Survival Analysis of Patients with High-Grade Gliomas Based on Data Mining of Imaging Variables

The authors compared survival prediction using machine-learning data-mining techniques versus traditional histopathologic analysis in a group of 74 tumors. They looked at 55 imaging variables, extracting the most important ones and comparing these with standard histology. The most important variables were: extent of resection, mass effects, volume of enhancing tumor, maximum T2 intensity, and mean trace intensity in non-enhancing or edematous surrounding areas. The accuracy of the data-mining method was 85% and based on Kaplan-Meier curves this predicted survival better than histology. BACKGROUND AND PURPOSE: The prediction of prognosis in HGGs is poor in the majority of patients. Our aim was to test whether multivariate prediction models constructed by machine-learning methods provide a more accurate predictor of prognosis in HGGs than histopathologic classification. The prediction of survival was based on DTI and rCBV measurements as an adjunct to conventional imaging. MATERIALS AND METHODS: The relationship of survival to 55 variables, including clinical parameters (age, sex), categoric or continuous tumor descriptors (eg, tumor location, extent of resection, multifocality, edema), and imaging characteristics in ROIs, was analyzed in a multivariate fashion by using data-mining techniques. A variable selection method was applied to identify the overall most important variables. The analysis was performed on 74 HGGs (18 anaplastic gliomas WHO grades III/IV and 56 GBMs or gliosarcomas WHO grades IV/IV). RESULTS: Five variables were identified as the most significant, including the extent of resection, mass effect, volume of enhancing tumor, maximum B0 intensity, and mean trace intensity in the nonenhancing/edematous region. These variables were used to construct a prediction model based on a J48 classification tree. The average classification accuracy, assessed by cross-validation, was 85.1%. Kaplan-Meier survival curves showed that the constructed prediction model classified malignant gliomas in a manner that better correlates with clinical outcome than standard histopathology. CONCLUSIONS: Prediction models based on data-mining algorithms can provide a more accurate predictor of prognosis in malignant gliomas than histopathologic classification alone.

[1]  R. Meuli,et al.  Perfusion and diffusion MRI of glioblastoma progression in a four-year prospective temozolomide clinical trial. , 2006, International Journal of Radiation Oncology, Biology, Physics.

[2]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[3]  M Kirkpatrick,et al.  Cerebral Blood Volume Measurements by Perfusion-Weighted MR Imaging in Gliomas: Ready for Prime Time in Predicting Short-Term Outcome and Recurrent Disease? , 2009, American Journal of Neuroradiology.

[4]  Z L Gokaslan,et al.  A multivariate analysis of 416 patients with glioblastoma multiforme: prognosis, extent of resection, and survival. , 2001, Journal of neurosurgery.

[5]  T. Tominaga,et al.  Long-term survivors of glioblastoma: clinical features and molecular analysis , 2009, Acta Neurochirurgica.

[6]  D. Edwards Data Mining: Concepts, Models, Methods, and Algorithms , 2003 .

[7]  J. Cairncross,et al.  Which glioblastoma multiforme patient will become a long‐term survivor? A population‐based study , 1999, Annals of neurology.

[8]  Douglas C. Miller,et al.  Gliomas: predicting time to progression or survival with cerebral blood volume measurements at dynamic susceptibility-weighted contrast-enhanced perfusion MR imaging. , 2008, Radiology.

[9]  Stephen M. Smith,et al.  Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm , 2001, IEEE Transactions on Medical Imaging.

[10]  Paul S Mischel,et al.  MR imaging correlates of survival in patients with high-grade gliomas. , 2005, AJNR. American journal of neuroradiology.

[11]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[12]  G. Barnett,et al.  The impact of genotype on outcome in oligodendroglioma: validation of the loss of chromosome arm 1p as an important factor in clinical decision making. , 2006, Journal of neurosurgery.

[13]  Timothy D Johnson,et al.  Parametric response map as an imaging biomarker to distinguish progression from pseudoprogression in high-grade glioma. , 2010, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[14]  Martin Glas,et al.  Long-term survival of patients with glioblastoma treated with radiotherapy and lomustine plus temozolomide. , 2009, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[15]  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.

[16]  A. Jackson,et al.  Do cerebral blood volume and contrast transfer coefficient predict prognosis in human glioma? , 2006, AJNR. American journal of neuroradiology.

[17]  D. Louis,et al.  Specific genetic predictors of chemotherapeutic response and survival in patients with anaplastic oligodendrogliomas. , 1998, Journal of the National Cancer Institute.

[18]  N. Rainov,et al.  Overall survival in patients with malignant glioma may be significantly longer with tumors located in deep grey matter , 2007, Journal of the Neurological Sciences.

[19]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[20]  D. Caldiroli,et al.  Prognostic factors for survival in 676 consecutive patients with newly diagnosed primary glioblastoma. , 2008, Neuro-oncology.

[21]  Michael H Lev,et al.  Glial tumor grading and outcome prediction using dynamic spin-echo MR susceptibility mapping compared with conventional contrast-enhanced MR: confounding effect of elevated rCBV of oligodendrogliomas [corrected]. , 2004, AJNR. American journal of neuroradiology.

[22]  Ying Lu,et al.  Survival analysis in patients with glioblastoma multiforme: Predictive value of choline‐to‐n‐acetylaspartate index, apparent diffusion coefficient, and relative cerebral blood volume , 2004, Journal of magnetic resonance imaging : JMRI.

[23]  Hongmin Cai,et al.  Multiparametric tissue characterization of brain neoplasms and their recurrence using pattern classification of MR images. , 2008, Academic radiology.

[24]  Elias R Melhem,et al.  Intraaxial brain masses: MR imaging-based diagnostic strategy--initial experience. , 2007, Radiology.

[25]  L. D.,et al.  Brain tumors , 2005, Psychiatric Quarterly.

[26]  Toshinori Hirai,et al.  Usefulness of diffusion‐weighted MRI with echo‐planar technique in the evaluation of cellularity in gliomas , 1999, Journal of magnetic resonance imaging : JMRI.

[27]  Rafael Martí,et al.  Scatter Search: Diseño Básico y Estrategias avanzadas , 2002, Inteligencia Artif..

[28]  M. Muti,et al.  Perfusion MRI in the evaluation of the relationship between tumour growth, necrosis and angiogenesis in glioblastomas and grade 1 meningiomas , 2003, Neuroradiology.