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

Background Glioblastoma is the most aggressive brain tumor with poor prognosis. The purpose of this study is to improve the tissue characterization of these highly heterogeneous tumors using delta-radiomic features of images from dynamic susceptibility contrast enhanced (DSC) magnetic resonance imaging (MRI). Methods Twenty-five patients with histopathologically confirmed to be 13 high-grade (HG) and 12 low-grade (LG) gliomas who underwent the standard brain tumor MRI protocol, including DSC MRI, were included. Tumor regions on all DSC MRI images were registered to and contoured in T2-weighted fluid-attenuated inversion recovery (FLAIR) images. These contours and its contralateral regions of the normal tissue were used to extract delta-radiomic features before applying feature selection. The most informative and non-redundant features were selected to train a random forest to differentiate HG and LG gliomas. Then a leave-one-out cross-validation random forest was applied to classify these tumors for grading. Finally, a majority-voting method was applied to reduce binarization bias and to combine the results of various feature lists. Results Analysis of the predictions showed that the reported method consistently predicted the tumor grade of 24 out of 25 patients correctly (0.96). Finally, the mean prediction accuracy was 0.950±0.091 for HG and 0.850±0.255 for LG. The area under the receiver operating characteristic curve (AUC) was 0.94. Conclusions This study shows that delta-radiomic features derived from DSC MRI data can be used to characterize and determine the tumor grades. The radiomic features from DSC MRI may be used to elucidate the underlying tumor biology and response to therapy.

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

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

[3]  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.

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

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

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

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

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

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

[10]  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.

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

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

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

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

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

[16]  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.

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

[18]  Robert G. Selker,et al.  Randomized trial of three chemotherapy regimens and two radiotherapy regimens in postoperative treatment of malignant glioma , 2009 .

[19]  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.

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

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

[22]  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.

[23]  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.

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

[25]  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.

[26]  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 .

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

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

[29]  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.

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

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