Abstract
Introduction
Being the most common primary brain tumor, glioblastoma presents as an extremely challenging malignancy to treat with dismal outcomes despite treatment. Varying molecular epidemiology of glioblastoma between patients and intra-tumoral heterogeneity explains the failure of current one-size-fits-all treatment modalities. Radiomics uses machine learning to identify salient features of the tumor on brain imaging and promises patient-specific management in glioblastoma patients.
Methods
We performed a comprehensive review of the available literature on studies investigating the role of radiomics and radiogenomics models for the diagnosis, stratification, prognostication as well as treatment planning and monitoring of glioblastoma.
Results
Classifiers based on a combination of various MRI sequences, genetic information and clinical data can predict non-invasive tumor diagnosis, overall survival and treatment response with reasonable accuracy. However, the use of radiomics for glioblastoma treatment remains in infancy as larger sample sizes, standardized image acquisition and data extraction techniques are needed to develop machine learning models that can be translated effectively into clinical practice.
Conclusion
Radiomics has the potential to transform the scope of glioblastoma management through personalized medicine.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
Glioblastoma
Glioblastoma has an incidence of 3.22 per 100,000 and median overall survival (OS) of 14.6 months following standard treatment, which includes a combination of surgical resection, radiation therapy and chemotherapy [1]. This “one-size-fits-all” model for the treatment of glioblastoma is now being questioned following research on various pathways implied in intratumoral heterogeneity, arising as a result of genetic and epigenetic makeup, levels of protein expression, metabolic or bioenergetic behavior, microenvironment biochemistry and structural composition [2]. Consequently, features differ on histopathology and imaging across patients as well as spatially throughout a single tumor [3,4,5]. Personalized treatment protocols targeting individual patients’ tumor characteristics are thus being increasingly advocated for improved success rates in glioblastoma management [4, 6, 7].
Radiomics and radiogenomics
Radiomics is an emerging application of neuroimaging where advanced computational methods are used to quantitatively extract characteristics from clinical images that are too complex for a human eye to appreciate [8, 9]. These imaging characteristics, called “features” reflect tumor characteristics and inner organization as well as the tumor microenvironment [9]. Radiomics is a multi-step process including the acquisition and preprocessing of images, segmentation, feature extraction and selection, and advanced statistics using machine learning (ML) algorithms (Fig. 1). The pipeline of radiomics is highly collaborative and involves contributions from clinicians, molecular biologists, statisticians, and bioengineers [8].
Radiomics-derived imaging phenotypes are associated with molecular markers to create ‘radiogenomics’ models [5]. It is a rapid and reproducible tool to evaluate tumor subtype, mutation status and intratumoral heterogeneity; and non-invasively predicts tumor progression, survival and response to targeted therapies using these characteristics [5, 8]. Radiogenomics offers more information as opposed to surgical biopsy in view of spatial tumor heterogeneity [8], especially useful for genomic profiling in recurrent glioblastoma which is driven by different clonal populations with varying hypermutations and evasion mechanisms [10]. Thus, clinical decision support systems using radiomics will form the base for precision medicine [9].
Applications of radiomics in glioblastoma management
Radiomics analysis has been widely studied for its use in subtyping brain tumors, predicting prognosis and treatment planning, supporting its potential use as a biomarker. Combining radiomics analysis with clinical and genetic information can remarkably enhance the utility of these models.
Diagnosis and classification of glioblastoma
Simple features on structural MRI such as tumor size, location and enhancement patterns have been used to predict histopathological subtypes of glioblastoma. Extracting complex features using image-processing software and combining with advanced MRI modalities can further improve the accuracy of these models (Table 1).
Tumor location
It is well known that the location of the tumor affects the outcomes in patients with glioblastoma. A “probabilistic radiographic atlas” of more than 500 glioblastoma patients showed associations between stereospecific frequency of tumor occurrence with age, extent of resection, genetic expression, and survival data. Interestingly, regions closer to subventricular zone were seen to have MGMT unmethylated, mesenchymal, and EGFR-amplified tumors [17], supporting their invasive nature and poor prognosis [38]. Another study showed correlation of tumor phenotypes with their spatial distribution [30]. A comparison between solitary and multicentric glioblastoma revealed upregulation of genes responsible for tumor cell motility and invasiveness and poor prognosis in the multicentric radiophenotype [22]. Thus, tumor location and multicentricity can give important clues to the cell of origin and tumor behavior.
Tumor size and contrast enhancement patterns
The correlation between tumor sizes and volume of different components (enhancing, necrosis and edema) is well established [27]. Previously, ‘VASARI’, a semi-quantitative feature set including tumor volumes, was employed to predict tumor subtypes and survival [15, 39]. In the VAK classification, a scoring system was developed to create phenotypes using tumor volumetry in combination with age and KPS annotation (Fig. 2) [35]. Volumetry was incorporated in a radiogenomics model where it was combined with DNA microarray analysis to train classifiers that can predict gene-expression patterns and survival. They showed that a high ratio of contrast-enhancing volume to the necrotic tumor volume (C:N) could predict overexpression of EGFR, an important therapeutic target [40]. In another radiogenomic study based on The Cancer Genome Atlas (TCGA) data, stratification into high and low FLAIR radiophenotypes reflected underlying edema and cellular invasion in glioblastoma, as they were associated with genes and microRNAs involved in cancer and cellular migration [36]. MRI volumetric features are predictive of several cancer-relevant, drug-targetable DNA mutations in glioblastoma. TP53, RB1, NF1, EGFR, and PDGFRA mutations could each be significantly predicted by at least one imaging feature [18]. These studies provide a basis for genomic profiling and non-invasively selecting patients for personalized therapies using tumor volumetry.
Radiomics can be used to distinguish solitary brain metastasis from glioblastoma on structural MRI. Artzi et al. developed an excellent classifier (AUC 0.96) with support vector machine (SVM) using post-contrast T1 weighted (T1CE) MRI. However, performance decreased when subtypes of brain metastasis were attempted to classify [11]. In another study, contrast-enhancing and peritumoral hyperintense masks in T2-weighted (T2W) MRI-based deep learning model showed best performance (area under curve AUC 0.956) compared to the traditional machine learning model (AUC 0.890) and human readers (AUC 0.774) [12]. However, when Shin et al. utilized both T1CE and T2W sequences to develop a 2D CNN, they only achieved reasonable accuracy implying no clear benefit of combining the two modalities [37].
Texture
Texture is a chief radiomic feature utilized for glioblastoma phenotyping. In one study, a gray-level co-occurrence matrix (GLCM) approach was employed for extracting phenotypic texture features for necrosis, active tumor, and edema on structural MRI. Features were significant predictors (p value < 0.01) of prognosis but in areas of active tumor only [41]. Another study was able to predict MGMT methylation status using space-frequency texture analysis based on the S-transform in T2W MRI, albeit with an accuracy of 71%, requiring better algorithms [16]. Other studies based on texture features were able to predict MGMT methylation status with reasonable accuracy [21, 20].
Occasionally, high‐grade gliomas (WHO Grade III and glioblastoma) may have the same MRI appearance as low-grade gliomas. Classifiers using texture along with size, shape, intensity, and histogram features can be used to differentiate low-grade from high-grade gliomas. Performance of these classifiers varies with the algorithm used, the best performance was observed with SVM (AUC 0.932) and Random forest (AUC 0.921) [28, 14].
Advanced MRI sequences and multimodal analyses
Advanced sequences such as Diffusion and Perfusion MRI have been extensively used in brain tumors to evaluate invasiveness, angiogenesis, and tumor behavior. Raw tumor features from structural MRI and delta-radiomic features from dynamic susceptibility contrast (DSC) perfusion MRI were extracted to differentiate low-grade gliomas from high-grade gliomas. This classifier reached an AUC of 0.94 [19]. However, a Cochrane meta-analysis on 7 studies to differentiate untreated solid and non‐enhancing low-grade from high-grade gliomas using DSC MRI features (rCBV and Ktrans) reported wide range of estimates for both sensitivity and specificity, making these parameters less reliable [42]. Diffusion MRI was employed to compare the expression of various genes between the high- versus low- Apparent Diffusion Coefficient (ADC) tumors in a subset of patients. High-ADC tumors were found to have higher expression of 13 genes, 6 of which encode for extracellular matrix (ECM) molecules including collagen or collagen-binding proteins, suggesting a role of these genes in pro-invasive phenotype [29]. In another study, physiologic MRI was correlated with stereotactic image-guided biopsies to differentiate contrast-enhancing and nonenhancing tumor areas. DSC MRI was useful for identifying tissue specimens with higher tumor proliferation, necrosis, and vascular hyperplasia in the contrast-enhancing component of the lesion, while diffusion MRI may be useful to detect infiltrating tumors in the non-enhancing region. This is of particular interest for defining tumor burden in non-enhancing regions, where distinguishing reactive edema from biologically active infiltrative tumor is clinically important. In this study, accuracy of the results could be confounded by the misregistration arising as a result of brain shift [13].
MR imaging features of Primary CNS Lymphoma (PCNSL) and glioblastoma overlap, with differing survival outcomes and treatment options. In a study where perfusion and diffusion-weighted MRI were used to differentiate glioblastoma from lymphoma, mean ADC and plasma volume (rVp) were higher in the glioblastoma compared to PCNSL. Moreover, mean ADC was superior (AUC 0.83) to rVp and permeability transfer constant (Ktrans). This was true for contrast-enhancing regions only, possibly due to increases in tumor cellularity, microvascular permeability, and vascular proliferation [25]. In another study, ADC was outperformed by a multi-parametric (T1WCE, post-contrast T2W and FLAIR) and multiregional radiomics classifier with AUC 0.921 [26]. This questions the benefit of including advanced sequences in classifier in the presence of conventional MRI.
Other studies have explored the utility of multiparametric MRI to create more accurate radiomic models for tumor subtyping, grading and predicting mutational status. Rathore et al. used 267 multiparametric MRI based radiomic features, extracted from T1-weighted (T1W), T2W, T1CE, T2 FLAIR, DSC, and DTI to subtype de novo glioblastoma into three imaging phenotypes. For example, the solid subtype was characterized by highly uniform vascularization, highest cell densities, small-sized edema, moderately spherical and well-circumscribed appearance, with peritumoral edematous tissue having signs of heterogeneous neovascularization. This subtype had a predilection for the right temporal lobe and was associated with the worst prognosis. A personalized treatment regimen would involve very aggressive peritumoral resection and radiation dose escalation in these tumors [30]. Combining various MRI sequences can also improve classifier accuracy for tumor grading [32, 34]. Classifier performance also increased using MRI features from multiregional and multiparametric structural MRI to predict MGMT methylation status in glioblastoma [33, 24]. Similarly, IDH 1 mutation status was predicted using radiomic features on multiparametric MRI with enhanced accuracy when age and multiple regions were included [23].
Prognostication of glioblastoma
It is increasingly important for physicians to understand an individual patient’s prognosis and adjust their therapy accordingly. For this reason, a large number of studies aimed to predict outcomes using radiomics alone and augmented with clinical data, genomics, and proteomics can be used. (Table 2).
Conventional MRI features
Studies have used various features extracted from conventional MRI to predict patient outcomes in glioblastoma. Longer median survival was associated with higher sphericity, surface-to-volume ratio and edge enhancement of glioblastoma lesions on T1W MRI [54]. Lao et. al divided features into ‘handcrafted features’ and ‘deep features’ to create a feature signature, which when coupled with clinical risk factors such as age and Karnofsky Performance Score, was able to predict overall survival (OS). Compared with the predictive ability of traditional risk factors, the proposed feature signature achieved a superior prediction of OS (C-index = 0.739) [49]. Similar combined models reached C-index of 0.974 [56].
Texture, tumor shape and volumetric features were extracted, and combined with age to produce a model that would predict short-term, mid-term, and long-term OS [56, 53]. Zhou et al. went one step further and identified spatial-based characteristics from tumor sub-regions that can be used to predict survival time in patients [57]. Similarly, Chaddad et al. found three texture features extracted from active part of the tumors that significantly predicted survival outcomes compared to the necrotic and edematous parts [41]. Moreover, these radiomic models could predict survival in different molecular subtypes as well [55]. Addition of location-based features of brain tumors to radiomic features extracted from conventional MRI enhanced the ability of a model to predict OS of patients by 9%. Furthermore, classifying groups according to resection status can also increase the accuracy of such prediction models [58]. Verma et al. used MRI features to create a radiomics risk score for predicting PFS. With a concordance index of 0.80, these features also correlated well with histopathologic attributes associated with glioblastoma aggressiveness. Such scores can be easily utilized in clinical settings [59].
Advanced MRI features
Advanced MRI modalities have also been also explored to predict glioblastoma patient outcomes [52]. It was seen that high rCBV in the non-enhancing region of tumor was predictive of worsening OS and Progression-free Survival (PFS) [48]. ADC histogram analysis was useful to predict PFS in newly diagnosed as well as recurrent glioblastoma [29, 60]. In these studies, low ADC predicted poor outcomes. Models incorporating both conventional and advanced MRI sequences may show better performance at predicting the prognosis.
Radiogenomics and proteomics
MGMT promoter hypermethylation is associated with better prognosis and response to therapy. This mutational status alongwith IDH has been combined with radiomic features from structural MRI to stratify patients based on overall survival producing more robust radiomics-based prognostic models [44, 51]. Zinn et al. stratified VAK annotated cases further with molecular signatures and found a 10.5 months’ additional survival benefit for the group with MGMT promoter methylation [15]. In another study, glioblastomas were first divided into groups based on vascularization (rCBV values). It was seen that MGMT methylation was a positive predictive factor for OS (p = 0.003, AUC = 0.70) in the moderately vascularized tumors. However, there was no significant effect of MGMT methylation in the highly vascularized tumors (p = 0.10, AUC = 0.56) [45]. Contrastingly, some studies did not find any significant association of prognosis with MGMT promoter hypermethylation [54, 31]. This could be due to insufficient feature selection methods.
Integrative models promise a reduction in prediction errors [44, 43]. Chaddad et al. created multi-omic integrative model using radiomic, clinical, protein expression and genetic features to predict the outcome for IDH1 wild-type glioblastoma patients which reached AUC of 78.24% [61]. Liao et al. extracted First order and multi-dimensional features from segmented lesions on FLAIR MRI and gave a feature importance score for feature selection [50]. When combined with genetic expression, the Gradient Boosting Decision Tree model predicted both short-term and long-term survival with an accuracy of 0.81. While six metagenes showed significant interactive effects with image features, this study was limited by unavailability of complete genomic data [50].
Immunophenotypes in glioblastoma are important as they predict response to immunotherapy and outcomes. Hsu et al. used radiomic immunophenotyping models to predict patient prognosis [62]. They showed that the phenotype with the worst prognosis comprised highly enriched myeloid-derived suppressor cells and lowly enriched Cytotoxic T lymphocytes [62].
Treatment of glioblastoma
Studies have shown the benefit of radiomics analysis in planning surgical procedures, evaluating the dose of radiotherapy, predicting the effective dose of chemotherapeutic agents and stratifying patients who will benefit from therapy. After initiating therapies, radiomics can be used to differentiate mimicking entities like true progression, pseudoprogression and radionecrosis(Table 3).
Surgical resection
A study correlating tumor surface regularity on T1W MRI with OS of 165 glioblastoma patients who underwent surgical resection highlighted that patients with surface-regular tumors had a higher survival rate and benefit from total tumor resection as compared to surface-irregular tumor patients [62]. Gaw et al. created a hybrid model to predict tumor cell invasion preoperatively for more effective surgery and radiation planning. The hybrid model, comprising an ML component that was driven by imaging data and a mechanistic model of tumor growth called the Proliferation-Invasion (PI) model, outperformed the individual components [68]. Thus, radiomics can help plan a targeted and personalized surgical treatment.
Radiation therapy (RT) planning
Radiomics shows immense potential to guide precision radiotherapy. Prediction models can estimate the extent of tumor infiltration and can help identify areas that are at a higher risk of tumor recurrence for targeted RT [63, 76]. Rathore et al. worked on a method for estimating peritumoral edema infiltration using radiomics by testing on pre- and post-operative multimodal MRI sequences in 90 de novo glioblastoma patients and found that recurrent tumor regions revealed higher vascularity and cellularity when compared with the non-recurrent regions [76]. A similar study done on 31 de novo glioblastoma patients confirmed these findings and also highlighted the importance of using multiparametric pattern analysis methods for planning a focused treatment approach to decrease recurrence rate [63]. Radiomics can guide in planning radiation therapy dose escalation in areas with higher risk of tumor recurrence as well as increasing gross total resection. This method can also help prevent dose-related toxicities seen with RT, salvaging the neural tissue at lower risk areas from damage [77].
Chemotherapy with temozolomide (TMZ)
Chemotherapy with TMZ along with adjuvant RT increases median OS [78]. However, TMZ resistance arises due to tumor heterogeneity. Yan et al. confirmed the importance of radiomics analysis in predicting disease progression in 57 glioblastoma patients treated with TMZ post-surgery using structural, diffusion and perfusion MRI. The study found lower ADC, higher FLAIR and hyperintense signals on T1CE in areas with a higher risk of tumor progression [72]. Another study assessed the efficacy of deep-learning based survival-prediction in 118 patients undergoing concurrent chemoradiotherapy with temozolomide post-surgery using features from multimodal MRI.. It highlighted that both clinical and radiomic features should be used hand in hand to predict OS of glioblastoma patients [73]. This reiterates the importance of radiomic models for identification of suitable treatment regimens guided by predicted response.
Therapy with bevacizumab
Bevacizumab is a monoclonal antibody targeting vascular endothelial growth factor (VEGF) used in patients with recurrent glioblastoma. However, variations in genetic makeup of VEGF among individuals can lead to resistance to bevacizumab, limiting its use [47]. Radiomics analysis can provide important biomarkers for selecting patients who will benefit from this therapy. Pre-treatment T1W and T1CE MRI of patients with recurrent glioblastoma were used to develop radiomics-based predictors of survival and progression. This has utility as a low-cost instrument for identifying treatment response in these patients [47, 69]. Using ADC and CBV of 54 patients with recurrent glioblastoma that were treated with RT and temozolomide, and subsequently treated with bevacizumab, was effective in segregating patients into responders and non-responders to bevacizumab treatment [71]. In a more complex model, a stratification model was created which integrated the pre-treatment MRI radiomics signature, the interval between radiotherapy and diagnosis of brain necrosis, and the interval between diagnosis of brain necrosis and treatment with bevacizumab to predict which patients will benefit from bevacizumab therapy for brain necrosis after radiotherapy. This model performed well with an AUC of 0.912 in the validation set [66].
Evaluating response to radiation therapy (RT) and chemotherapy
Radiotherapy can result in conditions that mimic true disease progression. Texture features derived from enhancing component and perilesional edema on structural MRI were used to differentiate pseudoprogression from true progression in glioblastoma [79]. Another model displayed a boost in accuracy when MGMT status was incorporated [65]. While these studies were based on post-RT MRI, pre-RT MRI scans may also predict the development of future pseudoprogression in glioblastoma patients [64]. Recent studies incorporated diffusion and perfusion MRI which reflect hypercellularity and hypervascularity to classify pseudoprogression.the accuracy is superior in these models than those based on conventional MRI alone [70, 67, 80]. Another post-RT effect that is difficult to differentiate from true progression is radiation necrosis. This can also be detected using ML classifiers based on traditional and delta radiomic features derived from MRI [74]. Pseudoprogression can also follow chemotherapy and radiomics offers hope in this regard. A clinio-radiomic classifier including multimodal MRI features was developed which showed an AUC of 0.80 [75].
Challenges in the clinical application of radiomics for glioblastoma
Despite the proven potential of radiomics in various aspects of glioblastoma management, these methods are yet to be introduced in mainstream clinical practice. Obstacles to translation include limited reproducibility of algorithms and less robust machine models. Formation of bodies to recommend standardization methods such as QIBA and QIN offer hope [81, 82].
Data availability and sharing
The majority of the studies exploring radiomics in glioblastoma are limited by small sample sizes. Biological variability of the tumor among patients explains why radiomics is still in its infancy. Promoting collaborative studies, sharing of data across institutions and making more high-quality datasets publicly available (such as Huiyihuiying Inc., BraTS, TCGA [83,84,85]) will result in more robust as well as reproducible models. This also requires overcoming the administrative and regulatory barriers to large-scale data sharing. In addition, clearly documenting the analysis and making original codes and data available will allow other investigators to replicate the results [62].
Image acquisition
The inclusion of retrospectively collected, multi-center data for clinical trials on radiomics is limited by variations across institutions in image acquisition such as the protocol defined by physicians, resolution, slice thickness, and washout period for contrast imaging of the acquired images [86]. Features extracted from MRI images can be influenced by field of view, field strength and slice thickness [87]. To combat the variability in the data collected, standardized steps are recommended following the image acquisition like intensity normalization, voxel re-slicing, use of a specific anatomical plane for multiparametric data, standardization of signal intensity prior to image listing, and developing algorithms for multiple MR modalities for image registration [86, 88, 89].
Segmentation and feature extraction
Although considered the highest standard for segmentation, manual segmentation of images is labor-intensive and increases risk of observer bias. In contrast, semi- and fully-automated methods can improve robustness and reproducibility [90]. Extracted features are dependent on the segmented region and tumor margins therefore segmentation is the key step [87]. While automated feature extraction has lower degree of variation in the scoring of semantic features [86], these methods can still lead to site-specific variations when obtaining imaging [86].
Machine learning models
Accuracy of ML models is limited by overfitting and underfitting. Overfitting of data occurs when doing feature extraction on high-dimensional, large-scale data [83]. However, it can be reduced by feature selection methods such as principal components analysis (PCA), sparse PCA, auto-encoders, etc. [91, 92]. Underfitting, due to small sample sizes, can be addressed using techniques like SMOTE [93].
Conclusion
Radiomics offers revolutionary changes in the scope of glioblastoma management through facilitating a personalized approach at various stages. Integrative models that include clinical, genetic and other molecular data can enhance the accuracy. The main limitation seen in most studies is the small sample size and the retrospective nature of these projects. Besides, variability in methods to generate data across institutions limits the generalizability in different patient populations. Whilst the results of these studies are promising, a key goal moving forward is to make these models more reproducible in a wide array of settings. Multicenter clinical trials are needed to translate these models and provide actual benefits to glioblastoma patients.
Data availability
Not applicable.
Code availability
Not applicable.
References
Tykocki T, Eltayeb M (2018) Ten-year survival in glioblastoma. A systematic Review. J Clin Neurosci 54:7–13
Hobbs SK, Shi G, Homer R, Harsh G, Atlas SW, Bednarski MD (2003) Magnetic resonance image-guided proteomics of human glioblastoma multiforme. J MagnReson Imaging 18(5):530–536
Ellingson BM (2015) Radiogenomics and imaging phenotypes in glioblastoma: novel observations and correlation with molecular characteristics. CurrNeurolNeurosci Rep 15(1):506
ElBanan MG, Amer AM, Zinn PO, Colen RR (2015) Imaging genomics of Glioblastoma: state of the art bridge between genomics and neuroradiology. Neuroimaging Clin N Am 25(1):141–153
Verduin M, Compter I, Steijvers D, Postma AA, Eekers DBP, Anten MM et al (2018) Noninvasive glioblastoma testing: multimodal approach to monitoring and predicting treatment response. Dis Markers 2018:2908609
Olar A, Aldape KD (2014) Using the molecular classification of glioblastoma to inform personalized treatment. J Pathol 232(2):165–177
Sotoudeh H, Shafaat O, Bernstock JD, Brooks MD, Elsayed GA, Chen JA et al (2019) Artificial intelligence in the management of glioma: era of personalized medicine. Front Oncol 9:768
Chaddad A, Kucharczyk MJ, Daniel P, Sabri S, Jean-Claude BJ, Niazi T, Abdulkarim B (2019) Radiomics in glioblastoma: current status and challenges facing clinical implementation. Front Oncol 21(9):374
Lambin P, Leijenaar RTH, Deist TM, Peerlings J, de Jong EEC, van Timmeren J et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14(12):749–762
Pinker K, Shitano F, Sala E, Do RK, Young RJ, Wibmer AG et al (2018) Background, current role, and potential applications of radiogenomics. J MagnReson Imaging 47(3):604–620
Artzi M, Bressler I, Bashat DB (2019) Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis. J Magn Reson Imaging 50(2):519–528
Bae S, An C, Ahn SS, Kim H, Han K, Kim SW et al (2020) Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation. Sci Rep 21:10
Barajas RF, Phillips JJ, Parvataneni R, Molinaro A, Essock-Burns E, Bourne G et al (2012) Regional variation in histopathologic features of tumor specimens from treatment-naive glioblastoma correlates with anatomic and physiologic MR Imaging. Neuro Oncol 14(7):942–954
Cho HH, Lee SH, Kim J, Park H (2018) Classification of the glioma grading using radiomics analysis. PeerJ. 22(6):e5982
Colen RR, Vangel M, Wang J, Gutman DA, Hwang SN, Wintermark M et al (2014) Imaging genomic mapping of an invasive MRI phenotype predicts patient outcome and metabolic dysfunction: a TCGA glioma phenotype research group project. BMC Med Genomics 2(7):30
Drabycz S, Roldán G, de Robles P, Adler D, McIntyre JB, Magliocco AM et al (2010) An analysis of image texture, tumor location, and MGMT promoter methylation in glioblastoma using magnetic resonance imaging. Neuroimage 49(2):1398–1405
Ellingson BM, Lai A, Harris RJ, Selfridge JM, Yong WH, Das K et al (2013) Probabilistic radiographic atlas of glioblastoma phenotypes. AJNR Am J Neuroradiol 34(3):533–540
Gutman DA, Dunn WD, Grossmann P, Cooper LAD, Holder CA, Ligon KL et al (2015) Somatic mutations associated with MRI-derived volumetric features in glioblastoma. Neuroradiology 57(12):1227–1237
Jeong J, Wang L, Ji B, Lei Y, Ali A, Liu T et al (2019) Machine-learning based classification of glioblastoma using delta-radiomic features derived from dynamic susceptibility contrast enhanced magnetic resonance images: Introduction. Quant Imaging Med Surg 9(7):1201–1213
Hajianfar G, Shiri I, Maleki H, Oveisi N, Haghparast A, Abdollahi H et al (2019) Noninvasive O6 methylguanine-DNA methyltransferase status prediction in glioblastoma multiforme cancer using magnetic resonance imaging radiomics features: univariate and multivariate radiogenomics analysis. World Neurosurg 1(132):e140–e161
Korfiatis P, Kline TL, Coufalova L, Lachance DH, Parney IF, Carter RE et al (2016) MRI texture features as biomarkers to predict MGMT methylation status in glioblastomas. Med Phys 43(6):2835–2844
Kong D-S, Kim J, Lee I-H, Kim ST, Seol HJ, Lee J-I et al (2016) Integrative radiogenomic analysis for multicentric radiophenotype in glioblastoma. Oncotarget 7(10):11526–11538
Lee MH, Kim J, Kim S-T, Shin H-M, You H-J, Choi JW et al (2019) Prediction of IDH1 mutation status in glioblastoma using machine learning technique based on quantitative radiomic data. World Neurosurg 125:e688–e696
Li Z-C, Bai H, Sun Q, Li Q, Liu L, Zou Y et al (2018) Multiregional radiomics features from multiparametric MRI for prediction of MGMT methylation status in glioblastoma multiforme: a multicentre study. EurRadiol 28(9):3640–3650
Lin X, Lee M, Buck O, Woo KM, Zhang Z, Hatzoglou V et al (2017) Diagnostic accuracy of T1-weighted DCE-MRI and DWI-ADC for differentiation of glioblastoma and primary CNS lymphoma. AJNR Am J Neuroradiol 38(3):485–491
Suh HB, Choi YS, Bae S, Ahn SS, Chang JH, Kang S-G et al (2018) Primary central nervous system lymphoma and atypical glioblastoma: differentiation using radiomics approach. EurRadiol 28(9):3832–3839
Naeini KM, Pope WB, Cloughesy TF, Harris RJ, Lai A, Eskin A et al (2013) Identifying the mesenchymal molecular subtype of glioblastoma using quantitative volumetric analysis of anatomic magnetic resonance images. Neuro Oncol 15(5):626–634
Nakamoto T, Takahashi W, Haga A, Takahashi S, Kiryu S, Nawa K et al (2019) Prediction of malignant glioma grades using contrast-enhanced T1-weighted and T2-weighted magnetic resonance images based on a radiomic analysis. Sci Rep 9(1):19411
Pope WB, Mirsadraei L, Lai A, Eskin A, Qiao J, Kim HJ et al (2012) Differential gene expression in glioblastoma defined by ADC histogram analysis: relationship to extracellular matrix molecules and survival. AJNR Am J Neuroradiol 33(6):1059–1064
Rathore S, Akbari H, Rozycki M, Abdullah KG, Nasrallah MP, Binder ZA et al (2018) Radiomic MRI signature reveals three distinct subtypes of glioblastoma with different clinical and molecular characteristics, offering prognostic value beyond IDH1. Sci Rep 8(1):5087
Sasaki T, Kinoshita M, Fujita K, Fukai J, Hayashi N, Uematsu Y et al (2019) Radiomics and MGMT promoter methylation for prognostication of newly diagnosed glioblastoma. Sci Rep 9(1):14435
Tian Q, Yan L-F, Zhang X, Zhang X, Hu Y-C, Han Y et al (2018) Radiomics strategy for glioma grading using texture features from multiparametric MRI. J MagnReson Imaging 48(6):1518–1528
Xi Y, Guo F, Xu Z, Li C, Wei W, Tian P et al (2018) Radiomics signature: A potential biomarker for the prediction of MGMT promoter methylation in glioblastoma. J Magn Reson Imaging 47(5):1380–1387
Zhang X, Yan L-F, Hu Y-C, Li G, Yang Y, Han Y et al (2017) Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features. Oncotarget 8(29):47816–47830
Zinn PO, Sathyan P, Mahajan B, Bruyere J, Hegi M, Majumder S et al (2012) A novel volume-age-KPS (VAK) glioblastoma classification identifies a prognostic cognate microRNA-gene signature. PLoS One. 7(8):e41522
Zinn PO, Mahajan B, Majadan B, Sathyan P, Singh SK, Majumder S et al (2011) Radiogenomic mapping of edema/cellular invasion MRI-phenotypes in glioblastoma multiforme. PLoS One. 6(10):e25451
Shin I, Kim H, Ahn SS, Sohn B, Bae S, Park JE, Kim HS, Lee SK (2021) Development and validation of a deep learning-based model to distinguish glioblastoma from solitary brain metastasis using conventional MR images. Am J Neuroradiol 42(5):838–844
Lim DA, Cha S, Mayo MC, Chen M-H, Keles E, VandenBerg S, Berger MS (2007) Relationship of glioblastoma multiforme to neural stem cell regions predicts invasive and multifocal tumor phenotype. Neuro Oncol 9(4):424–429
Gutman DA, Cooper LAD, Hwang SN, Holder CA, Gao J, Aurora TD et al (2013) MR imaging predictors of molecular profile and survival: multi-institutional study of the TCGA glioblastoma data set. Radiology 267(2):560–569
Diehn M, Nardini C, Wang DS, McGovern S, Jayaraman M, Liang Y et al (2008) Identification of noninvasive imaging surrogates for brain tumor gene-expression modules. Proc Natl AcadSci U S A 105(13):5213–5218
Chaddad A, Tanougast C (2016) Extracted magnetic resonance texture features discriminate between phenotypes and are associated with overall survival in glioblastoma multiforme patients. Med BiolEngComput 54(11):1707–1718
Abrigo JM, Fountain DM, Provenzale JM, Law EK, Kwong JS, Hart MG et al (2018) Magnetic resonance perfusion for differentiating low-grade from high-grade gliomas at first presentation. Cochrane Database Syst Rev. 1:CD011551
Beig N, Patel J, Prasanna P, Hill V, Gupta A, Correa R et al (2018) Radiogenomic analysis of hypoxia pathway is predictive of overall survival in Glioblastoma. Sci Rep 8(1):7
Choi Y, Nam Y, Jang J, Shin N-Y, Lee YS, Ahn K-J, et al (2020) Radiomics may increase the prognostic value for survival in glioblastoma patients when combined with conventional clinical and genetic prognostic models. EurRadiol.
Fuster-Garcia E, LorenteEstellés D, Álvarez-Torres M, Juan-Albarracín J, Chelebian E, Rovira A et al (2021) MGMT methylation may benefit overall survival in patients with moderately vascularized glioblastomas. EurRadiol 31(3):1738–47
Hsu JB-K, Lee GA, Chang T-H, Huang S-W, Le NQK, Chen Y-C, et al (2020) Radiomic immunophenotyping of GSEA-assessed immunophenotypes of glioblastoma and its implications for prognosis: a feasibility study. Cancers (Basel);12(10).
Kickingereder P, Götz M, Muschelli J, Wick A, Neuberger U, Shinohara RT et al (2016) Large-scale radiomic profiling of recurrent glioblastoma identifies an imaging predictor for stratifying anti-angiogenic treatment response. Clin Cancer Res 22(23):5765–5771
Jain R, Poisson LM, Gutman D, Scarpace L, Hwang SN, Holder CA et al (2014) Outcome prediction in patients with glioblastoma by using imaging, clinical, and genomic biomarkers: focus on the nonenhancing component of the tumor. Radiology 272(2):484–493
Lao J, Chen Y, Li Z-C, Li Q, Zhang J, Liu J et al (2017) A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme. Sci Rep 4:7
Liao X, Cai B, Tian B, Luo Y, Song W, Li Y (2019) Machine-learning based radiogenomics analysis of MRI features and metagenes in glioblastoma multiforme patients with different survival time. J Cell Mol Med 23(6):4375–4385
Molitoris JK, Rao YJ, Patel RA, Kane LT, Badiyan SN, Gittleman H et al (2017) Multi-institutional external validation of a novel glioblastoma prognostic nomogram incorporating MGMT methylation. J Neurooncol 134(2):331–338
Park JE, Kim HS, Jo Y, Yoo R-E, Choi SH, Nam SJ et al (2020) Radiomics prognostication model in glioblastoma using diffusion- and perfusion-weighted MRI. Sci Rep 10(1):4250
Sanghani P, Ang BT, King NKK, Ren H (2018) Overall survival prediction in glioblastoma multiforme patients from volumetric, shape and texture features using machine learning. SurgOncol 27(4):709–714
Tixier F, Um H, Bermudez D, Iyer A, Apte A, Graham MS et al (2019) Preoperative MRI-radiomics features improve prediction of survival in glioblastoma patients over MGMT methylation status alone. Oncotarget 10(6):660–672
Yang D, Rao G, Martinez J, Veeraraghavan A, Rao A (2015) Evaluation of tumor-derived MRI-texture features for discrimination of molecular subtypes and prediction of 12-month survival status in glioblastoma. Med Phys 42(11):6725–6735
Zhang X, Lu H, Tian Q, Feng N, Yin L, Xu X et al (2019) A radiomics nomogram based on multiparametric MRI might stratify glioblastoma patients according to survival. EurRadiol 29(10):5528–5538
Zhou M, Chaudhury B, Hall LO, Goldgof DB, Gillies RJ, Gatenby RA (2017) Identifying spatial imaging biomarkers of glioblastoma multiforme for survival group prediction. J MagnReson Imaging 46(1):115–123
Soltani M, Bonakdar A, Shakourifar N, Babaie R, Raahemifar K (2021) Efficacy of location-based features for survival prediction of patients with glioblastoma depending on resection status. Front Oncol 6(11):2509
Verma R, Correa R, Hill VB, Statsevych V, Bera K, Beig N, Mahammedi A, Madabhushi A, Ahluwalia M, Tiwari P (2020) Tumor habitat–derived radiomic features at pretreatment MRI that are prognostic for progression-free survival in glioblastoma are associated with key morphologic attributes at histopathologic examination: a feasibility study. Radiol Artificial Intelligence. 2(6):e190168
Pope WB, Lai A, Mehta R, Kim HJ, Qiao J, Young JR et al (2011) Apparent diffusion coefficient histogram analysis stratifies progression-free survival in newly diagnosed bevacizumab-treated glioblastoma. AJNR Am J Neuroradiol 32(5):882–889
Chaddad A, Daniel P, Sabri S, Desrosiers C, Abdulkarim B (2019) Integration of radiomic and multi-omic analyses predicts survival of newly diagnosed IDH1 wild-type glioblastoma. Cancers 11(8):1148
Pérez-Beteta J, Molina-García D, Ortiz-Alhambra JA, Fernández-Romero A, Luque B, Arregui E et al (2018) Tumor surface regularity at MR imaging predicts survival and response to surgery in patients with glioblastoma. Radiology 288(1):218–225
Akbari H, Macyszyn L, Da X, Bilello M, Wolf RL, Martinez-Lage M et al (2016) Imaging surrogates of infiltration obtained via multiparametric imaging pattern analysis predict subsequent location of recurrence of glioblastoma. Neurosurgery 78(4):572–580
Baine M, Burr J, Du Q, Zhang C, Liang X, Krajewski L et al (2021) The potential use of radiomics with pre-radiation therapy MR imaging in predicting risk of pseudoprogression in glioblastoma patients. J Imaging 7(2):17
Bani-Sadr A, Eker OF, Berner L-P, Ameli R, Hermier M, Barritault M, et al (2019) Conventional MRI radiomics in patients with suspected early- or pseudo-progression. Neuro-Oncol Adv;1(vdz019).
Cai J, Zheng J, Shen J, Yuan Z, Xie M, Gao M et al (2020) A Radiomics model for predicting the response to bevacizumab in brain necrosis after radiotherapy. Clin Cancer Res 26(20):5438–5447
Elshafeey N, Kotrotsou A, Hassan A, Elshafei N, Hassan I, Ahmed S et al (2019) Multicenter study demonstrates radiomic features derived from magnetic resonance perfusion images identify pseudoprogression in glioblastoma. Nat Commun 10(1):3170
Gaw N, Hawkins-Daarud A, Hu LS, Yoon H, Wang L, Xu Y et al (2019) Integration of machine learning and mechanistic models accurately predicts variation in cell density of glioblastoma using multiparametric MRI. Sci Rep 9(1):10063
Grossmann P, Narayan V, Chang K, Rahman R, Abrey L, Reardon DA et al (2017) Quantitative imaging biomarkers for risk stratification of patients with recurrent glioblastoma treated with bevacizumab. Neuro Oncol 19(12):1688–1697
Kim JY, Park JE, Jo Y, Shim WH, Nam SJ, Kim JH et al (2019) Incorporating diffusion- and perfusion-weighted MRI into a radiomics model improves diagnostic performance for pseudoprogression in glioblastoma patients. Neuro Oncol 21(3):404–414
Petrova L, Korfiatis P, Petr O, LaChance DH, Parney I, Buckner JC et al (2019) Cerebral blood volume and apparent diffusion coefficient - Valuable predictors of non-response to bevacizumab treatment in patients with recurrent glioblastoma. J Neurol Sci. 405:116433
Yan J-L, Li C, van der Hoorn A, Boonzaier NR, Matys T, Price SJ (2020) A Neural network approach to identify the peritumoral invasive areas in glioblastoma patients by using MR radiomics. Sci Rep 10(1):9748
Yoon HG, Cheon W, Jeong SW, Kim HS, Kim K, Nam H, et al (2020) Multi-Parametric Deep Learning Model for Prediction of Overall Survival after Postoperative Concurrent Chemoradiotherapy in Glioblastoma Patients. Cancers (Basel) [Internet];12(8)
Zhang Z, Yang J, Ho A, Jiang W, Logan J, Wang X et al (2018) A predictive model for distinguishing radiation necrosis from tumour progression after gamma knife radiosurgery based on radiomic features from MR images. EurRadiol 28(6):2255–2263
Patel M, Zhan J, Natarajan K, Flintham R, Davies N, Sanghera P, Grist J, Duddalwar V, Peet A, Sawlani V (2021) Machine learning-based radiomic evaluation of treatment response prediction in glioblastoma. Clin Radiol.
Rathore S, Akbari H, Doshi J, Shukla G, Rozycki M, Bilello M, Lustig RA, Davatzikos CA (2018) Radiomic signature of infiltration in peritumoral edema predicts subsequent recurrence in glioblastoma: implications for personalized radiotherapy planning. J Med Imaging. 5(2):021219
De Ruysscher D, Niedermann G, Burnet NG, Siva S, Lee AWM, Hegi-Johnson F (2019) Radiotherapy toxicity. Nat Rev Dis Primers 5(1):1–20
Lee SY (2016) Temozolomide resistance in glioblastoma multiforme. Genes Dis 3(3):198–210
Patel MD, Zhan J, Natarajan K, Flintham R, Davies N, Sanghera P, et al (2019) Radiomic evaluation of treatment response in patients with glioblastoma: a preliminary study. ECR 2019 EPOS. Eur Cong Radiol ECR; 2019
Elshafeey N, Kotrotsou A, GiniebraCamejo D, Abrol S, Hassan I, El Salek K, et al (2017) Multicenter study to demonstrate radiomic texture features derived from MR perfusion images of pseudoprogression compared to true progression in glioblastoma patients. JCO. ;35(15_suppl):2016–2016.
About the Quantitative Imaging Network (QIN) | Quantitative Imaging Network (QIN) | CIP Grant-supported Networks | Programs & Resources | Cancer Imaging Program (CIP) [Internet]. [cited 2021 Feb 20]. Available from: https://imaging.cancer.gov/programs_resources/specialized_initiatives/qin/about/teams.htm
Shukla-Dave A, Obuchowski NA, Chenevert TL, Jambawalikar S, Schwartz LH, Malyarenko D et al (2019) Quantitative imaging biomarkers alliance (QIBA) recommendations for improved precision of DWI and DCE-MRI derived biomarkers in multicenter oncology trials. J MagnReson Imaging 49(7):e101–e121
Medical Image Artificial Intelligence Cloud Platform - Huiyihuiying-Medical Image Artificial Intelligence Cloud Platform [Internet]. [cited 2021 Feb 22]. Available from: http://en.huiyihuiying.com/
Menze BH, Jakab A, Bauer S, Kalpathy-Cramer J, Farahani K, Kirby J et al (2015) The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging 34(10):1993–2024
The Cancer Genome Atlas Program - National Cancer Institute [Internet]. 2018 [cited 2021 Feb 22]. Available from: https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga
Narang S, Lehrer M, Yang D, Lee J, Rao A (2016) Radiomics in glioblastoma: current status, challenges and potential opportunities. Transl Cancer Res 5(4):383–397
Avanzo M, Stancanello J, El Naqa I (2017) Beyond imaging: the promise of radiomics. Phys Med 38:122–139
Bidgood WD, Horii SC, Prior FW et al (1997) Understanding and using DICOM, the data interchange standard for biomedical imaging. J Am Med Inform Assoc 4:199–212
Hoebel KV, Patel JB, Beers AL, Chang K, Singh P, Brown JM et al (2020) Radiomics repeatability pitfalls in a scan-rescan MRI study of glioblastoma. Radiol Artificial Intelligence. 3(1):e190199
Zaidi H, El Naqa I (2010) PET-guided delineation of radiation therapy treatment volumes: a survey of image segmentation techniques. Eur J Nucl Med Mol Imaging 37:2165–2187
Mishra D, Dash R, Rath AK et al (2011) Feature selection in gene expression data using principal component analysis and rough set theory. AdvExp Med Biol 696:91–100
Kumar D, Wong A, Clausi D (2015) Lung nodule classification using deep features in CT images. Computer & Robot Vision 327:110–116
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artificial Intelligence Res 1(16):321–357
Funding
None.
Author information
Authors and Affiliations
Contributions
KA—conceptualization, drafting, revising, reviewing, supervision, FBA—drafting, revising, SM—drafting, revising, FM—revising, reviewing, supervision, SAE—conceptualization, revising, reviewing, supervision, WBP—revising, reviewing, TM—revising, reviewing, JPR—revising, reviewing.
Corresponding author
Ethics declarations
Conflict of interest
None.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Aftab, K., Aamir, F.B., Mallick, S. et al. Radiomics for precision medicine in glioblastoma. J Neurooncol 156, 217–231 (2022). https://doi.org/10.1007/s11060-021-03933-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11060-021-03933-1