incidence of malignant gliomas is about 17,000 per year or 5 in 100,000. Overall, about 65% are grade IV which results in a mortality rate of over 10,000 deaths per year (3). These poor outcomes stem from the uncooperative, heterogeneous nature of GBMs where some develop and Original Article

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

[2]  Yang Lei,et al.  MRI-based pseudo CT generation using classification and regression random forest , 2019, Medical Imaging.

[3]  M. Hatt,et al.  18F-FDG PET Uptake Characterization Through Texture Analysis: Investigating the Complementary Nature of Heterogeneity and Functional Tumor Volume in a Multi–Cancer Site Patient Cohort , 2015, The Journal of Nuclear Medicine.

[4]  Yang Lei,et al.  Pseudo CT estimation from MRI using patch-based random forest , 2017, Medical Imaging.

[5]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

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

[7]  Jinzhong Yang,et al.  IBEX: an open infrastructure software platform to facilitate collaborative work in radiomics. , 2015, Medical physics.

[8]  S. Gabriel,et al.  Integrated genomic analysis identifies clinically relevant subtypes of glioblastoma characterized by abnormalities in PDGFRA, IDH1, EGFR, and NF1. , 2010, Cancer cell.

[9]  S B Green,et al.  Randomized trial of three chemotherapy regimens and two radiotherapy regimens and two radiotherapy regimens in postoperative treatment of malignant glioma. Brain Tumor Cooperative Group Trial 8001. , 1989, Journal of neurosurgery.

[10]  Jie Tian,et al.  Grading of Gliomas by Using Radiomic Features on Multiple Magnetic Resonance Imaging (MRI) Sequences , 2017, Medical science monitor : international medical journal of experimental and clinical research.

[11]  Ganesh Rao,et al.  Associating spatial diversity features of radiologically defined tumor habitats with epidermal growth factor receptor driver status and 12-month survival in glioblastoma: methods and preliminary investigation , 2015, Journal of medical imaging.

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

[13]  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 .

[14]  D. Haussler,et al.  The Somatic Genomic Landscape of Glioblastoma , 2013, Cell.

[15]  D. D. Maki,et al.  Radiogenomic analysis of breast cancer using MRI: a preliminary study to define the landscape. , 2012, AJR. American journal of roentgenology.

[16]  Dafna Ben Bashat,et al.  Classification of tumor area using combined DCE and DSC MRI in patients with glioblastoma , 2014, Journal of Neuro-Oncology.

[17]  Ashutosh Kumar Singh,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2010 .

[18]  C. Sommer,et al.  Characterization of genomic alterations associated with glioma progression by comparative genomic hybridization. , 1996, Oncogene.

[19]  Loris Nanni,et al.  Handcrafted vs. non-handcrafted features for computer vision classification , 2017, Pattern Recognit..

[20]  Tian Liu,et al.  MRI-based pseudo CT synthesis using anatomical signature and alternating random forest with iterative refinement model , 2018, Journal of medical imaging.

[21]  Descriptive epidemiology of primary brain and CNS tumors: results from the Central Brain Tumor Registry of the United States, 1990-1994. , 1999, Neuro-oncology.

[22]  Roberto Maroldi,et al.  Texture analysis of advanced non-small cell lung cancer (NSCLC) on contrast-enhanced computed tomography: prediction of the response to the first-line chemotherapy , 2013, European Radiology.

[23]  Pieter Wesseling,et al.  The pathological diagnosis of diffuse gliomas: towards a smart synthesis of microscopic and molecular information in a multidisciplinary context , 2011 .

[24]  Karra A. Jones,et al.  Glioma grading using structural magnetic resonance imaging and molecular data , 2019, Journal of medical imaging.

[25]  Arvind Rao,et al.  Radiomics in glioblastoma: current status, challenges and potential opportunities , 2016 .

[26]  Yang Lei,et al.  Learning‐based CBCT correction using alternating random forest based on auto‐context model , 2018, Medical physics.

[27]  Tian Liu,et al.  MRI-based synthetic CT generation using semantic random forest with iterative refinement , 2019, Physics in medicine and biology.

[28]  Xiaofeng Yang,et al.  Ultrasound GLCM texture analysis of radiation-induced parotid-gland injury in head-and-neck cancer radiotherapy: an in vivo study of late toxicity. , 2012, Medical physics.

[29]  V. P. Collins,et al.  Intratumor heterogeneity in human glioblastoma reflects cancer evolutionary dynamics , 2013, Proceedings of the National Academy of Sciences.

[30]  Shawn M. Gillespie,et al.  Single-cell RNA-seq highlights intratumoral heterogeneity in primary glioblastoma , 2014, Science.

[31]  H. Wheeler,et al.  Molecular Heterogeneity in Glioblastoma: Potential Clinical Implications , 2015, Front. Oncol..

[32]  R. Colen,et al.  Imaging Genomics of Glioblastoma: Biology, Biomarkers, and Breakthroughs , 2015, Topics in magnetic resonance imaging : TMRI.