Learning MRI-based classification models for MGMT methylation status prediction in glioblastoma

Deciphering glioblastoma: Unveiling imaging markers for predicting MGMT promoter methylation status

Glioblastoma, the most common primary malignant tumor of the central nervous system in adults, is also among the most lethal. Despite a comprehensive treatment approach which utilizes surgery and postoperative chemoradiation, prognosis typically remains dismal. However certain epigenetic modifications, such as methylation of the MGMT promoter, have been proven to correlate with improved post-treatment outcomes. The 2021 WHO classification emphasizes molecular characteristics, highlighting shared genomic alterations across different grades and positioning MGMT methylation as a key influencer of outcomes. A combined diagnostic approach involving current imaging technology and emerging radiomics and deep learning models may allow for timely and accurate prediction of MGMT methylation status and therefore earlier and more individualized treatment and prognostication. Though these advanced radiomics models are rapidly emerging, additional development, standardization, and implementation may lead to a higher and more individualized level of patient care. This review explores the potential of imaging features in predicting MGMT promoter methylation, a critical determinant of therapeutic response and patient outcomes.

Virtual Biopsy for the Prediction of MGMT Promoter Methylation in Gliomas: A Comprehensive Review of Radiomics and Deep Learning Approaches Applied to MRI

Background/Objectives: The methylation status of the O6-methylguanine-DNA methyltransferase (MGMT) promoter in gliomas has emerged as a critical biomarker for prognosis and treatment response. Conventional methods for assessing MGMT promoter methylation, such as methylation-specific PCR, are invasive and require tissue sampling. Methods: A comprehensive literature search was performed in compliance with the updated PRISMA 2020 guidelines within electronic databases MEDLINE/PubMed, Scopus, and IEEE Xplore. Search terms, including "MGMT", "methylation", "glioma", "glioblastoma", "machine learning", "deep learning", and "radiomics", were adopted in various MeSH combinations. Original studies in the English, Italian, German, and French languages were considered for inclusion. Results: This review analyzed 34 studies conducted in the last six years, focusing on assessing MGMT methylation status using radiomics (RD), deep learning (DL), or combined approaches. These studies utilized radiological data from the public (e.g., BraTS, TCGA) and private institutional datasets. Sixteen studies focused exclusively on glioblastoma (GBM), while others included low- and high-grade gliomas. Twenty-seven studies reported diagnostic accuracy, with fourteen achieving values above 80%. The combined use of DL and RD generally resulted in higher accuracy, sensitivity, and specificity, although some studies reported lower minimum accuracy compared to studies using a single model. Conclusions: The integration of RD and DL offers a powerful, non-invasive tool for precisely recognizing MGMT promoter methylation status in gliomas, paving the way for enhanced personalized medicine in neuro-oncology. The heterogeneity of study populations, data sources, and methodologies reflected the complexity of the pipeline and machine learning algorithms, which may require general standardization to be implemented in clinical practice.

Assessment of MGMT and TERT Subtypes and Prognosis of Glioblastoma by Whole Tumor Apparent Diffusion Coefficient Histogram Analysis

BACKGROUND

Adult glioblastomas (GBMs) are associated with high recurrence and mortality. Personalized treatment based on molecular markers may help improve the prognosis. We aimed to evaluate whether apparent diffusion coefficient (ADC) histogram analysis can better predict MGMT and TERT molecular characteristics and to determine the prognostic relevance of genetic profile in patients with GBM.

MATERIALS AND METHODS

MRI, clinical, and pathological data of 79 patients with GBM were retrospectively collected. The ADC values based on histogram analysis were described using 10th percentile (p10), 90th percentile (p90), mean, median, minimum, maximum, skewness, kurtosis, and entropy. The independent-sample t test, linear correlation analysis, receiver operating characteristics (ROC) curve analysis, Kaplan-Meier analysis, and Cox proportional hazard regression were performed.

RESULTS

MGMT promoter methylation and TERT promoter mutation were detected in 53.2% and 44.3% of GBM patients, respectively. The ADCp10 in MGMT promoter unmethylated group was significantly lower than that in the MGMT promoter methylated group (p = 0.005). There were significant differences in ADCmin, ADCp10, ADCmean, and entropy between TERT promoter mutant and wild-type groups. Entropy showed the best diagnostic performance in differentiating between positive and negative TERT groups (AUC = 0.722, p = 0.001). Overall survival (OS) showed a positive correlation with ADCmin. The TERT promoter mutation was the only independent prognostic factor for GBM.

CONCLUSIONS

ADC histogram analysis may be a potential noninvasive biomarker for differentiating MGMT and TERT molecular markers and providing prognostic information for GBM patients.

Dynamic susceptibility contrast‑enhanced perfusion magnetic resonance imaging parameters for predicting MGMT promoter methylation and prognostic value in newly diagnosed patients with glioblastoma

O6-methylguanine DNA methyltransferase (MGMT) promoter methylation is an important clinical biomarker of newly diagnosed glioblastoma. Previous radiological studies using dynamic susceptibility contrast (DSC) magnetic resonance imaging (MRI) perfusion have aimed to predict MGMT methylation status non-invasively in gliomas with radiological characteristics. The possibility of predicting MGMT methylation status using DSC-MRI perfusion with a radiological approach remains controversial. The present study aimed to evaluate the usefulness of MRI perfusion parameters as non-invasive markers to predict MGMT methylation status and prognosis in newly diagnosed glioblastoma patients. Thus, 50 patients with histologically confirmed primary glioblastoma, IDH-wildtype who underwent tumor resection at Osaka University Hospital (Suita, Japan) between January 2017 and January 2023 were included in this study. The mean cerebral blood volume (CBV) ratio (rCBV) and cerebral blood flow (CBF) ratio (rCBF) for tumors with MGMT methylation (mean rCBV:2.09 and mean rCBF:3.08) were significantly higher compared with those for tumors without MGMT methylation (mean rCBV:1.33 and mean rCBF:1.85; P<0.05). While patients with MGMT methylation had longer progression-free survival (PFS) compared with those without MGMT methylation (P<0.05), there was no significant difference in OS with or without MGMT methylation (P=0.06). By contrast, there was no association between MRI perfusion parameters and OS or PFS in patients with glioblastoma. Furthermore, the association between CBV, CBF, MGMT promotor methylation status, OS, and PFS were explored. There was no significant prognostic difference between low vascularity tumors (rCBV <1.3 or rCBF <1.8) with or without MGMT methylation. On the other hand, high vascularity tumors (rCBF ≥1.8) with MGMT promotor methylation were associated to longer OS and PFS compared with those without. However, there was no association between MGMT methylation status and OS or PFS in patients with high rCBV (rCBV ≥1.3). The present study indicated that CBV and CBF could be used to predict the MGMT methylation status in glioblastomas. However, the prognostic value of tumor vascularity and MGMT methylation status may be limited.

The Three Pillars of Glioblastoma: A Systematic Review and Novel Analysis of Multi-Omics and Clinical Data

Glioblastoma is the most fatal and common malignant brain tumor, excluding metastasis and with a median survival of approximately one year. While solid tumors benefit from newly approved drugs, immunotherapy, and prevention, none of these scenarios are opening for glioblastoma. The key to unlocking the peculiar features of glioblastoma is observing its molecular and anatomical features tightly entangled with the host's central nervous system (CNS). In June 2024, we searched the PUBMED electronic database. Data collection and analysis were conducted independently by two reviewers. Results: A total of 215 articles were identified, and 192 were excluded based on inclusion and exclusion criteria. The remaining 23 were used for collecting divergent molecular pathways and anatomical features of glioblastoma. The analysis of the selected papers revealed a multifaced tumor with extreme variability and cellular reprogramming that are observable within the same patient. All the variability of glioblastoma could be clustered into three pillars to dissect the physiology of the tumor: 1. necrotic core; 2. vascular proliferation; 3. CNS infiltration. These three pillars support glioblastoma survival, with a pivotal role of the neurovascular unit, as supported by the most recent paper published by experts in the field.

-New frontiers in domain-inspired radiomics and radiogenomics: increasing role of molecular diagnostics in CNS tumor classification and grading following WHO CNS-5 updates

Gliomas and Glioblastomas represent a significant portion of central nervous system (CNS) tumors associated with high mortality rates and variable prognosis. In 2021, the World Health Organization (WHO) updated its Glioma classification criteria, most notably incorporating molecular markers including CDKN2A/B homozygous deletion, TERT promoter mutation, EGFR amplification, + 7/-10 chromosome copy number changes, and others into the grading and classification of adult and pediatric Gliomas. The inclusion of these markers and the corresponding introduction of new Glioma subtypes has allowed for more specific tailoring of clinical interventions and has inspired a new wave of Radiogenomic studies seeking to leverage medical imaging information to explore the diagnostic and prognostic implications of these new biomarkers. Radiomics, deep learning, and combined approaches have enabled the development of powerful computational tools for MRI analysis correlating imaging characteristics with various molecular biomarkers integrated into the updated WHO CNS-5 guidelines. Recent studies have leveraged these methods to accurately classify Gliomas in accordance with these updated molecular-based criteria based solely on non-invasive MRI, demonstrating the great promise of Radiogenomic tools. In this review, we explore the relative benefits and drawbacks of these computational frameworks and highlight the technical and clinical innovations presented by recent studies in the landscape of fast evolving molecular-based Glioma subtyping. Furthermore, the potential benefits and challenges of incorporating these tools into routine radiological workflows, aiming to enhance patient care and optimize clinical outcomes in the evolving field of CNS tumor management, have been highlighted.

Preoperative prediction of MGMT promoter methylation in glioblastoma based on multiregional and multi-sequence MRI radiomics analysis

O6-methylguanine-DNA methyltransferase (MGMT) has been demonstrated to be an important prognostic and predictive marker in glioblastoma (GBM). To establish a reliable radiomics model based on MRI data to predict the MGMT promoter methylation status of GBM. A total of 183 patients with glioblastoma were included in this retrospective study. The visually accessible Rembrandt images (VASARI) features were extracted for each patient, and a total of 14676 multi-region features were extracted from enhanced, necrotic, "non-enhanced, and edematous" areas on their multiparametric MRI. Twelve individual radiomics models were constructed based on the radiomics features from different subregions and different sequences. Four single-sequence models, three single-region models and the combined radiomics model combining all individual models were constructed. Finally, the predictive performance of adding clinical factors and VASARI characteristics was evaluated. The ComRad model combining all individual radiomics models exhibited the best performance in test set 1 and test set 2, with the area under the receiver operating characteristic curve (AUC) of 0.839 (0.709-0.963) and 0.739 (0.581-0.897), respectively. The results indicated that the radiomics model combining multi-region and multi-parametric MRI features has exhibited promising performance in predicting MGMT methylation status in GBM. The Modeling scheme that combining all individual radiomics models showed best performance among all constructed moels.

Association between the Anatomical Location of Glioblastoma and Its Evaluation with Clinical Considerations: A Systematic Review and Meta-Analysis

Background: Glioblastoma is a primary malignant brain tumor; it is aggressive with a high degree of malignancy and unfavorable prognosis and is the most common type of malignant brain tumor. Glioblastomas can be located in the brain, cerebellum, brainstem, and spinal cord, originating from glial cells, particularly astrocytes. Methods: The databases MEDLINE, Scopus, Web of Science, Google Scholar, and CINAHL were researched up to January 2024. Two authors independently performed the search, study selection, and data extraction. Methodological quality was evaluated with an assurance tool for anatomical studies (AQUA). The statistical mean, standard deviation, and difference of means calculated with the Student's t-test for presence between hemispheres and presence in the frontal and temporal lobes were analyzed. Results: A total of 123 studies met the established selection criteria, with a total of 6224 patients. In relation to the mean, GBM between hemispheres had a mean of 33.36 (SD 58.00) in the right hemisphere and a mean of 34.70 (SD 65.07) in the left hemisphere, due to the difference in averages between hemispheres. There were no statistically significant differences, p = 0.35. For the comparison between the presence of GBM in the frontal lobe and the temporal lobe, there was a mean in the frontal lobe of 23.23 (SD 40.03), while in the temporal lobe, the mean was 22.05 (SD 43.50), and for the difference in means between the frontal lobe and the temporal lobe, there was no statistically significant difference for the presence of GBM, p = 0.178. Conclusions: We believe that before a treatment, it will always be correct to know where the GBM is located and how it behaves clinically, in order to generate correct conservative or surgical treatment guidelines for each patient. We believe that more detailed studies are also needed to show why GBM is associated more with some regions than others, despite the brain structure being homologous to other regions in which GMB occurs less frequently, which is why knowing its predominant presence in brain regions is very important.

AI-driven estimation of O6 methylguanine-DNA-methyltransferase (MGMT) promoter methylation in glioblastoma patients: a systematic review with bias analysis

BACKGROUND

Accurate and non-invasive estimation of MGMT promoter methylation status in glioblastoma (GBM) patients is of paramount clinical importance, as it is a predictive biomarker associated with improved overall survival (OS). In response to the clinical need, recent studies have focused on the development of non-invasive artificial intelligence (AI)-based methods for MGMT estimation. In this systematic review, we not only delve into the technical aspects of these AI-driven MGMT estimation methods but also emphasize their profound clinical implications. Specifically, we explore the potential impact of accurate non-invasive MGMT estimation on GBM patient care and treatment decisions.

METHODS

Employing a PRISMA search strategy, we identified 33 relevant studies from reputable databases, including PubMed, ScienceDirect, Google Scholar, and IEEE Explore. These studies were comprehensively assessed using 21 diverse attributes, encompassing factors such as types of imaging modalities, machine learning (ML) methods, and cohort sizes, with clear rationales for attribute scoring. Subsequently, we ranked these studies and established a cutoff value to categorize them into low-bias and high-bias groups.

RESULTS

By analyzing the 'cumulative plot of mean score' and the 'frequency plot curve' of the studies, we determined a cutoff value of 6.00. A higher mean score indicated a lower risk of bias, with studies scoring above the cutoff mark categorized as low-bias (73%), while 27% fell into the high-bias category.

CONCLUSION

Our findings underscore the immense potential of AI-based machine learning (ML) and deep learning (DL) methods in non-invasively determining MGMT promoter methylation status. Importantly, the clinical significance of these AI-driven advancements lies in their capacity to transform GBM patient care by providing accurate and timely information for treatment decisions. However, the translation of these technical advancements into clinical practice presents challenges, including the need for large multi-institutional cohorts and the integration of diverse data types. Addressing these challenges will be critical in realizing the full potential of AI in improving the reliability and accessibility of MGMT estimation while lowering the risk of bias in clinical decision-making.

Prediction of MGMT promotor methylation status in glioblastoma by contrast-enhanced T1-weighted intensity image

Background

The study aims to explore MRI phenotypes that predict glioblastoma's (GBM) methylation status of the promoter region of MGMT gene (pMGMT) by qualitatively assessing contrast-enhanced T1-weighted intensity images.

Methods

A total of 193 histologically and molecularly confirmed GBMs at the Kansai Network for Molecular Diagnosis of Central Nervous Tumors (KANSAI) were used as an exploratory cohort. From the Cancer Imaging Archive/Cancer Genome Atlas (TCGA) 93 patients were used as validation cohorts. "Thickened structure" was defined as the solid tumor component presenting circumferential extension or occupying >50% of the tumor volume. "Methylated contrast phenotype" was defined as indistinct enhancing circumferential border, heterogenous enhancement, or nodular enhancement. Inter-rater agreement was assessed, followed by an investigation of the relationship between radiological findings and pMGMT methylation status.

Results

Fleiss's Kappa coefficient for "Thickened structure" was 0.68 for the exploratory and 0.55 for the validation cohort, and for "Methylated contrast phenotype," 0.30 and 0.39, respectively. The imaging feature, the presence of "Thickened structure" and absence of "Methylated contrast phenotype," was significantly predictive of pMGMT unmethylation both for the exploratory (p = .015, odds ratio = 2.44) and for the validation cohort (p = .006, odds ratio = 7.83). The sensitivities and specificities of the imaging feature, the presence of "Thickened structure," and the absence of "Methylated contrast phenotype" for predicting pMGMT unmethylation were 0.29 and 0.86 for the exploratory and 0.25 and 0.96 for the validation cohort.

Conclusions

The present study showed that qualitative assessment of contrast-enhanced T1-weighted intensity images helps predict GBM's pMGMT methylation status.

MRI radiomics model for predicting TERT promoter mutation status in glioblastoma

BACKGROUND AND PURPOSE

The presence of TERT promoter mutations has been associated with worse prognosis and resistance to therapy for patients with glioblastoma (GBM). This study aimed to determine whether the combination model of different feature selections and classification algorithms based on multiparameter MRI can be used to predict TERT subtype in GBM patients.

METHODS

A total of 143 patients were included in our retrospective study, and 2553 features were obtained. The datasets were randomly divided into training and test sets in a ratio of 7:3. The synthetic minority oversampling technique was used to achieve data balance. The Pearson correlation coefficients were used for dimension reduction. Three feature selections and five classification algorithms were used to model the selected features. Finally, 10-fold cross validation was applied to the training dataset.

RESULTS

A model with eight features generated by recursive feature elimination (RFE) and linear discriminant analysis (LDA) showed the greatest diagnostic performance (area under the curve values for the training, validation, and testing sets: 0.983, 0.964, and 0.926, respectively), followed by relief and random forest (RF), analysis of variance and RF. Furthermore, the relief was the optimal feature selection for separately evaluating those five classification algorithms, and RF was the most preferable algorithm for separately assessing the three feature selectors. ADC entropy was the parameter that made the greatest contribution to the discrimination of TERT mutations.

CONCLUSIONS

Radiomics model generated by RFE and LDA mainly based on ADC entropy showed good performance in predicting TERT promoter mutations in GBM.

Potential of pre-operative MRI features in glioblastoma to predict for molecular stem cell subtype and patient overall survival

AIM OF THE STUDY

A molecular signature based on 10 mRNA abundances that characterizes the mesenchymal-to-proneural phenotype of glioblastoma stem(like) cells (GSCs) enriched in primary culture has been previously established. As this phenotype has been proposed to be prognostic for disease outcome the present study aims to identify features of the preoperative MR imaging that may predict the GSC phenotype of individual tumors.

MATERIAL/METHODS

Molecular mesenchymal-to-proneural mRNA signatures and intrinsic radioresistance (SF4, survival fraction at 4 Gy) of primary GSC-enriched cultures were associated with survival data and pre-operative MR imaging of the corresponding glioblastoma patients of a prospective cohort (n = 24). The analyzed imaging parameters comprised linear vectors derived from tumor volume, necrotic volume and edema as contoured manually.

RESULTS

A necrosis/tumor vector ratio and to a weaker extent the product of this ratio and the edema vector were identified to correlate with the mesenchymal-to-proneural mRNA signature and the SF4 of the patient-derived GSC cultures. Importantly, both parameter combinations were predictive for overall survival of the whole patient cohort. Moreover, the combination of necrosis/tumor vector ratio and edema vector differed significantly between uni- and multifocally recurring tumors.

CONCLUSION

Features of the preoperative MR images may reflect the molecular signature of the GSC population and might be used in the future as a prognostic factor and for treatment stratification especially in the MGMT promotor-unmethylated sub-cohort of glioblastoma patients.

An image-based modeling framework for predicting spatiotemporal brain cancer biology within individual patients

Imaging is central to the clinical surveillance of brain tumors yet it provides limited insight into a tumor's underlying biology. Machine learning and other mathematical modeling approaches can leverage paired magnetic resonance images and image-localized tissue samples to predict almost any characteristic of a tumor. Image-based modeling takes advantage of the spatial resolution of routine clinical scans and can be applied to measure biological differences within a tumor, changes over time, as well as the variance between patients. This approach is non-invasive and circumvents the intrinsic challenges of inter- and intratumoral heterogeneity that have historically hindered the complete assessment of tumor biology and treatment responsiveness. It can also reveal tumor characteristics that may guide both surgical and medical decision-making in real-time. Here we describe a general framework for the acquisition of image-localized biopsies and the construction of spatiotemporal radiomics models, as well as case examples of how this approach may be used to address clinically relevant questions.

Radiogenomics: a key component of precision cancer medicine

Radiogenomics, focusing on the relationship between genomics and imaging phenotypes, has been widely applied to address tumour heterogeneity and predict immune responsiveness and progression. It is an inevitable consequence of current trends in precision medicine, as radiogenomics costs less than traditional genetic sequencing and provides access to whole-tumour information rather than limited biopsy specimens. By providing voxel-by-voxel genetic information, radiogenomics can allow tailored therapy targeting a complete, heterogeneous tumour or set of tumours. In addition to quantifying lesion characteristics, radiogenomics can also be used to distinguish benign from malignant entities, as well as patient characteristics, to better stratify patients according to disease risk, thereby enabling more precise imaging and screening. Here, we have characterised the radiogenomic application in precision medicine using a multi-omic approach. we outline the main applications of radiogenomics in diagnosis, treatment planning and evaluations in the field of oncology with the aim of developing quantitative and personalised medicine. Finally, we discuss the challenges in the field of radiogenomics and the scope and clinical applicability of these methods.

A Comparison of Three Different Deep Learning-Based Models to Predict the MGMT Promoter Methylation Status in Glioblastoma Using Brain MRI

Glioblastoma (GBM) is the most common primary malignant brain tumor in adults. The standard treatment for GBM consists of surgical resection followed by concurrent chemoradiotherapy and adjuvant temozolomide. O-6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status is an important prognostic biomarker that predicts the response to temozolomide and guides treatment decisions. At present, the only reliable way to determine MGMT promoter methylation status is through the analysis of tumor tissues. Considering the complications of the tissue-based methods, an imaging-based approach is preferred. This study aimed to compare three different deep learning-based approaches for predicting MGMT promoter methylation status. We obtained 576 T2WI with their corresponding tumor masks, and MGMT promoter methylation status from, The Brain Tumor Segmentation (BraTS) 2021 datasets. We developed three different models: voxel-wise, slice-wise, and whole-brain. For voxel-wise classification, methylated and unmethylated MGMT tumor masks were made into 1 and 2 with 0 background, respectively. We converted each T2WI into 32 × 32 × 32 patches. We trained a 3D-Vnet model for tumor segmentation. After inference, we constructed the whole brain volume based on the patch's coordinates. The final prediction of MGMT methylation status was made by majority voting between the predicted voxel values of the biggest connected component. For slice-wise classification, we trained an object detection model for tumor detection and MGMT methylation status prediction, then for final prediction, we used majority voting. For the whole-brain approach, we trained a 3D Densenet121 for prediction. Whole-brain, slice-wise, and voxel-wise, accuracy was 65.42% (SD 3.97%), 61.37% (SD 1.48%), and 56.84% (SD 4.38%), respectively.

Fused deep learning paradigm for the prediction of o6-methylguanine-DNA methyltransferase genotype in glioblastoma patients: A neuro-oncological investigation

BACKGROUND

The O6-methylguanine-DNA methyltransferase (MGMT) is a deoxyribonucleic acid (DNA) repairing enzyme that has been established as an essential clinical brain tumor biomarker for Glioblastoma Multiforme (GBM). Knowing the status of MGMT methylation biomarkers using multi-parametric MRI (mp-MRI) helps neuro-oncologists to analyze GBM and its treatment plan.

METHOD

The hand-crafted radiomics feature extraction of GBM's subregions, such as edema(ED), tumor core (TC), and enhancing tumor (ET) in the machine learning (ML) framework, was investigated using support vector machine(SVM), K-Nearest Neighbours (KNN), random forest (RF), LightGBM, and extreme gradient boosting (XGB). For tissue-level analysis of the promotor genes in GBM, we used the deep residual neural network (ResNet-18) with 3D architecture, followed by EfficientNet-based investigation for variants as B0 and B1. Lastly, we analyzed the fused deep learning (FDL) framework that combines ML and DL frameworks.

RESULT

Structural mp-MRI consisting of T1, T2, FLAIR, and T1GD having a size of 400 and 185 patients, respectively, for discovery and replication cohorts. Using the CV protocol in the ResNet-3D framework, MGMT methylation status prediction in mp-MRI gave the AUC of 0.753 (p < 0.0001) and 0.72 (p < 0.0001) for the discovery and replication cohort, respectively. We presented that the FDL is ∼7% superior to solo DL and ∼15% to solo ML.

CONCLUSION

The proposed study aims to provide solutions for building an efficient predictive model of MGMT for GBM patients using deep radiomics features obtained from mp-MRI with the end-to-end ResNet-18 3D and FDL imaging signatures.

Beyond Imaging and Genetic Signature in Glioblastoma: Radiogenomic Holistic Approach in Neuro-Oncology

Glioblastoma (GBM) is a malignant brain tumor exhibiting rapid and infiltrative growth, with less than 10% of patients surviving over 5 years, despite aggressive and multimodal treatments. The poor prognosis and the lack of effective pharmacological treatments are imputable to a remarkable histological and molecular heterogeneity of GBM, which has led, to date, to the failure of precision oncology and targeted therapies. Identification of molecular biomarkers is a paradigm for comprehensive and tailored treatments; nevertheless, biopsy sampling has proved to be invasive and limited. Radiogenomics is an emerging translational field of research aiming to study the correlation between radiographic signature and underlying gene expression. Although a research field still under development, not yet incorporated into routine clinical practice, it promises to be a useful non-invasive tool for future personalized/adaptive neuro-oncology. This review provides an up-to-date summary of the recent advancements in the use of magnetic resonance imaging (MRI) radiogenomics for the assessment of molecular markers of interest in GBM regarding prognosis and response to treatments, for monitoring recurrence, also providing insights into the potential efficacy of such an approach for survival prognostication. Despite a high sensitivity and specificity in almost all studies, accuracy, reproducibility and clinical value of radiomic features are the Achilles heel of this newborn tool. Looking into the future, investigators' efforts should be directed towards standardization and a disciplined approach to data collection, algorithms, and statistical analysis.

Feasibility of evaluating the histologic and genetic subtypes of WHO grade II-IV gliomas by diffusion-weighted imaging

BACKGROUND

To explore the feasibility of diffusion-weighted imaging (DWI) metrics to predict the histologic subtypes and genetic status of gliomas (e.g., IDH, MGMT, and TERT) noninvasively.

METHODS

One hundred and eleven patients with pathologically confirmed WHO grade II-IV gliomas were recruited retrospectively. Apparent diffusion coefficient (ADC) values were measured in solid parts of gliomas on co-registered T2-weighted images and were compared with each other in terms of WHO grading and genotypes using t-tests. Receiver operating characteristic analysis was performed to assess the diagnostic performances of ADC. Subsequently, multiple linear regression was used to find independent variables, which can directly affect ADC values.

RESULTS

The values of overall mean ADC (omADC) and normalized ADC (nADC) of high grade gliomas and IDH wildtype gliomas were lower than low grade gliomas and IDH mutated gliomas (P < 0.05). nADC values showed better diagnostic performance than omADC in identifying tumor grade (AUC: 0.787 vs. 0.750) and IDH status (AUC: 0.836 vs. 0.777). ADC values had limited abilities in distinguishing TERT status (AUC = 0.607 for nADC and 0.617 for omADC) and MGMT status (AUC = 0.651 for nADC). Only tumor grade and IDH status were tightly associated with ADC values.

CONCLUSION

DWI metrics can predict glioma grading and IDH mutation noninvasively, but have limited use in detecting TERT mutation and MGMT methylation.

A hierarchical machine learning model based on Glioblastoma patients' clinical, biomedical, and image data to analyze their treatment plans

AIM OF STUDY

Glioblastoma Multiforme (GBM) is an aggressive brain cancer in adults that kills most patients in the first year due to ineffective treatment. Different clinical, biomedical, and image data features are needed to analyze GBM, increasing complexities. Besides, they lead to weak performances for machine learning models due to ignoring physicians' knowledge. Therefore, this paper proposes a hierarchical model based on Fuzzy C-mean (FCM) clustering, Wrapper feature selection, and twelve classifiers to analyze treatment plans.

METHODOLOGY/APPROACH

The proposed method finds the effectiveness of previous and current treatment plans, hierarchically determining the best decision for future treatment plans for GBM patients using clinical data, biomedical data, and different image data. A case study is presented based on the Cancer Genome Atlas Glioblastoma Multiforme dataset to prove the effectiveness of the proposed model. This dataset is analyzed using data preprocessing, experts' knowledge, and a feature reduction method based on the Principal Component Analysis. Then, the FCM clustering method is utilized to reinforce classifier learning.

OUTCOMES OF STUDY

The proposed model finds the best combination of Wrapper feature selection and classifier for each cluster based on different measures, including accuracy, sensitivity, specificity, precision, F-score, and G-mean according to a hierarchical structure. It has the best performance among other reinforced classifiers. Besides, this model is compatible with real-world medical processes for GBM patients based on clinical, biomedical, and image data.

Conventional MRI-Derived Biomarkers of Adult-Type Diffuse Glioma Molecular Subtypes: A Comprehensive Review

The introduction of molecular criteria into the classification of diffuse gliomas has added interesting practical implications to glioma management. This has created a new clinical need for correlating imaging characteristics with glioma genotypes, also known as radiogenomics or imaging genomics. Although many studies have primarily focused on the use of advanced magnetic resonance imaging (MRI) techniques for radiogenomics purposes, conventional MRI sequences remain the reference point in the study and characterization of brain tumors. A summary of the conventional imaging features of glioma molecular subtypes should be useful as a tool for daily diagnostic brain tumor management. Hence, this article aims to summarize the conventional MRI features of glioma molecular subtypes in light of the recent literature.

Multimodal MRI-Based Radiomic Nomogram for the Early Differentiation of Recurrence and Pseudoprogression of High-Grade Glioma

Objective

To evaluate the diagnostic value of multimodal MRI radiomics based on T2-weighted fluid attenuated inversion recovery imaging (T2WI-FLAIR) combined with T1-weighted contrast enhanced imaging (T1WI-CE) in the early differentiation of high-grade glioma recurrence from pseudoprogression.

Methods

A total of one hundred eighteen patients with brain gliomas who were diagnosed from March 2014 to April 2020 were retrospectively analyzed. According to the clinical characteristics, the patients were randomly split into a training group (n = 83) and a test group (n = 35) at a 7 : 3 ratio. The region of interest (ROI) was delineated, and 2632 radiomic features were extracted. We used multiple logistic regression to establish a classification model, including the T1 model, T2 model, and T1 + T2 model, to differentiate recurrence from pseudoprogression. The diagnostic efficiency of the model was evaluated by calculating the area under the receiver operating characteristic curve (AUC) and accuracy (ACC) and by analyzing the calibration curve of the nomogram and decision curve.

Results

There were 75 cases of recurrence and 43 cases of pseudoprogression. The diagnostic efficacies of the multimodal MRI-based radiomic model were relatively high. The AUC values and ACC of the training group were 0.831 and 77.11%, respectively, and the AUC values and ACC of the test group were 0.829 and 88.57%, respectively. The calibration curve of the nomogram showed that the discrimination probability was consistent with the actual occurrence in the training group, and the discrimination probability was roughly the same as the actual occurrence in the test group. In the decision curve analysis, the T1 + T2 model showed greater overall net efficiency.

Conclusion

The multimodal MRI radiomic model has relatively high efficiency in the early differentiation of recurrence from pseudoprogression, and it could be helpful for clinicians in devising correct treatment plans so that patients can be treated in a timely and accurate manner.

Improving MGMT methylation status prediction of glioblastoma through optimizing radiomics features using genetic algorithm-based machine learning approach

O6-Methylguanine-DNA-methyltransferase (MGMT) promoter methylation was shown in many studies to be an important predictive biomarker for temozolomide (TMZ) resistance and poor progression-free survival in glioblastoma multiforme (GBM) patients. However, identifying the MGMT methylation status using molecular techniques remains challenging due to technical limitations, such as the inability to obtain tumor specimens, high prices for detection, and the high complexity of intralesional heterogeneity. To overcome these difficulties, we aimed to test the feasibility of using a novel radiomics-based machine learning (ML) model to preoperatively and noninvasively predict the MGMT methylation status. In this study, radiomics features extracted from multimodal images of GBM patients with annotated MGMT methylation status were downloaded from The Cancer Imaging Archive (TCIA) public database for retrospective analysis. The radiomics features extracted from multimodal images from magnetic resonance imaging (MRI) had undergone a two-stage feature selection method, including an eXtreme Gradient Boosting (XGBoost) feature selection model followed by a genetic algorithm (GA)-based wrapper model for extracting the most meaningful radiomics features for predictive purposes. The cross-validation results suggested that the GA-based wrapper model achieved the high performance with a sensitivity of 0.894, specificity of 0.966, and accuracy of 0.925 for predicting the MGMT methylation status in GBM. Application of the extracted GBM radiomics features on a low-grade glioma (LGG) dataset also achieved a sensitivity 0.780, specificity 0.620, and accuracy 0.750, indicating the potential of the selected radiomics features to be applied more widely on both low- and high-grade gliomas. The performance indicated that our model may potentially confer significant improvements in prognosis and treatment responses in GBM patients.

An Attentive Multi-Modal CNN for Brain Tumor Radiogenomic Classification

Medical images of brain tumors are critical for characterizing the pathology of tumors and early diagnosis. There are multiple modalities for medical images of brain tumors. Fusing the unique features of each modality of the magnetic resonance imaging (MRI) scans can accurately determine the nature of brain tumors. The current genetic analysis approach is time-consuming and requires surgical extraction of brain tissue samples. Accurate classification of multi-modal brain tumor images can speed up the detection process and alleviate patient suffering. Medical image fusion refers to effectively merging the significant information of multiple source images of the same tissue into one image, which will carry abundant information for diagnosis. This paper proposes a novel attentive deep-learning-based classification model that integrates multi-modal feature aggregation, lite attention mechanism, separable embedding, and modal-wise shortcuts for performance improvement. We evaluate our model on the RSNA-MICCAI dataset, a scenario-specific medical image dataset, and demonstrate that the proposed method outperforms the state-of-the-art (SOTA) by around 3%.

AI and High-Grade Glioma for Diagnosis and Outcome Prediction: Do All Machine Learning Models Perform Equally Well?

Radiomic models outperform clinical data for outcome prediction in high-grade gliomas (HGG). However, lack of parameter standardization limits clinical applications. Many machine learning (ML) radiomic models employ single classifiers rather than ensemble learning, which is known to boost performance, and comparative analyses are lacking in the literature. We aimed to compare ML classifiers to predict clinically relevant tasks for HGG: overall survival (OS), isocitrate dehydrogenase (IDH) mutation, O-6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation, epidermal growth factor receptor vIII (EGFR) amplification, and Ki-67 expression, based on radiomic features from conventional and advanced magnetic resonance imaging (MRI). Our objective was to identify the best algorithm for each task. One hundred fifty-six adult patients with pathologic diagnosis of HGG were included. Three tumoral regions were manually segmented: contrast-enhancing tumor, necrosis, and non-enhancing tumor. Radiomic features were extracted with a custom version of Pyradiomics and selected through Boruta algorithm. A Grid Search algorithm was applied when computing ten times K-fold cross-validation (K=10) to get the highest mean and lowest spread of accuracy. Model performance was assessed as AUC-ROC curve mean values with 95% confidence intervals (CI). Extreme Gradient Boosting (xGB) obtained highest accuracy for OS (74,5%), Adaboost (AB) for IDH mutation (87.5%), MGMT methylation (70,8%), Ki-67 expression (86%), and EGFR amplification (81%). Ensemble classifiers showed the best performance across tasks. High-scoring radiomic features shed light on possible correlations between MRI and tumor histology.

Diagnostic performance of radiomics using machine learning algorithms to predict MGMT promoter methylation status in glioma patients: a meta-analysis

PURPOSE

We aimed to assess the diagnostic performance of radiomics using machine learning algorithms to predict the methylation status of the O6-methylguanine-DNA methyltransferase (MGMT) promoter in glioma patients.

METHODS

A comprehensive literature search of PubMed, EMBASE, and Web of Science until 27 July 2021 was performed to identify eligible studies. Stata SE 15.0 and Meta-Disc 1.4 were used for data analysis.

RESULTS

A total of fifteen studies with 1663 patients were included: five studies with training and validation cohorts and ten with only training cohorts. The pooled sensitivity and specificity of machine learning for predicting MGMT promoter methylation in gliomas were 85% (95% CI 79%-90%) and 84% (95% CI 78%-88%) in the training cohort (n=15) and 84% (95% CI 70%-92%) and 78% (95% CI 63%-88%) in the validation cohort (n=5). The AUC was 0.91 (95% CI 0.88-0.93) in the training cohort and 0.88 (95% CI 0.85-0.91) in the validation cohort. The meta-regression demonstrated that magnetic resonance imaging sequences were related to heterogeneity. The sensitivity analysis showed that heterogeneity was reduced by excluding one study with the lowest diagnostic performance.

CONCLUSION

This meta-analysis demonstrated that machine learning is a promising, reliable and repeatable candidate method for predicting MGMT promoter methylation status in glioma and showed a higher performance than non-machine learning methods.

Radiomics-based prediction of multiple gene alteration incorporating mutual genetic information in glioblastoma and grade 4 astrocytoma, IDH-mutant

Purpose

In glioma, molecular alterations are closely associated with disease prognosis. This study aimed to develop a radiomics-based multiple gene prediction model incorporating mutual information of each genetic alteration in glioblastoma and grade 4 astrocytoma, IDH-mutant.

Methods

From December 2014 through January 2020, we enrolled 418 patients with pathologically confirmed glioblastoma (based on the 2016 WHO classification). All selected patients had preoperative MRI and isocitrate dehydrogenase (IDH) mutation, O-6-methylguanine-DNA methyltransferase (MGMT) promoter methylation, epidermal growth factor receptor amplification, and alpha-thalassemia/mental retardation syndrome X-linked (ATRX) loss status. Patients were randomly split into training and test sets (7:3 ratio). Enhancing tumor and peritumoral T2-hyperintensity were auto-segmented, and 660 radiomics features were extracted. We built binary relevance (BR) and ensemble classifier chain (ECC) models for multi-label classification and compared their performance. In the classifier chain, we calculated the mean absolute Shapley value of input features.

Results

The micro-averaged area under the curves (AUCs) for the test set were 0.804 and 0.842 in BR and ECC models, respectively. IDH mutation status was predicted with the highest AUCs of 0.964 (BR) and 0.967 (ECC). The ECC model showed higher AUCs than the BR model for ATRX (0.822 vs. 0.775) and MGMT promoter methylation (0.761 vs. 0.653) predictions. The mean absolute Shapley values suggested that predicted outcomes from the prior classifiers were important for better subsequent predictions along the classifier chains.

Conclusion

We built a radiomics-based multiple gene prediction chained model that incorporates mutual information of each genetic alteration in glioblastoma and grade 4 astrocytoma, IDH-mutant and performs better than a simple bundle of binary classifiers using prior classifiers’ prediction probability.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11060-021-03870-z.

Reverse Engineering Glioma Radiomics to Conventional Neuroimaging

A novel radiological research field pursuing comprehensive quantitative image, namely “Radiomics,” gained traction along with the advancement of computational technology and artificial intelligence. This novel concept for analyzing medical images brought extensive interest to the neuro-oncology and neuroradiology research community to build a diagnostic workflow to detect clinically relevant genetic alteration of gliomas noninvasively. Although quite a few promising results were published regarding MRI-based diagnosis of isocitrate dehydrogenase (IDH) mutation in gliomas, it has become clear that an ample amount of effort is still needed to render this technology clinically applicable. At the same time, many significant insights were discovered through this research project, some of which could be “reverse engineered” to improve conventional non-radiomic MR image acquisition. In this review article, the authors aim to discuss the recent advancements and encountering issues of radiomics, how we can apply the knowledge provided by radiomics to standard clinical images, and further expected technological advances in the realm of radiomics and glioma.

Assessing Versatile Machine Learning Models for Glioma Radiogenomic Studies across Hospitals

Simple Summary

Radiogenomics enables prediction of the status and prognosis of patients using non-invasively obtained imaging data. Current machine learning (ML) methods used in radiogenomics require huge datasets, which involve the handling of large heterogeneous datasets from multiple cohorts/hospitals. In this study, two different glioma datasets were used to test various ML and image pre-processing methods to confirm whether the models trained on one dataset are universally applicable to other datasets. Our result suggested that the ML method that yielded the highest accuracy in a single dataset was likely to be overfitted. We demonstrated that implementation of standardization and dimension reduction procedures prior to classification, enabled the development of ML methods that are less affected by the multiple cohort difference. We advocate using caution in interpreting the results of radiogenomic studies of the training and testing datasets that are small or mixed, with a view to implementing practical ML methods in radiogenomics.

Abstract

Radiogenomics use non-invasively obtained imaging data, such as magnetic resonance imaging (MRI), to predict critical biomarkers of patients. Developing an accurate machine learning (ML) technique for MRI requires data from hundreds of patients, which cannot be gathered from any single local hospital. Hence, a model universally applicable to multiple cohorts/hospitals is required. We applied various ML and image pre-processing procedures on a glioma dataset from The Cancer Image Archive (TCIA, n = 159). The models that showed a high level of accuracy in predicting glioblastoma or WHO Grade II and III glioma using the TCIA dataset, were then tested for the data from the National Cancer Center Hospital, Japan (NCC, n = 166) whether they could maintain similar levels of high accuracy. Results: we confirmed that our ML procedure achieved a level of accuracy (AUROC = 0.904) comparable to that shown previously by the deep-learning methods using TCIA. However, when we directly applied the model to the NCC dataset, its AUROC dropped to 0.383. Introduction of standardization and dimension reduction procedures before classification without re-training improved the prediction accuracy obtained using NCC (0.804) without a loss in prediction accuracy for the TCIA dataset. Furthermore, we confirmed the same tendency in a model for IDH1/2 mutation prediction with standardization and application of dimension reduction that was also applicable to multiple hospitals. Our results demonstrated that overfitting may occur when an ML method providing the highest accuracy in a small training dataset is used for different heterogeneous data sets, and suggested a promising process for developing an ML method applicable to multiple cohorts.

Machine learning analysis of TCGA cancer data

In recent years, machine learning (ML) researchers have changed their focus towards biological problems that are difficult to analyse with standard approaches. Large initiatives such as The Cancer Genome Atlas (TCGA) have allowed the use of omic data for the training of these algorithms. In order to study the state of the art, this review is provided to cover the main works that have used ML with TCGA data. Firstly, the principal discoveries made by the TCGA consortium are presented. Once these bases have been established, we begin with the main objective of this study, the identification and discussion of those works that have used the TCGA data for the training of different ML approaches. After a review of more than 100 different papers, it has been possible to make a classification according to following three pillars: the type of tumour, the type of algorithm and the predicted biological problem. One of the conclusions drawn in this work shows a high density of studies based on two major algorithms: Random Forest and Support Vector Machines. We also observe the rise in the use of deep artificial neural networks. It is worth emphasizing, the increase of integrative models of multi-omic data analysis. The different biological conditions are a consequence of molecular homeostasis, driven by both protein coding regions, regulatory elements and the surrounding environment. It is notable that a large number of works make use of genetic expression data, which has been found to be the preferred method by researchers when training the different models. The biological problems addressed have been classified into five types: prognosis prediction, tumour subtypes, microsatellite instability (MSI), immunological aspects and certain pathways of interest. A clear trend was detected in the prediction of these conditions according to the type of tumour. That is the reason for which a greater number of works have focused on the BRCA cohort, while specific works for survival, for example, were centred on the GBM cohort, due to its large number of events. Throughout this review, it will be possible to go in depth into the works and the methodologies used to study TCGA cancer data. Finally, it is intended that this work will serve as a basis for future research in this field of study.

Machine learning applications to neuroimaging for glioma detection and classification: An artificial intelligence augmented systematic review

Glioma is the most common primary intraparenchymal tumor of the brain and the 5-year survival rate of high-grade glioma is poor. Magnetic resonance imaging (MRI) is essential for detecting, characterizing and monitoring brain tumors but definitive diagnosis still relies on surgical pathology. Machine learning has been applied to the analysis of MRI data in glioma research and has the potential to change clinical practice and improve patient outcomes. This systematic review synthesizes and analyzes the current state of machine learning applications to glioma MRI data and explores the use of machine learning for systematic review automation. Various datapoints were extracted from the 153 studies that met inclusion criteria and analyzed. Natural language processing (NLP) analysis involved keyword extraction, topic modeling and document classification. Machine learning has been applied to tumor grading and diagnosis, tumor segmentation, non-invasive genomic biomarker identification, detection of progression and patient survival prediction. Model performance was generally strong (AUC = 0.87 ± 0.09; sensitivity = 0.87 ± 0.10; specificity = 0.0.86 ± 0.10; precision = 0.88 ± 0.11). Convolutional neural network, support vector machine and random forest algorithms were top performers. Deep learning document classifiers yielded acceptable performance (mean 5-fold cross-validation AUC = 0.71). Machine learning tools and data resources were synthesized and summarized to facilitate future research. Machine learning has been widely applied to the processing of MRI data in glioma research and has demonstrated substantial utility. NLP and transfer learning resources enabled the successful development of a replicable method for automating the systematic review article screening process, which has potential for shortening the time from discovery to clinical application in medicine.

MRI-Based Deep-Learning Method for Determining Glioma MGMT Promoter Methylation Status

BACKGROUND AND PURPOSE

O6-Methylguanine-DNA methyltransferase (MGMT) promoter methylation confers an improved prognosis and treatment response in gliomas. We developed a deep learning network for determining MGMT promoter methylation status using T2 weighted Images (T2WI) only.

MATERIALS AND METHODS

Brain MR imaging and corresponding genomic information were obtained for 247 subjects from The Cancer Imaging Archive and The Cancer Genome Atlas. One hundred sixty-three subjects had a methylated MGMT promoter. A T2WI-only network (MGMT-net) was developed to determine MGMT promoter methylation status and simultaneous single-label tumor segmentation. The network was trained using 3D-dense-UNets. Three-fold cross-validation was performed to generalize the performance of the networks. Dice scores were computed to determine tumor-segmentation accuracy.

RESULTS

The MGMT-net demonstrated a mean cross-validation accuracy of 94.73% across the 3 folds (95.12%, 93.98%, and 95.12%, [SD, 0.66%]) in predicting MGMT methylation status with a sensitivity and specificity of 96.31% [SD, 0.04%] and 91.66% [SD, 2.06%], respectively, and a mean area under the curve of 0.93 [SD, 0.01]. The whole tumor-segmentation mean Dice score was 0.82 [SD, 0.008].

CONCLUSIONS

We demonstrate high classification accuracy in predicting MGMT promoter methylation status using only T2WI. Our network surpasses the sensitivity, specificity, and accuracy of histologic and molecular methods. This result represents an important milestone toward using MR imaging to predict prognosis and treatment response.

State of Radiomics in Glioblastoma

Radiomics is an emerging discipline that aims to make intelligent predictions and derive medical insights based on quantitative features extracted from medical images as a means to improve clinical diagnosis or outcome. Pertaining to glioblastoma, radiomics has provided powerful, noninvasive tools for gaining insights into pathogenesis and therapeutic responses. Radiomic studies have yielded meaningful biological understandings of imaging features that are often taken for granted in clinical medicine, including contrast enhancement on glioblastoma magnetic resonance imaging, the distance of a tumor from the subventricular zone, and the extent of mass effect. They have also laid the groundwork for noninvasive detection of mutations and epigenetic events that influence clinical outcomes such as isocitrate dehydrogenase (IDH) and O6-methylguanine-DNA methyltransferase (MGMT). In this article, we review advances in the field of glioblastoma radiomics as they pertain to prediction of IDH mutation status and MGMT promoter methylation status, as well as the development of novel, higher order radiomic parameters.

Machine Learning for the Prediction of Molecular Markers in Glioma on Magnetic Resonance Imaging: A Systematic Review and Meta-Analysis

BACKGROUND

Molecular characterization of glioma has implications for prognosis, treatment planning, and prediction of treatment response. Current histopathology is limited by intratumoral heterogeneity and variability in detection methods. Advances in computational techniques have led to interest in mining quantitative imaging features to noninvasively detect genetic mutations.

OBJECTIVE

To evaluate the diagnostic accuracy of machine learning (ML) models in molecular subtyping gliomas on preoperative magnetic resonance imaging (MRI).

METHODS

A systematic search was performed following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) guidelines to identify studies up to April 1, 2020. Methodological quality of studies was assessed using the Quality Assessment for Diagnostic Accuracy Studies (QUADAS)-2. Diagnostic performance estimates were obtained using a bivariate model and heterogeneity was explored using metaregression.

RESULTS

Forty-four original articles were included. The pooled sensitivity and specificity for predicting isocitrate dehydrogenase (IDH) mutation in training datasets were 0.88 (95% CI 0.83-0.91) and 0.86 (95% CI 0.79-0.91), respectively, and 0.83 to 0.85 in validation sets. Use of data augmentation and MRI sequence type were weakly associated with heterogeneity. Both O6-methylguanine-DNA methyltransferase (MGMT) gene promoter methylation and 1p/19q codeletion could be predicted with a pooled sensitivity and specificity between 0.76 and 0.83 in training datasets.

CONCLUSION

ML application to preoperative MRI demonstrated promising results for predicting IDH mutation, MGMT methylation, and 1p/19q codeletion in glioma. Optimized ML models could lead to a noninvasive, objective tool that captures molecular information important for clinical decision making. Future studies should use multicenter data, external validation and investigate clinical feasibility of ML models.

Noninvasive Assessment of O(6)-Methylguanine-DNA Methyltransferase Promoter Methylation Status in World Health Organization Grade II-IV Glioma Using Histogram Analysis of Inflow-Based Vascular-Space-Occupancy Combined with Structural Magnetic Resonance Imaging

BACKGROUND

O(6)-methylguanine-DNA methyltransferase (MGMT) promoter methylation is an important prognostic factor for gliomas and is associated with tumor angiogenesis. Arteriolar cerebral blood volume (CBVa) obtained from inflow-based vascular-space-occupancy (iVASO) magnetic resonance imaging (MRI) is assumed to be an indicator of tumor microvasculature. Its preoperative predictive ability for MGMT promoter methylation remains unclear.

PURPOSE

To investigate the role of iVASO-CBVa histogram features in determining MGMT promoter methylation status of grade II-IV gliomas.

STUDY TYPE

Retrospective SUBJECTS: Forty-six patients consisting of 20 MGMT methylated and 26 unmethylated gliomas.

FIELD STRENGTH/SEQUENCE

3.0 T magnetic resonance images containing iVASO MRI, T₁ -weighted image (T₁ WI), T₂ -weighted image, T₂ -weighted fluid attenuated inversion recovery image images, and enhanced T₁ WI.

ASSESSMENT

Sixteen structural imaging features were visually evaluated on structural MRI and 14 CBVa histogram features were extracted from iVASO-CBVa maps.

STATISTICAL TESTS

Imaging features were screened and ranked using Fisher's exact test, Mann-Whitney U-test, and randomforest algorithm. Features with higher importance were selected to develop logistic regression models to determine MGMT methylation status. Receiver operating characteristics (ROC) curve with the area under the curve (AUC) and leave-one-out cross-validation (LOOCV) were used to assess effectiveness and stability.

RESULTS

The top two CBVa histogram features were root mean squared (RMS) and variance. The top two structural imaging features were contrast-enhancing component of the tumor (CET) location and tumor location. Both the CBVa model of RMS and variance (ROC, AUC = 0.867; LOOCV, AUC = 0.819) and the model of structural features (ROC, AUC = 0.882; LOOCV, AUC = 0.802) accurately identified MGMT methylation. The fusion model of CBVa RMS and CET location improved diagnostic performance (ROC, AUC = 0.931; LOOCV, AUC =0.906). DATA CONCLUSION: iVASO-CBVa has potential in evaluating MGMT methylation status in grade II-IV gliomas.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: Stage 2.

Differentiation of Pseudoprogression from True Progressionin Glioblastoma Patients after Standard Treatment: A Machine Learning Strategy Combinedwith Radiomics Features from T1-weighted Contrast-enhanced Imaging

Background

Based on conventional MRI images, it is difficult to differentiatepseudoprogression from true progressionin GBM patients after standard treatment, which isa critical issue associated with survival. The aim of this study was to evaluate the diagnostic performance of machine learning using radiomics modelfrom T₁-weighted contrast enhanced imaging(T₁CE) in differentiating pseudoprogression from true progression after standard treatment for GBM.

Methods

Seventy-sevenGBM patients, including 51 with true progression and 26 with pseudoprogression,who underwent standard treatment and T₁CE, were retrospectively enrolled.Clinical information, including sex, age, KPS score, resection extent, neurological deficit and mean radiation dose, were also recorded collected for each patient. The whole tumor enhancementwas manually drawn on the T₁CE image, and a total of texture 9675 features were extracted and fed to a two-step feature selection scheme. A random forest (RF) classifier was trained to separate the patients by their outcomes.The diagnostic efficacies of the radiomics modeland radiologist assessment were further compared by using theaccuracy (ACC), sensitivity and specificity.

Results

No clinical features showed statistically significant differences between true progression and pseudoprogression.The radiomic classifier demonstrated ACC, sensitivity, and specificity of 72.78%(95% confidence interval [CI]: 0.45,0.91), 78.36%(95%CI: 0.56,1.00) and 61.33%(95%CI: 0.20,0.82).The accuracy, sensitivity and specificity of three radiologists’ assessment were66.23%(95% CI: 0.55,0.76), 61.50%(95% CI: 0.43,0.78) and 68.62%(95% CI: 0.55,0.80); 55.84%(95% CI: 0.45,0.66),69.25%(95% CI: 0.50,0.84) and 49.13%(95% CI: 0.36,0.62); 55.84%(95% CI: 0.45,0.66), 69.23%(95% CI: 0.50,0.84) and 47.06%(95% CI: 0.34,0.61), respectively.

Conclusion

T₁CE–based radiomics showed better classification performance compared with radiologists’ assessment.The radiomics modelwas promising in differentiating pseudoprogression from true progression.

Can Tumor Location on Pre-treatment MRI Predict Likelihood of Pseudo-Progression vs. Tumor Recurrence in Glioblastoma?-A Feasibility Study

A significant challenge in Glioblastoma (GBM) management is identifying pseudo-progression (PsP), a benign radiation-induced effect, from tumor recurrence, on routine imaging following conventional treatment. Previous studies have linked tumor lobar presence and laterality to GBM outcomes, suggesting that disease etiology and progression in GBM may be impacted by tumor location. Hence, in this feasibility study, we seek to investigate the following question: Can tumor location on treatment-naïve MRI provide early cues regarding likelihood of a patient developing pseudo-progression vs. tumor recurrence? In this study, 74 pre-treatment Glioblastoma MRI scans with PsP (33) and tumor recurrence (41) were analyzed. First, enhancing lesion on Gd-T1w MRI and peri-lesional hyperintensities on T2w/FLAIR were segmented by experts and then registered to a brain atlas. Using patients from the two phenotypes, we construct two atlases by quantifying frequency of occurrence of enhancing lesion and peri-lesion hyperintensities, by averaging voxel intensities across the population. Analysis of differential involvement was then performed to compute voxel-wise significant differences (p-value < 0.05) across the atlases. Statistically significant clusters were finally mapped to a structural atlas to provide anatomic localization of their location. Our results demonstrate that patients with tumor recurrence showed prominence of their initial tumor in the parietal lobe, while patients with PsP showed a multi-focal distribution of the initial tumor in the frontal and temporal lobes, insula, and putamen. These preliminary results suggest that lateralization of pre-treatment lesions toward certain anatomical areas of the brain may allow to provide early cues regarding assessing likelihood of occurrence of pseudo-progression from tumor recurrence on MRI scans.

Automatic Prediction of MGMT Status in Glioblastoma via Deep Learning-Based MR Image Analysis

Methylation of the O⁶-methylguanine methyltransferase (MGMT) gene promoter is correlated with the effectiveness of the current standard of care in glioblastoma patients. In this study, a deep learning pipeline is designed for automatic prediction of MGMT status in 87 glioblastoma patients with contrast-enhanced T1W images and 66 with fluid-attenuated inversion recovery(FLAIR) images. The end-to-end pipeline completes both tumor segmentation and status classification. The better tumor segmentation performance comes from FLAIR images (Dice score, 0.897 ± 0.007) compared to contrast-enhanced T1WI (Dice score, 0.828 ± 0.108), and the better status prediction is also from the FLAIR images (accuracy, 0.827 ± 0.056; recall, 0.852 ± 0.080; precision, 0.821 ± 0.022; and F ₁ score, 0.836 ± 0.072). This proposed pipeline not only saves the time in tumor annotation and avoids interrater variability in glioma segmentation but also achieves good prediction of MGMT methylation status. It would help find molecular biomarkers from routine medical images and further facilitate treatment planning.

Precision Digital Oncology: Emerging Role of Radiomics-based Biomarkers and Artificial Intelligence for Advanced Imaging and Characterization of Brain Tumors

Advances in computerized image analysis and the use of artificial intelligence-based approaches for image-based analysis and construction of prediction algorithms represent a new era for noninvasive biomarker discovery. In recent literature, it has become apparent that radiologic images can serve as mineable databases that contain large amounts of quantitative features with potential clinical significance. Extraction and analysis of these quantitative features is commonly referred to as texture or radiomic analysis. Numerous studies have demonstrated applications for texture and radiomic characterization methods for assessing brain tumors to improve noninvasive predictions of tumor histologic characteristics, molecular profile, distinction of treatment-related changes, and prediction of patient survival. In this review, the current use and future potential of texture or radiomic-based approaches with machine learning for brain tumor image analysis and prediction algorithm construction will be discussed. This technology has the potential to advance the value of diagnostic imaging by extracting currently unused information on medical scans that enables more precise, personalized therapy; however, significant barriers must be overcome if this technology is to be successfully implemented on a wide scale for routine use in the clinical setting. Keywords: Adults and Pediatrics, Brain/Brain Stem, CNS, Computer Aided Diagnosis (CAD), Computer Applications-General (Informatics), Image Postprocessing, Informatics, Neural Networks, Neuro-Oncology, Oncology, Treatment Effects, Tumor Response Supplemental material is available for this article. © RSNA, 2020.

Analysis of MRI Data in Diagnostic Neuroradiology

Magnetic resonance imaging (MRI) is a noninvasive imaging tool for neuroradiological diagnosis. Numerous concepts of automated MRI analysis and the use of machine learning have been proposed to assist diagnosis and prognosis. While these academic innovations have proven effective in principle within controlled environments, their application to clinical practice has faced unmet requirements, such as the ability to perform reliably across a heterogeneous population, to work robustly in the presence of comorbidities, and to be invariant to scanner hardware and image quality. The lack of realistic confidence bounds and the inability to handle missing data have also reduced the application of most of these methods outside of academic studies. Mastering the complex challenges in the diagnostic process may help researchers discover novel biological constructs in multimodal data and improve stratification for clinical trials, paving the way for precision medicine. This review presents the state of the art of computerized brain MRI analysis for diagnostic purposes. We critically evaluate the current clinical usefulness of the methods and highlight challenges and future perspectives of the field.

Predicting MGMT Promoter Methylation of Glioblastoma from Dynamic Susceptibility Contrast Perfusion: A Radiomic Approach

BACKGROUND AND PURPOSE

This study aims to investigate whether radiomic quantitative image features (IFs) from perfusion dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) retain sufficient strength to predict O6-methylguanine-DNA methyltransferase promoter methylation (MGMT_pm) in newly diagnosed glioblastoma (GB) patients.

METHODS

We retrospectively reviewed the perfusion DSC-MRI of 59 patients with GB. Patients were classified into three groups: (1) unmethylated if MGMT_pm ≤ 9% (UM); (2) intermediate-methylated if MGMT_pm ranged between 10% and 29% (IM); (3) methylated if MGMT_pm ≥ 30% (M). A total of 92 quantitative IFs were obtained from relative cerebral blood volume and relative cerebral blood flow maps. The Mann-Whitney U-test was applied to assess whether there were statistical differences in IFs between patient groups. Those IFs showing significant difference between two patient groups were termed relevant IFs (rIFs). rIFs were uploaded to a machine learning model to predict the MGMT_pm.

RESULTS

No rIFs were found between UM and IM groups. Fourteen rIFs were found among UM-M, IM-M, and (UM + IM)-M groups. We built a multilayer perceptron deep learning model that classified patients as belonging to UM + IM and M group. The model performed well with 75% sensitivity, 85% specificity, and an area under the receiver-operating curve of .84.

CONCLUSION

rIFs from perfusion DSC-MRI are potential biomarkers in GBs with a ≥30% MGMT_pm. Otherwise, unmethylated and intermediate-methylated GBs lack of rIFs. Five of 14 rIFs show sufficient strength to build an accurate prediction model of MGMT_pm.

Decoding the Genomic Report for Radiologists

OBJECTIVE. The purpose of this review is to provide a guide for radiologists that explains the language and format of modern genomic reports and summarizes the relevance of this information for modern oncologic imaging. CONCLUSION. Genomic testing plays a critical role in guiding oncologic therapies in the age of targeted treatments. Understanding and interpreting genomic reports is a valuable skill for radiologists involved with oncologic imaging interpretation.

Prediction of Molecular Mutations in Diffuse Low-Grade Gliomas using MR Imaging Features

Diffuse low-grade gliomas (LGG) have been reclassified based on molecular mutations, which require invasive tumor tissue sampling. Tissue sampling by biopsy may be limited by sampling error, whereas non-invasive imaging can evaluate the entirety of a tumor. This study presents a non-invasive analysis of low-grade gliomas using imaging features based on the updated classification. We introduce molecular (MGMT methylation, IDH mutation, 1p/19q co-deletion, ATRX mutation, and TERT mutations) prediction methods of low-grade gliomas with imaging. Imaging features are extracted from magnetic resonance imaging data and include texture features, fractal and multi-resolution fractal texture features, and volumetric features. Training models include nested leave-one-out cross-validation to select features, train the model, and estimate model performance. The prediction models of MGMT methylation, IDH mutations, 1p/19q co-deletion, ATRX mutation, and TERT mutations achieve a test performance AUC of 0.83 ± 0.04, 0.84 ± 0.03, 0.80 ± 0.04, 0.70 ± 0.09, and 0.82 ± 0.04, respectively. Furthermore, our analysis shows that the fractal features have a significant effect on the predictive performance of MGMT methylation IDH mutations, 1p/19q co-deletion, and ATRX mutations. The performance of our prediction methods indicates the potential of correlating computed imaging features with LGG molecular mutations types and identifies candidates that may be considered potential predictive biomarkers of LGG molecular classification.

Whole-tumor radiomics analysis of DKI and DTI may improve the prediction of genotypes for astrocytomas: A preliminary study

PURPOSE

To test whether the whole-tumor radiomics analysis of DKI and DTI images could predict IDH and MGMTmet genotypes of astrocytomas.

METHOD

Sixty-two astrocytomas were enrolled. 364 radiomics features of whole tumor were extracted from mean-kurtosis (MK), and mean-diffusivity (MD) images, respectively. The multivariable logistic regression was used to select the most meaningful radiomics features for predicting IDH and MGMTmet genotypes. A radiomics model was built by logistic linear regression. A combined model was established based on selected radiomic, radiological and clinical features. To assess the difference between the models, the Z-test was performed.

RESULTS

The radiomics model built using the three most informative radiomics features for each genotype yielded an AUC of 0.831 ((95 % confidence interval [CI]: 0.721-0.918) for predicting IDH genotype, and 0.835 (95 %CI: 0.686-0.951) for MGMTmet genotype. A combined model for predicting IDH based on the radiomics score, age, and degree of edema reached an AUC of 0.885 (95 %CI: 0.802-0.955) and a combined model for predicting MGMTmet based on radiomics score and edema degree reached an AUC of 0.859 (95 %CI: 0.751-0.945) which was not significantly higher than the radiomics only model (P =  0.081).

CONCLUSIONS

The radiomics models via an objective whole-tumor analysis of MK and MD maps were independent imaging biomarkers for predicting IDH and MGMTmet genotypes, and the combined model further improved the performance for IDH, but not for MGMTmet.

Radiomics and MGMT promoter methylation for prognostication of newly diagnosed glioblastoma

We attempted to establish a magnetic resonance imaging (MRI)-based radiomic model for stratifying prognostic subgroups of newly diagnosed glioblastoma (GBM) patients and predicting O (6)-methylguanine-DNA methyltransferase promotor methylation (pMGMT-met) status of the tumor. Preoperative MRI scans from 201 newly diagnosed GBM patients were included in this study. A total of 489 texture features including the first-order feature, second-order features from 162 datasets, and location data from 182 datasets were collected. Supervised principal component analysis was used for prognostication and predictive modeling for pMGMT-met status was performed based on least absolute shrinkage and selection operator regression. 22 radiomic features that were correlated with prognosis were used to successfully stratify patients into high-risk and low-risk groups (p = 0.004, Log-rank test). The radiomic high- and low-risk stratification and pMGMT status were independent prognostic factors. As a matter of fact, predictive accuracy of the pMGMT methylation status was 67% when modeled by two significant radiomic features. A significant survival difference was observed among the combined high-risk group, combined intermediate-risk group (this group consists of radiomic low risk and pMGMT-unmet or radiomic high risk and pMGMT-met), and combined low-risk group (p = 0.0003, Log-rank test). Radiomics can be used to build a prognostic score for stratifying high- and low-risk GBM, which was an independent prognostic factor from pMGMT methylation status. On the other hand, predictive accuracy of the pMGMT methylation status by radiomic analysis was insufficient for practical use.

Noninvasive O6 Methylguanine-DNA Methyltransferase Status Prediction in Glioblastoma Multiforme Cancer Using Magnetic Resonance Imaging Radiomics Features: Univariate and Multivariate Radiogenomics Analysis

BACKGROUND

This study aimed to predict methylation status of the O₆ methylguanine-DNA methyltransferase (MGMT) gene promoter status by using magnetic resonance imaging radiomics features, as well as univariate and multivariate analysis.

METHODS

Eighty-two patients who had an MGMT methylation status were included in this study. Tumors were manually segmented in the 4 regions of magnetic resonance images, 1) whole tumor, 2) active/enhanced region, 3) necrotic regions, and 4) edema regions. About 7000 radiomics features were extracted for each patient. Feature selection and classifier were used to predict MGMT status through different machine learning algorithms. The area under the curve (AUC) of the receiver operating characteristic curve was used for model evaluations.

RESULTS

Regarding univariate analysis, the Inverse Variance feature From Gray Level Co-occurrence Matrix in whole tumor segment with 4.5 mm Sigma of Laplacian of Gaussian filter with AUC of 0.71 (P value = 0.002) was found to be the best predictor. For multivariate analysis, the Decision Tree classifier with Select from Model feature selector and LOG (Laplacian of Gaussian) filter in edema region had the highest performance (AUC, 0.78), followed by Ada-Boost classifier with Select from Model feature selector and LOG filter in edema region (AUC, 0.74).

CONCLUSIONS

This study showed that radiomics using machine learning algorithms is a feasible noninvasive approach to predict MGMT methylation status in patients with glioblastoma multiforme cancer.