Radiomics for precision medicine in glioblastoma

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-ts-all treatment modalities. Radiomics uses machine-learning to identify salient features of the tumor on brain imaging and promises patient speci c 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, strati cation, prognostication as well as treatment planning and monitoring of glioblastoma.Results: Classi ers based on 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. Glioblastoma:Glioblastoma has an incidence of 3.22 per 100,000 and a 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-ts-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 patient's 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" re ect 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 (Figure 1). The pipeline of radiomics is highly

Radiogenomic Predictors of Recurrence in Glioblastoma—A Systematic Review

“…Likewise, advances in machine learning and deep learning approaches could be observed. New reviews in this field have focused on ML and deep learning approaches [ 67 ]. However, in contrast to other reviews, we focused on both classical to machine learning approaches.…”

“…Beyond the scope of manually extracted features, ML allows for an automated extraction of, e.g., first-order statistics, shape-based/textural/wavelet/geodesic features, or tissue probability maps [ 65 ]. As high dimensionality may lead to increased model complexity and overfitting issues, reducing dimensionality by feature selection is an essential step that can be performed by methods such as least absolute shrinkage and selection operator (LASSO) or random forests (RF) [ 66 , 67 ]. Based on selected features, various ML approaches can be applied for classification and outcome prediction, e.g., support vector machines (SVM), decision trees (DT), RFs as an extension of DTs, artificial neural networks (ANN), logistic regression (LR), Naïve Bayes (NB), or K-nearest neighbors (KNN).…”

Application of artificial intelligence in glioma researches: A bibliometric analysis

“…There have been an increasing number of systematic and narrative reviews focusing on the application of AI in glioma researches ( 25 – 28 ). They highlighted the application of machine learning and deep learning technologies in tumor segmentation and prognosis prediction.…”

Conventional and Advanced Imaging Techniques in Post-treatment Glioma Imaging

“…These types of multiparametric investigations have led to the advent of radiomics, the use of advanced computational methods to quantitatively identify and evaluate clinically relevant characteristics in treated gliomas that are too complex for the human eye to appreciate (165)(166)(167). For instance, Cai et al were able to create a stratification model which integrated a set of radiomic features extracted from the pretreatment MRI of each patient and relevant clinical factors to predict which patients would benefit from BVZ therapy, with the model achieving AUCs of 0.91 and 0.83 in the validation data set (166).…”