Prediction of survival with multi-scale radiomic analysis in glioblastoma patients

AbstractWe propose a multiscale texture features based on Laplacian-of Gaussian (LoG) filter to predict progression free (PFS) and overall survival (OS) in patients newly diagnosed with glioblastoma (GBM). Experiments use the extracted features derived from 40 patients of GBM with T1-weighted imaging (T1-WI) and Fluid-attenuated inversion recovery (FLAIR) images that were segmented manually into areas of active tumor, necrosis, and edema. Multiscale texture features were extracted locally from each of these areas of interest using a LoG filter and the relation between features to OS and PFS was investigated using univariate (i.e., Spearman’s rank correlation coefficient, log-rank test and Kaplan-Meier estimator) and multivariate analyses (i.e., Random Forest classifier). Three and seven features were statistically correlated with PFS and OS, respectively, with absolute correlation values between 0.32 and 0.36 and p < 0.05. Three features derived from active tumor regions only were associated with OS (p < 0.05) with hazard ratios (HR) of 2.9, 3, and 3.24, respectively. Combined features showed an AUC value of 85.37 and 85.54% for predicting the PFS and OS of GBM patients, respectively, using the random forest (RF) classifier. We presented a multiscale texture features to characterize the GBM regions and predict he PFS and OS. The efficiency achievable suggests that this technique can be developed into a GBM MR analysis system suitable for clinical use after a thorough validation involving more patients. Graphical abstractScheme of the proposed model for characterizing the heterogeneity of GBM regions and predicting the overall survival and progression free survival of GBM patients. (1) Acquisition of pretreatment MRI images; (2) Affine registration of T1-WI image with its corresponding FLAIR images, and GBM subtype (phenotypes) labelling; (3) Extraction of nine texture features from the three texture scales fine, medium, and coarse derived from each of GBM regions; (4) Comparing heterogeneity between GBM regions by ANOVA test; Survival analysis using Univariate (Spearman rank correlation between features and survival (i.e., PFS and OS) based on each of the GBM regions, Kaplan-Meier estimator and log-rank test to predict the PFS and OS of patient groups that grouped based on median of feature), and multivariate (random forest model) for predicting the PFS and OS of patients groups that grouped based on median of PFS and OS.

[1]  G. Tutz,et al.  An introduction to recursive partitioning: rationale, application, and characteristics of classification and regression trees, bagging, and random forests. , 2009, Psychological methods.

[2]  J. H. Zar,et al.  Significance Testing of the Spearman Rank Correlation Coefficient , 1972 .

[3]  V. Valentini,et al.  How Can Radiomics Improve Clinical Choices , 2018 .

[4]  N. deSouza,et al.  Relationship between imaging biomarkers of stage I cervical cancer and poor-prognosis histologic features: quantitative histogram analysis of diffusion-weighted MR images. , 2013, AJR. American journal of roentgenology.

[5]  Balaji Ganeshan,et al.  Texture analysis of non-small cell lung cancer on unenhanced computed tomography: initial evidence for a relationship with tumour glucose metabolism and stage , 2010, Cancer imaging : the official publication of the International Cancer Imaging Society.

[6]  Camel Tanougast,et al.  Extracted magnetic resonance texture features discriminate between phenotypes and are associated with overall survival in glioblastoma multiforme patients , 2016, Medical & Biological Engineering & Computing.

[7]  Leland S. Hu,et al.  Radiogenomics to characterize regional genetic heterogeneity in glioblastoma , 2016, Neuro-oncology.

[8]  Zev A. Binder,et al.  Radiomic MRI signature reveals three distinct subtypes of glioblastoma with different clinical and molecular characteristics, offering prognostic value beyond IDH1 , 2018, Scientific Reports.

[9]  Bradley James Erickson,et al.  Part 1. Automated Change Detection and Characterization in Serial MR Studies of Brain-Tumor Patients , 2007, Journal of Digital Imaging.

[10]  P. Lambin,et al.  Radiomics: the bridge between medical imaging and personalized medicine , 2017, Nature Reviews Clinical Oncology.

[11]  Rivka R. Colen,et al.  Statistical feature selection for enhanced detection of brain tumor , 2014, Optics & Photonics - Optical Engineering + Applications.

[12]  Matthew Toews,et al.  Multi-scale radiomic analysis of sub-cortical regions in MRI related to autism, gender and age , 2017, Scientific Reports.

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

[14]  K Takakura,et al.  Subacute brain atrophy after radiation therapy for malignant brain tumor , 1989, Cancer.

[15]  Ahmed Bouridane,et al.  Multi Texture Analysis of Colorectal Cancer Continuum Using Multispectral Imagery , 2016, PloS one.

[16]  Balaji Ganeshan,et al.  Imaging heterogeneity in gliomas using texture analysis. , 2011 .

[17]  Ricardo Fraiman,et al.  An anova test for functional data , 2004, Comput. Stat. Data Anal..

[18]  A. Madabhushi,et al.  Radiomic features from the peritumoral brain parenchyma on treatment-naïve multi-parametric MR imaging predict long versus short-term survival in glioblastoma multiforme: Preliminary findings , 2017, European Radiology.

[19]  S. Holm.  A Simple Sequentially Rejective Multiple Test Procedure , 1979 .

[20]  M. Götz,et al.  Radiomic Profiling of Glioblastoma: Identifying an Imaging Predictor of Patient Survival with Improved Performance over Established Clinical and Radiologic Risk Models. , 2016, Radiology.

[21]  J. Brenton,et al.  Unravelling tumour heterogeneity using next-generation imaging: radiomics, radiogenomics, and habitat imaging. , 2017, Clinical radiology.

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

[23]  Stephen M. Moore,et al.  The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository , 2013, Journal of Digital Imaging.

[24]  Matthew Toews,et al.  GBM heterogeneity characterization by radiomic analysis of phenotype anatomical planes , 2016, SPIE Medical Imaging.

[25]  D. Kleinbaum,et al.  Kaplan-Meier Survival Curves and the Log-Rank Test , 2012 .

[26]  Juha Öhman,et al.  Texture analysis of MR images of patients with Mild Traumatic Brain Injury , 2010, BMC Medical Imaging.

[27]  J. Seoane,et al.  Glioblastoma Multiforme: A Look Inside Its Heterogeneous Nature , 2014, Cancers.

[28]  Martin Sill,et al.  Large-scale Radiomic Profiling of Recurrent Glioblastoma Identifies an Imaging Predictor for Stratifying Anti-Angiogenic Treatment Response , 2016, Clinical Cancer Research.

[29]  Maximilian Reiser,et al.  Radiomic Analysis Reveals Prognostic Information in T1-Weighted Baseline Magnetic Resonance Imaging in Patients With Glioblastoma , 2017, Investigative radiology.

[30]  J. Decertaines.  Can dynamic contrast-enhanced magnetic resonance imaging combined with texture analysis differentiate malignant glioneuronal tumors from other glioblastoma ? , 2012 .

[31]  James V. Miller,et al.  GBM Volumetry using the 3D Slicer Medical Image Computing Platform , 2013, Scientific Reports.

[32]  H. Schwarzmaier,et al.  MR‐guided laser irradiation of recurrent glioblastomas , 2005, Journal of magnetic resonance imaging : JMRI.

[33]  R. Gillies,et al.  Identifying spatial imaging biomarkers of glioblastoma multiforme for survival group prediction , 2016, Journal of magnetic resonance imaging : JMRI.

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

[35]  Yang Liu,et al.  Relationship between Glioblastoma Heterogeneity and Survival Time: An MR Imaging Texture Analysis , 2017, American Journal of Neuroradiology.

[36]  Kaibin Xu,et al.  Relationship between necrotic patterns in glioblastoma and patient survival: fractal dimension and lacunarity analyses using magnetic resonance imaging , 2017, Scientific Reports.

[37]  Hongbing Lu,et al.  The effect of glioblastoma heterogeneity on survival stratification: a multimodal MR imaging texture analysis , 2018, Acta radiologica.

[38]  K M Leung,et al.  Censoring issues in survival analysis. , 1997, Annual review of public health.

[39]  Chen-Zhuoya Sheng,et al.  A parameterized logarithmic image processing method based on Laplacian of Gaussian filtering for lung nodules enhancement in chest radiographs , 2013, 2013 2nd International Symposium on Instrumentation and Measurement, Sensor Network and Automation (IMSNA).

[40]  E Le Rumeur,et al.  MRI texture analysis on texture test objects, normal brain and intracranial tumors. , 2003, Magnetic resonance imaging.

[41]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[42]  R. Gillies,et al.  Radiologically defined ecological dynamics and clinical outcomes in glioblastoma multiforme: preliminary results. , 2014, Translational oncology.

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

[44]  Guangtao Zhai,et al.  A Deep Learning-Based Radiomics Model for Prediction of Survival in Glioblastoma Multiforme , 2017, Scientific Reports.

[45]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[46]  Maciej A. Mazurowski,et al.  Computer-extracted MR imaging features are associated with survival in glioblastoma patients , 2014, Journal of Neuro-Oncology.

[47]  J. Todd.  Book Review: Digital image processing (second edition). By R. C. Gonzalez and P. Wintz, Addison-Wesley, 1987. 503 pp. Price: £29.95. (ISBN 0-201-11026-1) , 1988 .

[48]  Michael Weller,et al.  Changing paradigms--an update on the multidisciplinary management of malignant glioma. , 2006, The oncologist.

[49]  Balaji Ganeshan,et al.  Diagnostic performance of texture analysis on MRI in grading cerebral gliomas. , 2016, European journal of radiology.

[50]  Ruijiang Li,et al.  Volume of high-risk intratumoral subregions at multi-parametric MR imaging predicts overall survival and complements molecular analysis of glioblastoma , 2017, European Radiology.

[51]  Matthew Toews,et al.  Radiomic analysis of multi-contrast brain MRI for the prediction of survival in patients with glioblastoma multiforme , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

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

[53]  Christos Davatzikos,et al.  Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme , 2009, Magnetic resonance in medicine.

[54]  Steinar Lundgren,et al.  Dynamic contrast‐enhanced MRI texture analysis for pretreatment prediction of clinical and pathological response to neoadjuvant chemotherapy in patients with locally advanced breast cancer , 2014, NMR in biomedicine.

[55]  Vinod Kumar,et al.  Segmentation, Feature Extraction, and Multiclass Brain Tumor Classification , 2013, Journal of Digital Imaging.

[56]  Matthew Toews,et al.  Novel Radiomic Features Based on Joint Intensity Matrices for Predicting Glioblastoma Patient Survival Time , 2019, IEEE Journal of Biomedical and Health Informatics.

[57]  Lei Xing,et al.  Prognostic Imaging Biomarkers in Glioblastoma: Development and Independent Validation on the Basis of Multiregion and Quantitative Analysis of MR Images. , 2016, Radiology.

[58]  Matthew Toews,et al.  Phenotypic characterization of glioblastoma identified through shape descriptors , 2016, SPIE Medical Imaging.

[59]  Sheng Chen,et al.  A parameterized logarithmic image processing method with Laplacian of Gaussian filtering for lung nodule enhancement in chest radiographs , 2016, Medical & Biological Engineering & Computing.

[60]  Richard Frayne,et al.  A comparison of texture quantification techniques based on the Fourier and S transforms. , 2008, Medical physics.

[61]  S. E. Norred,et al.  Magnetic Resonance-Guided Laser Induced Thermal Therapy for Glioblastoma Multiforme: A Review , 2014, BioMed research international.

[62]  A. Rao,et al.  Texture Feature Ratios from Relative CBV Maps of Perfusion MRI Are Associated with Patient Survival in Glioblastoma , 2016, American Journal of Neuroradiology.