Evaluation of tumor‐derived MRI‐texture features for discrimination of molecular subtypes and prediction of 12‐month survival status in glioblastoma

Yang, Dalu; Rao, Ganesh; Martinez, Juan; Veeraraghavan, Ashok; Rao, Arvind

doi:10.1118/1.4934373

Cited by 136 publications

(102 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…22,[35][36][37] This study is also related to recent work establishing a link between image features, based on spatial habitats 38 and texture (i.e. fractal texture analysis, histogram of oriented gradients, run length, local binary patterns and Haralick features) 39 and the 12-month survival status of patients with GBM. In comparison with these studies, our analysis focuses on the morphological characteristics of GBM tumours occurring in regions corresponding to necrosis, oedema and active tumour.…”

Section: Discussionmentioning

confidence: 99%

A quantitative study of shape descriptors from glioblastoma multiforme phenotypes for predicting survival outcome

Chaddad¹,

Desrosiers²,

Hassan³

et al. 2016

The British Journal of Radiology

View full text Add to dashboard Cite

Objective: Predicting the survival outcome of patients with glioblastoma multiforme (GBM) is of key importance to clinicians for selecting the optimal course of treatment. The goal of this study was to evaluate the usefulness of geometric shape features, extracted from MR images, as a potential non-invasive way to characterize GBM tumours and predict the overall survival times of patients with GBM. Methods: The data of 40 patients with GBM were obtained from the Cancer Genome Atlas and Cancer Imaging Archive. The T 1 weighted post-contrast and fluid-attenuated inversion-recovery volumes of patients were co-registered and segmented into delineate regions corresponding to three GBM phenotypes: necrosis, active tumour and oedema/invasion. A set of two-dimensional shape features were then extracted slicewise from each phenotype region and combined over slices to describe the three-dimensional shape of these phenotypes. Thereafter, a Kruskal–Wallis test was employed to identify shape features with significantly different distributions across phenotypes. Moreover, a Kaplan–Meier analysis was performed to find features strongly associated with GBM survival. Finally, a multivariate analysis based on the random forest model was used for predicting the survival group of patients with GBM. Results: Our analysis using the Kruskal–Wallis test showed that all but one shape feature had statistically significant differences across phenotypes, with p-value < 0.05, following Holm–Bonferroni correction, justifying the analysis of GBM tumour shapes on a per-phenotype basis. Furthermore, the survival analysis based on the Kaplan–Meier estimator identified three features derived from necrotic regions (i.e. Eccentricity, Extent and Solidity) that were significantly correlated with overall survival (corrected p-value < 0.05; hazard ratios between 1.68 and 1.87). In the multivariate analysis, features from necrotic regions gave the highest accuracy in predicting the survival group of patients, with a mean area under the receiver-operating characteristic curve (AUC) of 63.85%. Combining the features of all three phenotypes increased the mean AUC to 66.99%, suggesting that shape features from different phenotypes can be used in a synergic manner to predict GBM survival. Conclusion: Results show that shape features, in particular those extracted from necrotic regions, can be used effectively to characterize GBM tumours and predict the overall survival of patients with GBM. Advances in knowledge: Simple volumetric features have been largely used to characterize the different phenotypes of a GBM tumour (i.e. active tumour, oedema and necrosis). This study extends previous work by considering a wide range of shape features, extracted in different phenotypes, for the prediction of survival in patients with GBM.

show abstract

Section: Discussionmentioning

confidence: 99%

A quantitative study of shape descriptors from glioblastoma multiforme phenotypes for predicting survival outcome

Chaddad¹,

Desrosiers²,

Hassan³

et al. 2016

The British Journal of Radiology

View full text Add to dashboard Cite

show abstract

“…A major reason is that most groups use nonlocalizing biopsies to determine a single representative profile for an entire tumor. 11,[13][14][15][16][17][18][19][20][21] By definition, this does not account for the genetic diversity throughout the various tumor subregions. Also, most biopsies originate from MRI enhancement per routine surgical practice, so tumor profiles from the nonenhancing BAT are typically under-represented.…”

Section: Introductionmentioning

confidence: 99%

“…The textural patterns between voxel intensities and their surrounding neighbors provide further insight to tissue microstructure and the local environment. 11,12 Numerous studies have correlated both MRI signal and texture analysis with genetic profiles in GBM, 5,11,[13][14][15][16][17][18][19][20][21] yet these have been limited in resolving the challenge of GBM's intratumoral heterogeneity. A major reason is that most groups use nonlocalizing biopsies to determine a single representative profile for an entire tumor.…”

Section: Introductionmentioning

confidence: 99%

Radiogenomics to characterize regional genetic heterogeneity in glioblastoma

et al. 2016

View full text Add to dashboard Cite

Background. Glioblastoma (GBM) exhibits profound intratumoral genetic heterogeneity. Each tumor comprises multiple genetically distinct clonal populations with different therapeutic sensitivities. This has implications for targeted therapy and genetically informed paradigms. Contrast-enhanced (CE)-MRI and conventional sampling techniques have failed to resolve this heterogeneity, particularly for nonenhancing tumor populations. This study explores the feasibility of using multiparametric MRI and texture analysis to characterize regional genetic heterogeneity throughout MRI-enhancing and nonenhancing tumor segments. Methods. We collected multiple image-guided biopsies from primary GBM patients throughout regions of enhancement (ENH) and nonenhancing parenchyma (so called brain-around-tumor, [BAT]). For each biopsy, we analyzed DNA copy number variants for core GBM driver genes reported by The Cancer Genome Atlas. We co-registered biopsy locations with MRI and texture maps to correlate regional genetic status with spatially matched imaging measurements. We also built multivariate predictive decision-tree models for each GBM driver gene and validated accuracies using leave-one-out-cross-validation (LOOCV). Results. We collected 48 biopsies (13 tumors) and identified significant imaging correlations (univariate analysis) for 6 driver genes: EGFR, PDGFRA, PTEN, CDKN2A, RB1, and TP53. Predictive model accuracies (on LOOCV) varied by driver gene of interest. Highest accuracies were observed for PDGFRA (77.1%), EGFR (75%), CDKN2A (87.5%), and RB1 (87.5%), while lowest accuracy was observed in TP53 (37.5%). Models for 4 driver genes (EGFR, RB1, CDKN2A,

show abstract

“…[11][12][13][14] However, to our knowledge, only two works have studied twodimensional (2D) textural features for outcome assessment. 15,16 METHODS AND MATERIALS Patients This retrospective, three-centre (blinded for review) study was approved by the local institutional review boards (blinded for review). All subjects provided written informed consent at hospital admittance for research and treatment.…”

Section: Introductionmentioning

confidence: 99%

“…This fact can be due to the 3D analysis developed, which translates into an averaged nondirectional mapping of tumour heterogeneity, instead of most standard 2D analyses, where different distances or directions lead to different matrices with partial information. 15,16 However, according to Ng et al, 29 whole-tumour analysis was indeed better than single cross-section analysis in separating the Kaplan-Meier survival curve in colorectal cancer, for which they concluded that whole-tumour analysis seems to be more representative of tumour heterogeneity. 30 Moreover, among these texture features, entropy is found again, which reflects the unpredictability of the information content of an image.…”

mentioning

confidence: 99%

Tumour heterogeneity in glioblastoma assessed by MRI texture analysis: a potential marker of survival

Melodelima¹,

Pérez-Beteta²,

Luque³

et al. 2016

BJR

View full text Add to dashboard Cite

Objective: The main objective of this retrospective work was the study of three-dimensional (3D) heterogeneity measures of post-contrast pre-operative MR images acquired with T 1 weighted sequences of patients with glioblastoma (GBM) as predictors of clinical outcome. Methods: 79 patients from 3 hospitals were included in the study. 16 3D textural heterogeneity measures were computed including run-length matrix (RLM) features (regional heterogeneity) and co-occurrence matrix (CM) features (local heterogeneity). The significance of the results was studied using Kaplan-Meier curves and Cox proportional hazards analysis. Correlation between the variables of the study was assessed using the Spearman's correlation coefficient.Results: Kaplan-Meyer survival analysis showed that 4 of the 11 RLM features and 4 of the 5 CM features considered were robust predictors of survival. The median survival differences in the most significant cases were of over 6 months. Conclusion: Heterogeneity measures computed on the post-contrast pre-operative T 1 weighted MR images of patients with GBM are predictors of survival. Advances in knowledge: Texture analysis to assess tumour heterogeneity has been widely studied. However, most works develop a two-dimensional analysis, focusing only on one MRI slice to state tumour heterogeneity. The study of fully 3D heterogeneity textural features as predictors of clinical outcome is more robust and is not dependent on the selected slice of the tumour. INTRODUCTIONGlioblastoma (GBM) is the most frequent malignant brain tumour in adults and the most lethal type, with a median survival of 14.6 months for patients receiving the standard of care, i.e. maximal safe surgery plus radiotherapy and chemotherapy.1 Pre-operative MRI is routinely used for diagnosis, treatment planning, response evaluation and follow-up.The typical GBM appearance upon diagnosis on MRI consists of an enhanced ring with a central non-enhanced core of necrosis observed mainly on contrast-enhanced T 1 weighted images. Recently, there has been an increased use of advanced imaging techniques alone or in combination with conventional MRI modalities to characterize the connection of the so-called radio phenotype with the tumour genotype, the so-called radiogenomics (e.g. recent reviews for GBM 2,3 ). However, the use of those techniques requires further research and validation to achieve a broad clinical applicability. Thus, in clinical practice and trials, T 1 contrast-enhanced and T 2 /fluid-attenuated inversionrecovery images are still the gold standard for diagnosis and treatment planning. 4 One of the most important characteristics of GBM is its marked intratumour heterogeneity. In fact, these tumours are usually referred to as "glioblastoma multiforme", in order to highlight their heterogeneous nature. GBM tumours are formed by tumour cells which differ in their morphology, genetics and biological behaviour and may underlie the inability of conventional therapies to significantly impact patient outcomes.5 It is well known that ...

show abstract

Evaluation of tumor‐derived MRI‐texture features for discrimination of molecular subtypes and prediction of 12‐month survival status in glioblastoma

Cited by 136 publications

References 51 publications

A quantitative study of shape descriptors from glioblastoma multiforme phenotypes for predicting survival outcome

A quantitative study of shape descriptors from glioblastoma multiforme phenotypes for predicting survival outcome

Radiogenomics to characterize regional genetic heterogeneity in glioblastoma

Tumour heterogeneity in glioblastoma assessed by MRI texture analysis: a potential marker of survival

Contact Info

Product

Resources

About