Cluster Analysis of DSC MRI, Dynamic Contrast-Enhanced MRI, and DWI Parameters Associated with Prognosis in Patients with Glioblastoma after Removal of the Contrast-Enhancing Component: A Preliminary Study

This model showed that nonenhancing T2 high-signal-intensity lesions with relatively low normalized CBV, low volume transfer constant values, and the lowest ADC values could serve as useful prognostic imaging markers for predicting survival outcomes in patients with glioblastoma. BACKGROUND AND PURPOSE: No report has been published on the use of DSC MR imaging, DCE MR imaging, and DWI parameters in combination to create a prognostic prediction model in glioblastoma patients. The aim of this study was to develop a machine learning–based model to find preoperative multiparametric MR imaging parameters associated with prognosis in patients with glioblastoma. Normalized CBV, volume transfer constant, and ADC of the nonenhancing T2 high-signal-intensity lesions were evaluated using K-means clustering. MATERIALS AND METHODS: A total of 142 patients with glioblastoma who underwent preoperative MR imaging and total resection were included in this retrospective study. From the normalized CBV, volume transfer constant, and ADC maps, the parametric data were sorted using the K-means clustering method. Patients were divided into training and test sets (ratio, 1:1), and the optimal number of clusters was determined using receiver operating characteristic analysis. Kaplan-Meier survival analysis and log-rank tests were performed to identify potential parametric predictors. A multivariate Cox proportional hazard model was conducted to adjust for clinical predictors. RESULTS: The nonenhancing T2 high-signal-intensity lesions were divided into 6 clusters. The cluster (class 4) with the relatively low normalized CBV and volume transfer constant value and the lowest ADC values was most associated with predicting glioblastoma prognosis. The optimal cutoff of the class 4 volume fraction of nonenhancing T2 high-signal-intensity lesions predicting 1-year progression-free survival was 9.70%, below which the cutoff was associated with longer progression-free survival. Two Kaplan-Meier curves based on the cutoff value showed a statistically significant difference (P = .037). When we adjusted for all clinical predictors, the cluster with the relatively low normalized CBV and volume transfer constant values and the lowest ADC value was an independent prognostic marker (hazard ratio, 3.04; P = .048). The multivariate Cox proportional hazard model showed a concordance index of 0.699 for progression-free survival. CONCLUSIONS: Our model showed that nonenhancing T2 high-signal-intensity lesions with the relatively low normalized CBV, low volume transfer constant values, and the lowest ADC values could serve as useful prognostic imaging markers for predicting survival outcomes in patients with glioblastoma.

[1]  Mehdi Salkhordeh Haghighi,et al.  The Systematic Review of K-Means Clustering Algorithm , 2020, ICNCC.

[2]  J. H. Kim,et al.  Prognostic Value of Dynamic Contrast-Enhanced MRI-Derived Pharmacokinetic Variables in Glioblastoma Patients: Analysis of Contrast-Enhancing Lesions and Non-Enhancing T2 High-Signal Intensity Lesions , 2020, Korean journal of radiology.

[3]  P. Mitsias,et al.  Current and Future Trends on Diagnosis and Prognosis of Glioblastoma: From Molecular Biology to Proteomics , 2019, Cells.

[4]  F. Gaillard,et al.  Non-Contrast-Enhancing Tumor: A New Frontier in Glioblastoma Research , 2019, American Journal of Neuroradiology.

[5]  P. Madureira,et al.  The Role of Hypoxia in Glioblastoma Invasion , 2017, Cells.

[6]  G. Reifenberger,et al.  European Association for Neuro-Oncology (EANO) guideline on the diagnosis and treatment of adult astrocytic and oligodendroglial gliomas. , 2017, The Lancet. Oncology.

[7]  Tae Min Kim,et al.  Prognosis prediction of non-enhancing T2 high signal intensity lesions in glioblastoma patients after standard treatment: application of dynamic contrast-enhanced MR imaging , 2017, European Radiology.

[8]  G. Reifenberger,et al.  The 2016 World Health Organization Classification of Tumors of the Central Nervous System: a summary , 2016, Acta Neuropathologica.

[9]  Axel Montagne,et al.  Optimal acquisition and modeling parameters for accurate assessment of low Ktrans blood–brain barrier permeability using dynamic contrast‐enhanced MRI , 2016, Magnetic resonance in medicine.

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

[11]  H. Fine,et al.  Glioma Angiogenesis and Perfusion Imaging: Understanding the Relationship between Tumor Blood Volume and Leakiness with Increasing Glioma Grade , 2015, American Journal of Neuroradiology.

[12]  Dimitrios I. Fotiadis,et al.  Machine learning applications in cancer prognosis and prediction , 2014, Computational and structural biotechnology journal.

[13]  Amy S Nowacki,et al.  Residual tumor volume versus extent of resection: predictors of survival after surgery for glioblastoma. , 2014, Journal of neurosurgery.

[14]  Joanna M. Wardlaw,et al.  Assessment of blood–brain barrier disruption using dynamic contrast-enhanced MRI. A systematic review , 2014, NeuroImage: Clinical.

[15]  Jill S. Barnholtz-Sloan,et al.  Epidemiologic and Molecular Prognostic Review of Glioblastoma , 2014, Cancer Epidemiology, Biomarkers & Prevention.

[16]  Scott N. Hwang,et al.  Outcome prediction in patients with glioblastoma by using imaging, clinical, and genomic biomarkers: focus on the nonenhancing component of the tumor. , 2014, Radiology.

[17]  L. Deangelis,et al.  Glioblastoma and other malignant gliomas: a clinical review. , 2013, JAMA.

[18]  Rajan Jain,et al.  Measurements of tumor vascular leakiness using DCE in brain tumors: clinical applications , 2013, NMR in biomedicine.

[19]  Xiujie Wang,et al.  Hypoxia and hypoxia-inducible factors in glioblastoma multiforme progression and therapeutic implications. , 2012, Experimental cell research.

[20]  Nader Sanai,et al.  The Value of Glioma Extent of Resection in the Modern Neurosurgical Era , 2012, Front. Neur..

[21]  J P B O'Connor,et al.  Imaging biomarkers of angiogenesis and the microvascular environment in cerebral tumours. , 2011, The British journal of radiology.

[22]  Heinrich Lanfermann,et al.  Multimodality Assessment of Brain Tumors and Tumor Recurrence , 2011, The Journal of Nuclear Medicine.

[23]  D. Collins,et al.  Diffusion-weighted MRI in the body: applications and challenges in oncology. , 2007, AJR. American journal of roentgenology.

[24]  Daniel J Brat,et al.  'Pseudopalisading' Necrosis in Glioblastoma: A Familiar Morphologic Feature That Links Vascular Pathology, Hypoxia, and Angiogenesis , 2006, Journal of neuropathology and experimental neurology.

[25]  Daniel J Brat,et al.  Hypoxia and the hypoxia-inducible-factor pathway in glioma growth and angiogenesis. , 2005, Neuro-oncology.

[26]  Yu-Ting Kuo,et al.  Distinction between high-grade gliomas and solitary metastases using peritumoral 3-T magnetic resonance spectroscopy, diffusion, and perfusion imagings , 2004, Neuroradiology.

[27]  Daniel J Brat,et al.  Pseudopalisades in Glioblastoma Are Hypoxic, Express Extracellular Matrix Proteases, and Are Formed by an Actively Migrating Cell Population , 2004, Cancer Research.

[28]  D. Mikulis,et al.  Diagnostic value of peritumoral minimum apparent diffusion coefficient for differentiation of glioblastoma multiforme from solitary metastatic lesions. , 2011, AJR. American journal of roentgenology.