Data-driven Grading of Brain Gliomas: A Multiparametric MR Imaging Study

Caulo, Massimo; Panara, Valentina; Tortora, Domenico; Mattei, Peter A.; Briganti, C.; Pravatà, Emanuele; Salice, Simone; Cotroneo, Antonio Raffaele; Tartaro, Armando

doi:10.1148/radiol.14132040

Cited by 86 publications

(82 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The differential contrast afforded by multiparametric MR imaging has not been exploited to its full potential. Several preliminary studies have begun to address these issues, and initial results appear promising (15)(16)(17).…”

Section: Study Populationmentioning

confidence: 99%

Prognostic Imaging Biomarkers in Glioblastoma: Development and Independent Validation on the Basis of Multiregion and Quantitative Analysis of MR Images

Cui¹,

et al. 2016

View full text Add to dashboard Cite

).q RSNA, 2015 Purpose:To develop and independently validate prognostic imaging biomarkers for predicting survival in patients with glioblastoma on the basis of multiregion quantitative image analysis. Materials and Methods:This retrospective study was approved by the local institutional review board, and informed consent was waived. A total of 79 patients from two independent cohorts were included. The discovery and validation cohorts consisted of 46 and 33 patients with glioblastoma from the Cancer Imaging Archive (TCIA) and the local institution, respectively. Preoperative T1-weighted contrast material-enhanced and T2-weighted fluid-attenuation inversion recovery magnetic resonance (MR) images were analyzed. For each patient, we semiautomatically delineated the tumor and performed automated intratumor segmentation, dividing the tumor into spatially distinct subregions that demonstrate coherent intensity patterns across multiparametric MR imaging. Within each subregion and for the entire tumor, we extracted quantitative imaging features, including those that fully capture the differential contrast of multimodality MR imaging. A multivariate sparse Cox regression model was trained by using TCIA data and tested on the validation cohort. Results:The optimal prognostic model identified five imaging biomarkers that quantified tumor surface area and intensity distributions of the tumor and its subregions. In the validation cohort, our prognostic model achieved a concordance index of 0.67 and significant stratification of overall survival by using the log-rank test (P = .018), which outperformed conventional prognostic factors, such as age (concordance index, 0.57; P = .389) and tumor volume (concordance index, 0.59; P = .409). Conclusion:The multiregion analysis presented here establishes a general strategy to effectively characterize intratumor heterogeneity manifested at multimodality imaging and has the potential to reveal useful prognostic imaging biomarkers in glioblastoma.q RSNA, 2015

show abstract

Section: Study Populationmentioning

confidence: 99%

Prognostic Imaging Biomarkers in Glioblastoma: Development and Independent Validation on the Basis of Multiregion and Quantitative Analysis of MR Images

Cui¹,

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The highest CBV values were obtained, and the rCBV max normalization to the contralateral unaffected white matter CBV value was based on previously published methods. 1,23,24 Measurements were performed by 2 neuroradiologists (H.-Y.K. and J.-Q.F).…”

Section: Rcbv Measurementsmentioning

confidence: 99%

“…1 The final step was a calculation of the mean values generated from the 4 measurements made by the 2 independent observers. The VSI color map of grade II gliomas is represented in blue-green, denoting low VSI values (VSI mean and VSI max values, 42.96 Ϯ 26.43 m and 79.10 Ϯ 29.17 m, respectively); however, the CBV maps of the 2 cases of grade II oligodendrogliomas are represented in red (Fig 1).…”

Section: Characteristics Of Vsi and Rcbv In Gliomas With Different Grmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of the Effect of Vessel Size Imaging and Cerebral Blood Volume Derived from Perfusion MR Imaging on Glioma Grading

Hj¹,

Xiao²,

Chen³

et al. 2015

AJNR Am J Neuroradiol

View full text Add to dashboard Cite

BACKGROUND AND PURPOSE:Vascular proliferation is a major criterion for grading gliomas on the basis of histology. Relative cerebral blood volume can provide pathophysiologic information about glioma grading. Vessel size imaging, in some animals, can be used to estimate the microvascular caliber of a glioma, but its clinical use remains unclear. Herein, we aimed to compare the predictive power of relative cerebral blood volume and vessel size imaging in glioma grading, with grading based on histology.

show abstract

“…The choice of the window sizes ( ) for different metabolites can influence the performance of the system. In addition, the window size must be kept small to avoid Sym1 [1][2][3][4][5][6][7][8][9][10][11][12] 83.2% ± 1.6% 92.5% (with Sym1 and 7 or 9 levels of decomposition) Sym2 [1][2][3][4][5][6][7][8][9][10][11][12] 83.2% ± 1.6% Sym3 [1][2][3][4][5][6][7][8][9][10][11][12] 83.1% ± 1.6% Table 2). The window size for each metabolite was varied in turn with the window sizes of the remaining metabolites kept fixed, and inherent to this process is the assumption that the window sizes are independent in terms of optimisation.…”

Section: B Feature Extractionmentioning

confidence: 99%

Discrete Wavelet Transform-Based Whole-Spectral and Subspectral Analysis for Improved Brain Tumor Clustering Using Single Voxel MR Spectroscopy

Yang

Nawaz

Barrick

et al. 2015

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Abstract-Many approaches have been considered for automatic grading of brain tumours by means of pattern recognition with magnetic resonance spectroscopy (MRS). Providing an improved technique which can assist clinicians in accurately identifying brain tumour grades is our main objective. The proposed technique, which is based on the discrete wavelet transform (DWT) of whole-spectral or subspectral information of key metabolites, combined with unsupervised learning, inspects the separability of the extracted wavelet features from the MRS signal to aid the clustering. In total, we included 134 short echo time single voxel MRS spectra (SV MRS) in our study that cover normal controls, low grade and high grade tumours. The combination of DWT-based whole-spectral or sub-spectral analysis and unsupervised clustering achieved an overall clustering accuracy of 94.8% and a balanced error rate of 7.8%. To the best of our knowledge, it is the first study using DWT combined with unsupervised learning to cluster brain SV MRS. Instead of dimensionality reduction on SV MRS or feature selection using model fitting, our study provides an alternative method of extracting features to obtain promising clustering results.

show abstract

Data-driven Grading of Brain Gliomas: A Multiparametric MR Imaging Study

Abstract: A quantitative multiparametric MR imaging evaluation that incorporated heterogeneity at MR imaging significantly improved discrimination between low- and high-grade brain gliomas with a very high AUC (ie, 0.95), thus reducing the risk of inappropriate or delayed surgery, respectively.

Cited by 86 publications

References 27 publications

Prognostic Imaging Biomarkers in Glioblastoma: Development and Independent Validation on the Basis of Multiregion and Quantitative Analysis of MR Images

Prognostic Imaging Biomarkers in Glioblastoma: Development and Independent Validation on the Basis of Multiregion and Quantitative Analysis of MR Images

Comparison of the Effect of Vessel Size Imaging and Cerebral Blood Volume Derived from Perfusion MR Imaging on Glioma Grading

Discrete Wavelet Transform-Based Whole-Spectral and Subspectral Analysis for Improved Brain Tumor Clustering Using Single Voxel MR Spectroscopy

Contact Info

Product

Resources

About