Outcome prediction in patients with glioblastoma by using imaging, clinical, and genomic biomarkers: focus on the nonenhancing component of the tumor

VASARI-auto: Equitable, efficient, and economical featurisation of glioma MRI

The VASARI MRI feature set is a quantitative system designed to standardise glioma imaging descriptions. Though effective, deriving VASARI is time-consuming and seldom used clinically. We sought to resolve this problem with software automation and machine learning. Using glioma data from 1172 patients, we developed VASARI-auto, an automated labelling software applied to open-source lesion masks and an openly available tumour segmentation model. Consultant neuroradiologists independently quantified VASARI features in 100 held-out glioblastoma cases. We quantified 1) agreement across neuroradiologists and VASARI-auto, 2) software equity, 3) an economic workforce analysis, and 4) fidelity in predicting survival. Tumour segmentation was compatible with the current state of the art and equally performant regardless of age or sex. A modest inter-rater variability between in-house neuroradiologists was comparable to between neuroradiologists and VASARI-auto, with far higher agreement between VASARI-auto methods. The time for neuroradiologists to derive VASARI was substantially higher than VASARI-auto (mean time per case 317 vs. 3 s). A UK hospital workforce analysis forecast that three years of VASARI featurisation would demand 29,777 consultant neuroradiologist workforce hours and >£1.5 ($1.9) million, reducible to 332 hours of computing time (and £146 of power) with VASARI-auto. The best-performing survival model utilised VASARI-auto features instead of those derived by neuroradiologists. VASARI-auto is a highly efficient and equitable automated labelling system, a favourable economic profile if used as a decision support tool, and non-inferior survival prediction. Future work should iterate upon and integrate such tools to enhance patient care.

Ten Years of VASARI Glioma Features: Systematic Review and Meta-Analysis of Their Impact and Performance

BACKGROUND

Visually Accessible Rembrandt (Repository for Molecular Brain Neoplasia Data) Images (VASARI) features, a vocabulary to establish reproducible terminology for glioma reporting, have been applied for a decade, but a systematic performance evaluation is lacking.

PURPOSE

Our aim was to conduct a systematic review and meta-analysis of the performance of the VASARI features set for glioma assessment.

DATA SOURCES

MEDLINE, Web of Science, EMBASE, and the Cochrane Library were systematically searched until September 26, 2023.

STUDY SELECTION

Original articles predicting diagnosis, progression, and survival in patients with glioma were included.

DATA ANALYSIS

The modified Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool was applied to evaluate the risk-of-bias. The meta-analysis used a random effects model and forest plot visualizations, if ≥5 comparable studies with a low or medium risk of bias were provided.

DATA SYNTHESIS

Thirty-five studies (3304 patients) were included. Risk-of-bias scores were medium (n = 33) and low (n = 2). Recurring objectives were overall survival (n = 18) and isocitrate dehydrogenase mutation (IDH; n = 12) prediction. Progression-free survival was examined in 7 studies. In 4 studies (glioblastoma n = 2, grade 2/3 glioma n = 1, grade 3 glioma n = 1), a significant association was found between progression-free survival and single VASARI features. The single features predicting overall survival with the highest pooled hazard ratios were multifocality (hazard ratio = 1.80; 95%-CI, 1.21-2.67; I2 = 53%), ependymal invasion (hazard ratio = 1.73; 95% CI, 1.45-2.05; I2 = 0%), and enhancing tumor crossing the midline (hazard ratio = 2.08; 95% CI, 1.35-3.18; I2 = 52%). IDH mutation-predicting models combining VASARI features rendered a pooled area under the receiver operating characteristic curve of 0.82 (95% CI, 0.76-0.88) at considerable heterogeneity (I2 = 100%). Combined input models using VASARI plus clinical and/or radiomics features outperformed single data-type models in all relevant studies (n = 17).

LIMITATIONS

Studies were heterogeneously designed and often with a small sample size. Several studies used The Cancer Imaging Archive database, with likely overlapping cohorts. The meta-analysis for IDH was limited due to a high study heterogeneity.

CONCLUSIONS

Some VASARI features perform well in predicting overall survival and IDH mutation status, but combined models outperform single features. More studies with less heterogeneity are needed to increase the evidence level.

The prognostic relevance of a gene expression signature in MRI-defined highly vascularized glioblastoma

Background

The vascular heterogeneity of glioblastomas (GB) remains an important area of research, since tumor progression and patient prognosis are closely tied to this feature. With this study, we aim to identify gene expression profiles associated with MRI-defined tumor vascularity and to investigate its relationship with patient prognosis.

Methods

The study employed MRI parameters calculated with DSC Perfusion Quantification of ONCOhabitats glioma analysis software and RNA-seq data from the TCGA-GBM project dataset. In our study, we had a total of 147 RNA-seq samples, which 15 of them also had MRI parameter information. We analyzed the gene expression profiles associated with MRI-defined tumor vascularity using differential gene expression analysis and performed Log-rank tests to assess the correlation between the identified genes and patient prognosis.

Results

The findings of our research reveal a set of 21 overexpressed genes associated with the high vascularity pattern. Notably, several of these overexpressed genes have been previously implicated in worse prognosis based on existing literature. Our log-rank test further validates that the collective upregulation of these genes is indeed correlated with an unfavorable prognosis. This set of genes includes a variety of molecules, such as cytokines, receptors, ligands, and other molecules with diverse functions.

Conclusions

Our findings suggest that the set of 21 overexpressed genes in the High Vascularity group could potentially serve as prognostic markers for GB patients. These results highlight the importance of further investigating the relationship between the molecules such as cytokines or receptors underlying the vascularity in GB and its observation through MRI and developing targeted therapies for this aggressive disease.

Cluster-based prognostication in glioblastoma: Unveiling heterogeneity based on diffusion and perfusion similarities

BACKGROUND

While the association between diffusion and perfusion magnetic resonance imaging (MRI) and survival in glioblastoma is established, prognostic models for patients are lacking. This study employed clustering of functional imaging to identify distinct functional phenotypes in untreated glioblastomas, assessing their prognostic significance for overall survival.

METHODS

A total of 289 patients with glioblastoma who underwent preoperative multimodal MR imaging were included. Mean values of apparent diffusion coefficient normalized relative cerebral blood volume and relative cerebral blood flow were calculated for different tumor compartments and the entire tumor. Distinct imaging patterns were identified using partition around medoids (PAM) clustering on the training dataset, and their ability to predict overall survival was assessed. Additionally, tree-based machine-learning models were trained to ascertain the significance of features pertaining to cluster membership.

RESULTS

Using the training dataset (231/289) we identified 2 stable imaging phenotypes through PAM clustering with significantly different overall survival (OS). Validation in an independent test set revealed a high-risk group with a median OS of 10.2 months and a low-risk group with a median OS of 26.6 months (P = 0.012). Patients in the low-risk cluster had high diffusion and low perfusion values throughout, while the high-risk cluster displayed the reverse pattern. Including cluster membership in all multivariate Cox regression analyses improved performance (P ≤ 0.004 each).

CONCLUSIONS

Our research demonstrates that data-driven clustering can identify clinically relevant, distinct imaging phenotypes, highlighting the potential role of diffusion, and perfusion MRI in predicting survival rates of glioblastoma patients.

Meta-research: How many diagnostic or prognostic models published in radiological journals are evaluated externally?

OBJECTIVES

Prognostic and diagnostic models must work in their intended clinical setting, proven via "external evaluation", preferably by authors uninvolved with model development. By systematic review, we determined the proportion of models published in high-impact radiological journals that are evaluated subsequently.

METHODS

We hand-searched three radiological journals for multivariable diagnostic/prognostic models 2013-2015 inclusive, developed using regression. We assessed completeness of data presentation to allow subsequent external evaluation. We then searched literature to August 2022 to identify external evaluations of these index models.

RESULTS

We identified 98 index studies (73 prognostic; 25 diagnostic) describing 145 models. Only 15 (15%) index studies presented an evaluation (two external). No model was updated. Only 20 (20%) studies presented a model equation. Just 7 (15%) studies developing Cox models presented a risk table, and just 4 (9%) presented the baseline hazard. Two (4%) studies developing non-Cox models presented the intercept. Just 20 (20%) articles presented a Kaplan-Meier curve of the final model. The 98 index studies attracted 4224 citations (including 559 self-citations), median 28 per study. We identified just six (6%) subsequent external evaluations of an index model, five of which were external evaluations by researchers uninvolved with model development, and from a different institution.

CONCLUSIONS

Very few prognostic or diagnostic models published in radiological literature are evaluated externally, suggesting wasted research effort and resources. Authors' published models should present data sufficient to allow external evaluation by others. To achieve clinical utility, researchers should concentrate on model evaluation and updating rather than continual redevelopment.

CLINICAL RELEVANCE STATEMENT

The large majority of prognostic and diagnostic models published in high-impact radiological journals are never evaluated. It would be more efficient for researchers to evaluate existing models rather than practice continual redevelopment.

KEY POINTS

• Systematic review of highly cited radiological literature identified few diagnostic or prognostic models that were evaluated subsequently by researchers uninvolved with the original model. • Published radiological models frequently omit important information necessary for others to perform an external evaluation: Only 20% of studies presented a model equation or nomogram. • A large proportion of research citing published models focuses on redevelopment and ignores evaluation and updating, which would be a more efficient use of research resources.

Added prognostic value of 3D deep learning-derived features from preoperative MRI for adult-type diffuse gliomas

BACKGROUND

To investigate the prognostic value of spatial features from whole-brain MRI using a three-dimensional (3D) convolutional neural network for adult-type diffuse gliomas.

METHODS

In a retrospective, multicenter study, 1925 diffuse glioma patients were enrolled from 5 datasets: SNUH (n = 708), UPenn (n = 425), UCSF (n = 500), TCGA (n = 160), and Severance (n = 132). The SNUH and Severance datasets served as external test sets. Precontrast and postcontrast 3D T1-weighted, T2-weighted, and T2-FLAIR images were processed as multichannel 3D images. A 3D-adapted SE-ResNeXt model was trained to predict overall survival. The prognostic value of the deep learning-based prognostic index (DPI), a spatial feature-derived quantitative score, and established prognostic markers were evaluated using Cox regression. Model evaluation was performed using the concordance index (C-index) and Brier score.

RESULTS

The MRI-only median DPI survival prediction model achieved C-indices of 0.709 and 0.677 (BS = 0.142 and 0.215) and survival differences (P < 0.001 and P = 0.002; log-rank test) for the SNUH and Severance datasets, respectively. Multivariate Cox analysis revealed DPI as a significant prognostic factor, independent of clinical and molecular genetic variables: hazard ratio = 0.032 and 0.036 (P < 0.001 and P = 0.004) for the SNUH and Severance datasets, respectively. Multimodal prediction models achieved higher C-indices than models using only clinical and molecular genetic variables: 0.783 vs. 0.774, P = 0.001, SNUH; 0.766 vs. 0.748, P = 0.023, Severance.

CONCLUSIONS

The global morphologic feature derived from 3D CNN models using whole-brain MRI has independent prognostic value for diffuse gliomas. Combining clinical, molecular genetic, and imaging data yields the best performance.

Distinguishing Tumor Cell Infiltration and Vasogenic Edema in the Peritumoral Region of Glioblastoma at the Voxel Level via Conventional MRI Sequences

RATIONALE AND OBJECTIVES

The peritumoral region of glioblastoma (GBM) is composed of infiltrating tumor cells and vasogenic edema, which are difficult to distinguish manually on MRI. To distinguish tumor cell infiltration and vasogenic edema in GBM peritumoral regions, it is crucial to develop a method that is precise, effective, and widely applicable.

MATERIALS AND METHODS

We retrieved the image characteristics of 379,730 voxels (marker of tumor infiltration) from 28 non-enhanced gliomas and 365,262 voxels (marker of edema) from the peritumoral edema region of 14 meningiomas on conventional MRI sequences (T1-weighted image, the contrast-enhancing T1-weighted image, the T2-weighted image, the T2-fluid attenuated inversion recovery image, and the apparent diffusion coefficient map). Using the SVM classifier, a model for predicting tumor cell infiltration and vasogenic edema at the voxel level was developed. The accuracy of the model's predictions was then evaluated using 15 GBM patients who underwent stereotactic biopsies.

RESULTS

The area under the curve (AUC), accuracy, sensitivity, and specificity of the prediction model were 0.93, 0.84, 0.83, and 0.85 in the training set, and 0.90, 0.82, 0.83, and 0.83 in the test set (704,992 voxels), respectively. The pathology verification of 28 biopsy points with an accuracy of 0.79.

CONCLUSION

At the voxel level, it seems possible to forecast tumor cell infiltration and vasogenic edema in the peritumoral region of GBM based on conventional MRI sequences.

Artificial intelligence in neuro-oncology

Artificial intelligence (AI) describes the application of computer algorithms to the solution of problems that have traditionally required human intelligence. Although formal work in AI has been slowly advancing for almost 70 years, developments in the last decade, and particularly in the last year, have led to an explosion of AI applications in multiple fields. Neuro-oncology has not escaped this trend. Given the expected integration of AI-based methods to neuro-oncology practice over the coming years, we set to provide an overview of existing technologies as they are applied to the neuropathology and neuroradiology of brain tumors. We highlight current benefits and limitations of these technologies and offer recommendations on how to appraise novel AI-tools as they undergo consideration for integration into clinical workflows.

Vascular differences between IDH-wildtype glioblastoma and astrocytoma IDH-mutant grade 4 at imaging and transcriptomic levels

Global agreement in central nervous system (CNS) tumor classification is essential for predicting patient prognosis and determining the correct course of treatment, as well as for stratifying patients for clinical trials at international level. The last update by the World Health Organization of CNS tumor classification and grading in 2021 considered, for the first time, IDH-wildtype glioblastoma and astrocytoma IDH-mutant grade 4 as different tumors. Mutations in the genes isocitrate dehydrogenase (IDH) 1 and 2 occur early and, importantly, contribute to gliomagenesis. IDH mutation produces a metabolic reprogramming of tumor cells, thus affecting the processes of hypoxia and vascularity, resulting in a clear advantage for those patients who present with IDH-mutated astrocytomas. Despite the clinical relevance of IDH mutation, current protocols do not include full sequencing for every patient. Alternative biomarkers could be useful and complementary to obtain a more reliable classification. In this sense, magnetic resonance imaging (MRI)-perfusion biomarkers, such as relative cerebral blood volume and flow, could be useful from the moment of presurgery, without incurring additional financial costs or requiring extra effort. The main purpose of this work is to analyze the vascular and hemodynamic differences between IDH-wildtype glioblastoma and IDH-mutant astrocytoma. To achieve this, we evaluate and validate the association between dynamic susceptibility contrast-MRI perfusion biomarkers and IDH mutation status. In addition, to gain a deeper understanding of the vascular differences in astrocytomas depending on the IDH mutation, we analyze the transcriptomic bases of the vascular differences.

Aptamer-functionalized quantum dots as theranostic nanotools against cancer and bacterial infections: A comprehensive overview of recent trends

Aptamers (Apts) are synthetic nucleic acid ligands that can be engineered to target various molecules, including amino acids, proteins, and pharmaceuticals. Through a series of adsorption, recovery, and amplification steps, Apts are extracted from combinatorial libraries of synthesized nucleic acids. Using aptasensors in bioanalysis and biomedicine can be improved by combining them with nanomaterials. Moreover, Apt-associated nanomaterials, including liposomes, polymeric, dendrimers, carbon nanomaterials, silica, nanorods, magnetic NPs, and quantum dots (QDs), have been widely used as promising nanotools in biomedicine. Following surface modifications and conjugation with appropriate functional groups, these nanomaterials can be successfully used in aptasensing. Advanced biological assays can use Apts immobilized on QD surfaces through physical interaction and chemical bonding. Accordingly, modern QD aptasensing platforms rely on interactions between QDs, Apts, and targets to detect them. QD-Apt conjugates can be used to directly detect prostate, ovarian, colorectal, and lung cancers or simultaneously detect biomarkers associated with these malignancies. Tenascin-C, mucin 1, prostate-specific antigen, prostate-specific membrane antigen, nucleolin, growth factors, and exosomes are among the cancer biomarkers that can be sensitively detected using such bioconjugates. Furthermore, Apt-conjugated QDs have shown great potential for controlling bacterial infections such as Bacillus thuringiensis, Pseudomonas aeruginosa, Escherichia coli, Acinetobacter baumannii, Campylobacter jejuni, Staphylococcus aureus, and Salmonella typhimurium. This comprehensive review discusses recent advancements in the design of QD-Apt bioconjugates and their applications in cancer and bacterial theranostics.

Construction of 3D and 2D contrast-enhanced CT radiomics for prediction of CGB3 expression level and clinical prognosis in bladder cancer

Objective

The purpose of this study was to construct a 3D and 2D contrast-enhanced computed tomography (CECT) radiomics model to predict CGB3 levels and assess its prognostic abilities in bladder cancer (Bca) patients.

Methods

Transcriptome data and CECT images of Bca patients were downloaded from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA) database. Clinical data of 43 cases from TCGA and TCIA were used for radiomics model evaluation. The Volume of interest (VOI) (3D) and region of interest (ROI) (2D) radiomics features were extracted. For the construction of predicting radiomics models, least absolute shrinkage and selection operator regression were used, and the filtered radiomics features were fitted using the logistic regression algorithm (LR). The model's effectiveness was measured using 10-fold cross-validation and the area under the receiver operating characteristic curve (AUC of ROC).

Result

CGB3 was a differential expressed prognosis-related gene and involved in the immune response process of plasma cells and T cell gamma delta. The high levels of CGB3 are a risk element for overall survival (OS). The AUCs of VOI and ROI radiomics models in the training set were 0.841 and 0.776, while in the validation set were 0.815 and 0.754, respectively. The Delong test revealed that the AUCs of the two models were not statistically different, and both models had good predictive performance.

Conclusion

The CGB3 expression level is an important prognosis factor for Bca patients. Both 3D and 2D CECT radiomics are effective in predicting CGB3 expression levels.

Perifocal Zone of Brain Gliomas: Application of Diffusion Kurtosis and Perfusion MRI Values for Tumor Invasion Border Determination

(1) Purpose: To determine the borders of malignant gliomas with diffusion kurtosis and perfusion MRI biomarkers. (2) Methods: In 50 high-grade glioma patients, diffusion kurtosis and pseudo-continuous arterial spin labeling (pCASL) cerebral blood flow (CBF) values were determined in contrast-enhancing area, in perifocal infiltrative edema zone, in the normal-appearing peritumoral white matter of the affected cerebral hemisphere, and in the unaffected contralateral hemisphere. Neuronavigation-guided biopsy was performed from all affected hemisphere regions. (3) Results: We showed significant differences between the DKI values in normal-appearing peritumoral white matter and unaffected contralateral hemisphere white matter. We also established significant (p < 0.05) correlations of DKI with Ki-67 labeling index and Bcl-2 expression activity in highly perfused enhancing tumor core and in perifocal infiltrative edema zone. CBF correlated with Ki-67 LI in highly perfused enhancing tumor core. One hundred percent of perifocal infiltrative edema tissue samples contained tumor cells. All glioblastoma samples expressed CD133. In the glioblastoma group, several normal-appearing white matter specimens were infiltrated by tumor cells and expressed CD133. (4) Conclusions: DKI parameters reveal changes in brain microstructure invisible on conventional MRI, e.g., possible infiltration of normal-appearing peritumoral white matter by glioma cells. Our results may be useful for plotting individual tumor invasion maps for brain glioma surgery or radiotherapy planning.

Development of prediction models for one-year brain tumour survival using machine learning: a comparison of accuracy and interpretability

BACKGROUND AND OBJECTIVE

Prediction of survival in patients diagnosed with a brain tumour is challenging because of heterogeneous tumour behaviours and treatment response. Advances in machine learning have led to the development of clinical prognostic models, but due to the lack of model interpretability, integration into clinical practice is almost non-existent. In this retrospective study, we compare five classification models with varying degrees of interpretability for the prediction of brain tumour survival greater than one year following diagnosis.

METHODS

1028 patients aged ≥16 years with a brain tumour diagnosis between April 2012 and April 2020 were included in our study. Three intrinsically interpretable 'glass box' classifiers (Bayesian Rule Lists [BRL], Explainable Boosting Machine [EBM], and Logistic Regression [LR]), and two 'black box' classifiers (Random Forest [RF] and Support Vector Machine [SVM]) were trained on electronic patients records for the prediction of one-year survival. All models were evaluated using balanced accuracy (BAC), F1-score, sensitivity, specificity, and receiver operating characteristics. Black box model interpretability and misclassified predictions were quantified using SHapley Additive exPlanations (SHAP) values and model feature importance was evaluated by clinical experts.

RESULTS

The RF model achieved the highest BAC of 78.9%, closely followed by SVM (77.7%), LR (77.5%) and EBM (77.1%). Across all models, age, diagnosis (tumour type), functional features, and first treatment were top contributors to the prediction of one year survival. We used EBM and SHAP to explain model misclassifications and investigated the role of feature interactions in prognosis.

CONCLUSION

Interpretable models are a natural choice for the domain of predictive medicine. Intrinsically interpretable models, such as EBMs, may provide an advantage over traditional clinical assessment of brain tumour prognosis by weighting potential risk factors and their interactions that may be unknown to clinicians. An agreement between model predictions and clinical knowledge is essential for establishing trust in the models decision making process, as well as trust that the model will make accurate predictions when applied to new data.

Deep Learning of Time-Signal Intensity Curves from Dynamic Susceptibility Contrast Imaging Enables Tissue Labeling and Prediction of Survival in Glioblastoma

BACKGROUND AND PURPOSE

An autoencoder can learn representative time-signal intensity patterns to provide tissue heterogeneity measures using dynamic susceptibility contrast MR imaging. The aim of this study was to investigate whether such an autoencoder-based pattern analysis could provide interpretable tissue labeling and prognostic value in isocitrate dehydrogenase (IDH) wild-type glioblastoma.

MATERIALS AND METHODS

Preoperative dynamic susceptibility contrast MR images were obtained from 272 patients with IDH wild-type glioblastoma (training and validation, 183 and 89 patients, respectively). The autoencoder was applied to the dynamic susceptibility contrast MR imaging time-signal intensity curves of tumor and peritumoral areas. Representative perfusion patterns were defined by voxelwise K-means clustering using autoencoder latent features. Perfusion patterns were labeled by comparing parameters with anatomic reference tissues for baseline, signal drop, and percentage recovery. In the validation set (n = 89), a survival model was created from representative patterns and clinical predictors using Cox proportional hazard regression analysis, and its performance was calculated using the Harrell C-index.

RESULTS

Eighty-nine patients were enrolled. Five representative perfusion patterns were used to characterize tissues as high angiogenic tumor, low angiogenic/cellular tumor, perinecrotic lesion, infiltrated edema, and vasogenic edema. Of these, the low angiogenic/cellular tumor (hazard ratio, 2.18; P = .047) and infiltrated edema patterns (hazard ratio, 1.88; P = .009) in peritumoral areas showed significant prognostic value. The combined perfusion patterns and clinical predictors (C-index, 0.72) improved prognostication when added to clinical predictors (C-index, 0.55).

CONCLUSIONS

The autoencoder perfusion pattern analysis enabled tissue characterization of peritumoral areas, providing heterogeneity and dynamic information that may provide useful prognostic information in IDH wild-type glioblastoma.

Protein disulfide-isomerase A4 confers glioblastoma angiogenesis promotion capacity and resistance to anti-angiogenic therapy

Introduction

Increasing evidence has revealed the key activity of protein disulfide isomerase A4 (PDIA4) in the endoplasmic reticulum stress (ERS) response. However, the role of PDIA4 in regulating glioblastoma (GBM)-specific pro-angiogenesis is still unknown.

Methods

The expression and prognostic role of PDIA4 were analyzed using a bioinformatics approach and were validated in 32 clinical samples and follow-up data. RNA-sequencing was used to search for PDIA4-associated biological processes in GBM cells, and proteomic mass spectrum (MS) analysis was used to screen for potential PDIA4 substrates. Western blotting, real-time quantitative polymerase chain reaction (RT-qPCR), and enzyme-linked immunosorbent assays (ELISA) were used to measure the levels of the involved factors. Cell migration and tube formation assays determined the pro-angiogenesis activity of PDIA4 in vitro. An intracranial U87 xenograft GBM animal model was constructed to evaluate the pro-angiogenesis role of PDIA4 in vivo.

Results

Aberrant overexpression of PDIA4 was associated with a poor prognosis in patients with GBM, although PDIA4 could also functionally regulate intrinsic GBM secretion of vascular endothelial growth factor-A (VEGF-A) through its active domains of Cys-X-X-Cys (CXXC) oxidoreductase. Functionally, PDIA4 exhibits pro-angiogenesis activity both in vitro and in vivo, and can be upregulated by ERS through transcriptional regulation of X-box binding protein 1 (XBP1). The XBP1/PDIA4/VEGFA axis partially supports the mechanism underlying GBM cell survival under ER stress. Further, GBM cells with higher expression of PDIA4 showed resistance to antiangiogenic therapy in vivo.

Conclusions

Our findings revealed the pro-angiogenesis role of PDIA4 in GBM progression and its potential impact on GBM survival under a harsh microenvironment. Targeting PDIA4 might help to improve the efficacy of antiangiogenic therapy in patients with GBM.

Integrative multi-omics networks identify PKCδ and DNA-PK as master kinases of glioblastoma subtypes and guide targeted cancer therapy

Despite producing a panoply of potential cancer-specific targets, the proteogenomic characterization of human tumors has yet to demonstrate value for precision cancer medicine. Integrative multi-omics using a machine-learning network identified master kinases responsible for effecting phenotypic hallmarks of functional glioblastoma subtypes. In subtype-matched patient-derived models, we validated PKCδ and DNA-PK as master kinases of glycolytic/plurimetabolic and proliferative/progenitor subtypes, respectively, and qualified the kinases as potent and actionable glioblastoma subtype-specific therapeutic targets. Glioblastoma subtypes were associated with clinical and radiomics features, orthogonally validated by proteomics, phospho-proteomics, metabolomics, lipidomics and acetylomics analyses, and recapitulated in pediatric glioma, breast and lung squamous cell carcinoma, including subtype specificity of PKCδ and DNA-PK activity. We developed a probabilistic classification tool that performs optimally with RNA from frozen and paraffin-embedded tissues, which can be used to evaluate the association of therapeutic response with glioblastoma subtypes and to inform patient selection in prospective clinical trials.

Magnetic Resonance Imaging of Primary Adult Brain Tumors: State of the Art and Future Perspectives

MRI is undoubtedly the cornerstone of brain tumor imaging, playing a key role in all phases of patient management, starting from diagnosis, through therapy planning, to treatment response and/or recurrence assessment. Currently, neuroimaging can describe morphologic and non-morphologic (functional, hemodynamic, metabolic, cellular, microstructural, and sometimes even genetic) characteristics of brain tumors, greatly contributing to diagnosis and follow-up. Knowing the technical aspects, strength and limits of each MR technique is crucial to correctly interpret MR brain studies and to address clinicians to the best treatment strategy. This article aimed to provide an overview of neuroimaging in the assessment of adult primary brain tumors. We started from the basilar role of conventional/morphological MR sequences, then analyzed, one by one, the non-morphological techniques, and finally highlighted future perspectives, such as radiomics and artificial intelligence.

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.

Cluster Analysis of DSC MRI, Dynamic Contrast-Enhanced MRI, and DWI Parameters Associated with Prognosis in Patients with Glioblastoma after Removal of the Contrast-Enhancing Component: A Preliminary Study

BACKGROUND AND PURPOSE

No report has been published on the use of DSC MR imaging, DCE MR imaging, and DWI parameters in combination to create a prognostic prediction model in glioblastoma patients. The aim of this study was to develop a machine learning-based model to find preoperative multiparametric MR imaging parameters associated with prognosis in patients with glioblastoma. Normalized CBV, volume transfer constant, and ADC of the nonenhancing T2 high-signal-intensity lesions were evaluated using K-means clustering.

MATERIALS AND METHODS

A total of 142 patients with glioblastoma who underwent preoperative MR imaging and total resection were included in this retrospective study. From the normalized CBV, volume transfer constant, and ADC maps, the parametric data were sorted using the K-means clustering method. Patients were divided into training and test sets (ratio, 1:1), and the optimal number of clusters was determined using receiver operating characteristic analysis. Kaplan-Meier survival analysis and log-rank tests were performed to identify potential parametric predictors. A multivariate Cox proportional hazard model was conducted to adjust for clinical predictors.

RESULTS

The nonenhancing T2 high-signal-intensity lesions were divided into 6 clusters. The cluster (class 4) with the relatively low normalized CBV and volume transfer constant value and the lowest ADC values was most associated with predicting glioblastoma prognosis. The optimal cutoff of the class 4 volume fraction of nonenhancing T2 high-signal-intensity lesions predicting 1-year progression-free survival was 9.70%, below which the cutoff was associated with longer progression-free survival. Two Kaplan-Meier curves based on the cutoff value showed a statistically significant difference (P = .037). When we adjusted for all clinical predictors, the cluster with the relatively low normalized CBV and volume transfer constant values and the lowest ADC value was an independent prognostic marker (hazard ratio, 3.04; P = .048). The multivariate Cox proportional hazard model showed a concordance index of 0.699 for progression-free survival.

CONCLUSIONS

Our model showed that nonenhancing T2 high-signal-intensity lesions with the relatively low normalized CBV, low volume transfer constant values, and the lowest ADC values could serve as useful prognostic imaging markers for predicting survival outcomes in patients with glioblastoma.

The federated tumor segmentation (FeTS) tool: an open-source solution to further solid tumor research

Objective.De-centralized data analysis becomes an increasingly preferred option in the healthcare domain, as it alleviates the need for sharing primary patient data across collaborating institutions. This highlights the need for consistent harmonized data curation, pre-processing, and identification of regions of interest based on uniform criteria.Approach.Towards this end, this manuscript describes theFederatedTumorSegmentation (FeTS) tool, in terms of software architecture and functionality.Main results.The primary aim of the FeTS tool is to facilitate this harmonized processing and the generation of gold standard reference labels for tumor sub-compartments on brain magnetic resonance imaging, and further enable federated training of a tumor sub-compartment delineation model across numerous sites distributed across the globe, without the need to share patient data.Significance.Building upon existing open-source tools such as the Insight Toolkit and Qt, the FeTS tool is designed to enable training deep learning models targeting tumor delineation in either centralized or federated settings. The target audience of the FeTS tool is primarily the computational researcher interested in developing federated learning models, and interested in joining a global federation towards this effort. The tool is open sourced athttps://github.com/FETS-AI/Front-End.

Predicting Survival in Patients with Brain Tumors: Current State-of-the-Art of AI Methods Applied to MRI

Given growing clinical needs, in recent years Artificial Intelligence (AI) techniques have increasingly been used to define the best approaches for survival assessment and prediction in patients with brain tumors. Advances in computational resources, and the collection of (mainly) public databases, have promoted this rapid development. This narrative review of the current state-of-the-art aimed to survey current applications of AI in predicting survival in patients with brain tumors, with a focus on Magnetic Resonance Imaging (MRI). An extensive search was performed on PubMed and Google Scholar using a Boolean research query based on MeSH terms and restricting the search to the period between 2012 and 2022. Fifty studies were selected, mainly based on Machine Learning (ML), Deep Learning (DL), radiomics-based methods, and methods that exploit traditional imaging techniques for survival assessment. In addition, we focused on two distinct tasks related to survival assessment: the first on the classification of subjects into survival classes (short and long-term or eventually short, mid and long-term) to stratify patients in distinct groups. The second focused on quantification, in days or months, of the individual survival interval. Our survey showed excellent state-of-the-art methods for the first, with accuracy up to ∼98%. The latter task appears to be the most challenging, but state-of-the-art techniques showed promising results, albeit with limitations, with C-Index up to ∼0.91. In conclusion, according to the specific task, the available computational methods perform differently, and the choice of the best one to use is non-univocal and dependent on many aspects. Unequivocally, the use of features derived from quantitative imaging has been shown to be advantageous for AI applications, including survival prediction. This evidence from the literature motivates further research in the field of AI-powered methods for survival prediction in patients with brain tumors, in particular, using the wealth of information provided by quantitative MRI techniques.

The University of Pennsylvania glioblastoma (UPenn-GBM) cohort: advanced MRI, clinical, genomics, & radiomics

Glioblastoma is the most common aggressive adult brain tumor. Numerous studies have reported results from either private institutional data or publicly available datasets. However, current public datasets are limited in terms of: a) number of subjects, b) lack of consistent acquisition protocol, c) data quality, or d) accompanying clinical, demographic, and molecular information. Toward alleviating these limitations, we contribute the "University of Pennsylvania Glioblastoma Imaging, Genomics, and Radiomics" (UPenn-GBM) dataset, which describes the currently largest publicly available comprehensive collection of 630 patients diagnosed with de novo glioblastoma. The UPenn-GBM dataset includes (a) advanced multi-parametric magnetic resonance imaging scans acquired during routine clinical practice, at the University of Pennsylvania Health System, (b) accompanying clinical, demographic, and molecular information, (d) perfusion and diffusion derivative volumes, (e) computationally-derived and manually-revised expert annotations of tumor sub-regions, as well as (f) quantitative imaging (also known as radiomic) features corresponding to each of these regions. This collection describes our contribution towards repeatable, reproducible, and comparative quantitative studies leading to new predictive, prognostic, and diagnostic assessments.

Glioblastoma Stem-like Cell Detection Using Perfusion and Diffusion MRI

Simple Summary

Glioblastoma stem-like cells (GSCs) are known to be aggressive and radio-resistant and proliferate heterogeneously in preferred environments. Additionally, quantitative diffusion and perfusion MRI biomarkers provide insight into the tissue micro-environment. This study assessed the sensitivity of these imaging biomarkers to GSCs in the hyperintensities-FLAIR region, where relapses may occur. A total of 16 patients underwent an MRI session and biopsies were extracted to study the GSCs. In vivo and in vitro biomarkers were compared and both Apparent Diffusion Coefficient (ADC) and relative Cerebral Blood Volume (rCBV) MRI metrics were found to be good predictors of GSCs presence and aggressiveness.

Abstract

Purpose: With current gold standard treatment, which associates maximum safe surgery and chemo-radiation, the large majority of glioblastoma patients relapse within a year in the peritumoral non contrast-enhanced region (NCE). A subpopulation of glioblastoma stem-like cells (GSC) are known to be particularly radio-resistant and aggressive, and are thus suspected to be the cause of these relapses. Previous studies have shown that their distribution is heterogeneous in the NCE compartment, but no study exists on the sensitivity of medical imaging for localizing these cells. In this work, we propose to study the magnetic resonance (MR) signature of these infiltrative cells. Methods: In the context of a clinical trial on 16 glioblastoma patients, relative Cerebral Blood Volume (rCBV) and Apparent Diffusion Coefficient (ADC) were measured in a preoperative diffusion and perfusion MRI examination. During surgery, two biopsies were extracted using image-guidance in the hyperintensities-FLAIR region. GSC subpopulation was quantified within the biopsies and then cultivated in selective conditions to determine their density and aggressiveness. Results: Low ADC was found to be a good predictor of the time to GSC neurospheres formation in vitro. In addition, GSCs were found in higher concentrations in areas with high rCBV. Conclusions: This study confirms that GSCs have a critical role for glioblastoma aggressiveness and supports the idea that peritumoral sites with low ADC or high rCBV should be preferably removed when possible during surgery and targeted by radiotherapy.

Clinical measures, radiomics, and genomics offer synergistic value in AI-based prediction of overall survival in patients with glioblastoma

Multi-omic data, i.e., clinical measures, radiomic, and genetic data, capture multi-faceted tumor characteristics, contributing to a comprehensive patient risk assessment. Here, we investigate the additive value and independent reproducibility of integrated diagnostics in prediction of overall survival (OS) in isocitrate dehydrogenase (IDH)-wildtype GBM patients, by combining conventional and deep learning methods. Conventional radiomics and deep learning features were extracted from pre-operative multi-parametric MRI of 516 GBM patients. Support vector machine (SVM) classifiers were trained on the radiomic features in the discovery cohort (n = 404) to categorize patient groups of high-risk (OS < 6 months) vs all, and low-risk (OS ≥ 18 months) vs all. The trained radiomic model was independently tested in the replication cohort (n = 112) and a patient-wise survival prediction index was produced. Multivariate Cox-PH models were generated for the replication cohort, first based on clinical measures solely, and then by layering on radiomics and molecular information. Evaluation of the high-risk and low-risk classifiers in the discovery/replication cohorts revealed area under the ROC curves (AUCs) of 0.78 (95% CI 0.70-0.85)/0.75 (95% CI 0.64-0.79) and 0.75 (95% CI 0.65-0.84)/0.63 (95% CI 0.52-0.71), respectively. Cox-PH modeling showed a concordance index of 0.65 (95% CI 0.6-0.7) for clinical data improving to 0.75 (95% CI 0.72-0.79) for the combination of all omics. This study signifies the value of integrated diagnostics for improved prediction of OS in GBM.

FLAIRectomy: Resecting beyond the Contrast Margin for Glioblastoma

The standard of care for isocitrate dehydrogenase (IDH)-wildtype glioblastoma (GBM) is maximal resection followed by chemotherapy and radiation. Studies investigating the resection of GBM have primarily focused on the contrast enhancing portion of the tumor on magnetic resonance imaging. Histopathological studies, however, have demonstrated tumor infiltration within peri-tumoral fluid-attenuated inversion recovery (FLAIR) abnormalities, which is often not resected. The histopathology of FLAIR and local recurrence patterns of GBM have prompted interest in the resection of peri-tumoral FLAIR, or FLAIRectomy. To this point, recent studies have suggested a significant survival benefit associated with safe peri-tumoral FLAIR resection. In this review, we discuss the evidence surrounding the composition of peri-tumoral FLAIR, outcomes associated with FLAIRectomy, future directions of the field, and potential implications for patients.

Hemodynamic Imaging in Cerebral Diffuse Glioma-Part B: Molecular Correlates, Treatment Effect Monitoring, Prognosis, and Future Directions

Gliomas, and glioblastoma in particular, exhibit an extensive intra- and inter-tumoral molecular heterogeneity which represents complex biological features correlating to the efficacy of treatment response and survival. From a neuroimaging point of view, these specific molecular and histopathological features may be used to yield imaging biomarkers as surrogates for distinct tumor genotypes and phenotypes. The development of comprehensive glioma imaging markers has potential for improved glioma characterization that would assist in the clinical work-up of preoperative treatment planning and treatment effect monitoring. In particular, the differentiation of tumor recurrence or true progression from pseudoprogression, pseudoresponse, and radiation-induced necrosis can still not reliably be made through standard neuroimaging only. Given the abundant vascular and hemodynamic alterations present in diffuse glioma, advanced hemodynamic imaging approaches constitute an attractive area of clinical imaging development. In this context, the inclusion of objective measurable glioma imaging features may have the potential to enhance the individualized care of diffuse glioma patients, better informing of standard-of-care treatment efficacy and of novel therapies, such as the immunotherapies that are currently increasingly investigated. In Part B of this two-review series, we assess the available evidence pertaining to hemodynamic imaging for molecular feature prediction, in particular focusing on isocitrate dehydrogenase (IDH) mutation status, MGMT promoter methylation, 1p19q codeletion, and EGFR alterations. The results for the differentiation of tumor progression/recurrence from treatment effects have also been the focus of active research and are presented together with the prognostic correlations identified by advanced hemodynamic imaging studies. Finally, the state-of-the-art concepts and advancements of hemodynamic imaging modalities are reviewed together with the advantages derived from the implementation of radiomics and machine learning analyses pipelines.

Prediction of Glioma Grade Using Intratumoral and Peritumoral Radiomic Features From Multiparametric MRI Images

The accurate prediction of glioma grade before surgery is essential for treatment planning and prognosis. Since the gold standard (i.e., biopsy)for grading gliomas is both highly invasive and expensive, and there is a need for a noninvasive and accurate method. In this study, we proposed a novel radiomics-based pipeline by incorporating the intratumoral and peritumoral features extracted from preoperative mpMRI scans to accurately and noninvasively predict glioma grade. To address the unclear peritumoral boundary, we designed an algorithm to capture the peritumoral region with a specified radius. The mpMRI scans of 285 patients derived from a multi-institutional study were adopted. A total of 2153 radiomic features were calculated separately from intratumoral volumes (ITVs)and peritumoral volumes (PTVs)on mpMRI scans, and then refined using LASSO and mRMR feature ranking methods. The top-ranking radiomic features were entered into the classifiers to build radiomic signatures for predicting glioma grade. The prediction performance was evaluated with five-fold cross-validation on a patient-level split. The radiomic signatures utilizing the features of ITV and PTV both show a high accuracy in predicting glioma grade, with AUCs reaching 0.968. By incorporating the features of ITV and PTV, the AUC of IPTV radiomic signature can be increased to 0.975, which outperforms the state-of-the-art methods. Additionally, our proposed method was further demonstrated to have strong generalization performance in an external validation dataset with 65 patients. The source code of our implementation is made publicly available at https://github.com/chengjianhong/glioma_grading.git.

Clinical factors and conventional MRI may independently predict progression-free survival and overall survival in adult pilocytic astrocytomas

PURPOSE

Pilocytic astrocytoma (PA) is rare in adults, and only limited knowledge on the clinical course and prognosis has been available. The combination of clinical information and comprehensive imaging parameters could be used for accurate prognostic stratification in adult PA patients. This study was conducted to predict the prognostic factors from clinical information and conventional magnetic resonance imaging (MRI) features in adult PAs.

METHODS

A total of 56 adult PA patients were enrolled in the institutional cohort. Clinical characteristics including age, sex, anaplastic PA, presence of neurofibromatosis type 1, Karnofsky performance status, extent of resection, and postoperative treatment were collected. MRI characteristics including major axis length, tumor location, presence of the typical 'cystic mass with enhancing mural nodule appearance', proportion of enhancing tumor, the proportion of edema, conspicuity of the nonenhancing margin, and presence of a cyst were evaluated. Univariable and multivariable Cox proportional hazard modeling were performed.

RESULTS

The 5-year progression-free survival (PFS) and overall survival (OS) rates were 83.9% and 91.l%, respectively. On univariable analysis, older age, larger proportion of edema, and poor definition of nonenhancing margin were predictors of shorter PFS and OS, respectively (all Ps < .05). On multivariable analysis, older age (hazard ratio [HR] = 1.04, P = .014; HR = 1.14, P = .030) and poor definition of nonenhancing margin (HR = 3.66, P = .027; HR = 24.30, P = .024) were independent variables for shorter PFS and OS, respectively.

CONCLUSION

Age and the margin of the nonenhancing part of the tumor may be useful biomarkers for predicting the outcome in adult PAs.

Features of Visually AcceSAble Rembrandt Images: Interrater Reliability in Pediatric Brain Tumors

BACKGROUND AND PURPOSE

At present, no evidence-based lexicon exists for pediatric intracranial tumors. The Visually AcceSAble Rembrandt Images terminology describes reproducible MR imaging features of adult gliomas for prediction of tumor grade, molecular markers, and survival. Our aim was to assess the interrater reliability of the pre-resection features of Visually AcceSAble Rembrandt Images in pediatric brain tumors.

MATERIALS AND METHODS

Fifty consecutive pre-resection brain MR imaging examinations of pediatric intracranial neoplasms were independently reviewed by 3 neuroradiologists. The intraclass correlation coefficient for continuous variables and the Krippendorf alpha were used to evaluate the interrater agreement. Subgroup analysis was performed for 30 gliomas.

RESULTS

Parameters with almost perfect agreement (α > .8) included tumor location (F1) and proportion of enhancing tumor (F5). Parameters with substantial agreement (α = .61-.80) were side of tumor epicenter (F2), involvement of eloquent brain (F3), enhancement quality (F4), proportion of non-contrast-enhancing tumor (F6), and deep white matter invasion (F21). The other parameters showed either moderate (α = .41-.60; n = 11), fair (α = .21-.40; n = 5), or slight agreement (α = 0-.20; n = 1). Subgroup analysis of 30 gliomas showed almost perfect agreement for tumor location (F1), involvement of eloquent brain (F3), and proportion of enhancing tumor (F5); and substantial agreement for side of tumor epicenter (F2), enhancement quality (F4), proportion of noncontrast enhancing tumor (F6), cysts (F8), thickness of enhancing margin (F11), and deep white matter invasion (F21). The intraclass correlation coefficient for measurements in the axial plane was excellent in both the main group (0.984 [F29] and 0.982 [F30]) and the glioma subgroup (0.973 [F29] and 0.973 [F30]).

CONCLUSIONS

Nine features of Visually AcceSAble Rembrandt Images have an acceptable interrater agreement in pediatric brain tumors. For the subgroup of pediatric gliomas, 11 features of Visually AcceSAble Rembrandt Images have an acceptable interrater agreement. The low degree of reproducibility of the remainder of the features necessitates the use of features tailored to the pediatric age group and is likely related to the more heterogeneous imaging morphology of pediatric brain tumors.

Radiomics for precision medicine in glioblastoma

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.

Applications of Radiomics and Radiogenomics in High-Grade Gliomas in the Era of Precision Medicine

Simple Summary

Radiomics and radiogenomics offer new insight into high-grade glioma biology, as well as into glioma behavior in response to standard therapies. In this article, we provide neuro-oncology, neuropathology, and computational perspectives on the role of radiomics in providing more accurate diagnoses, prognostication, and surveillance of patients with high-grade glioma, and on the potential application of radiomics in clinical practice, with the overarching goal of advancing precision medicine for optimal patient care.

Abstract

Machine learning (ML) integrated with medical imaging has introduced new perspectives in precision diagnostics of high-grade gliomas, through radiomics and radiogenomics. This has raised hopes for characterizing noninvasive and in vivo biomarkers for prediction of patient survival, tumor recurrence, and genomics and therefore encouraging treatments tailored to individualized needs. Characterization of tumor infiltration based on pre-operative multi-parametric magnetic resonance imaging (MP-MRI) scans may allow prediction of the loci of future tumor recurrence and thereby aid in planning the course of treatment for the patients, such as optimizing the extent of resection and the dose and target area of radiation. Imaging signatures of tumor genomics can help in identifying the patients who benefit from certain targeted therapies. Specifying molecular properties of gliomas and prediction of their changes over time and with treatment would allow optimization of treatment. In this article, we provide neuro-oncology, neuropathology, and computational perspectives on the promise of radiomics and radiogenomics for allowing personalized treatments of patients with gliomas and discuss the challenges and limitations of these methods in multi-institutional clinical trials and suggestions to mitigate the issues and the future directions.

Multiple Survival Outcome Prediction of Glioblastoma Patients Based on Multiparametric MRI

PURPOSE

Construction of radiomics models for the individualized estimation of multiple survival stratification in glioblastoma (GBM) patients using the multiregional information extracted from multiparametric MRI that could facilitate clinical decision-making for GBM patients.

MATERIALS AND METHODS

A total of 134 eligible GBM patients were selected from The Cancer Genome Atlas. These patients were separated into the long-term and short-term survival groups according to the median of individual survival indicators: overall survival (OS), progression-free survival (PFS), and disease-specific survival (DSS). Then, the patients were divided into a training set and a validation set in a ratio of 2:1. Radiomics features (n = 5,152) were extracted from multiple regions of the GBM using multiparametric MRI. Then, radiomics signatures that are related to the three survival indicators were respectively constructed using the analysis of variance (ANOVA) and the least absolute shrinkage and selection operator (LASSO) regression for each patient in the training set. Based on a Cox proportional hazards model, the radiomics model was further constructed by combining the signature and clinical risk factors.

RESULTS

The constructed radiomics model showed a promising discrimination ability to differentiate in the training set and validation set of GBM patients with survival indicators of OS, PFS, and DSS. Both the four MRI modalities and five tumor subregions have different effects on the three survival indicators of GBM. The favorable calibration and decision curve analysis indicated the clinical decision value of the radiomics model. The performance of models of the three survival indicators was different but excellent; the best model achieved C indexes of 0.725, 0.677, and 0.724, respectively, in the validation set.

CONCLUSION

Our results show that the proposed radiomics models have favorable predictive accuracy on three survival indicators and can provide individualized probabilities of survival stratification for GBM patients by using multiparametric and multiregional MRI features.

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.

Radiomics and radiogenomics in gliomas: a contemporary update

The natural history and treatment landscape of primary brain tumours are complicated by the varied tumour behaviour of primary or secondary gliomas (high-grade transformation of low-grade lesions), as well as the dilemmas with identification of radiation necrosis, tumour progression, and pseudoprogression on MRI. Radiomics and radiogenomics promise to offer precise diagnosis, predict prognosis, and assess tumour response to modern chemotherapy/immunotherapy and radiation therapy. This is achieved by a triumvirate of morphological, textural, and functional signatures, derived from a high-throughput extraction of quantitative voxel-level MR image metrics. However, the lack of standardisation of acquisition parameters and inconsistent methodology between working groups have made validations unreliable, hence multi-centre studies involving heterogenous study populations are warranted. We elucidate novel radiomic and radiogenomic workflow concepts and state-of-the-art descriptors in sub-visual MR image processing, with relevant literature on applications of such machine learning techniques in glioma management.

Advanced MRI assessment of non-enhancing peritumoral signal abnormality in brain lesions

Evaluation of Central Nervous System (CNS) focal lesions has been classically made focusing on the assessment solid or enhancing component. However, the assessment of solitary peripherally enhancing lesions where the differential diagnosis includes High-Grade Gliomas (HGG) and metastasis, is usually challenging. Several studies have tried to address the characteristics of peritumoral non-enhancing areas, for better characterization of these lesions. Peritumoral hyperintense T2/FLAIR signal abnormality predominantly contains infiltrating tumor cells in HGG whereas CNS metastasis induce pure vasogenic edema. In addition, the accurate determination of the real extension of HGG is critical for treatment selection and outcome. Conventional MRI sequences are limited in distinguishing infiltrating neoplasm from vasogenic edema. Advanced MRI sequences like Diffusion Weighted Imaging (DWI), Diffusion Tensor Imaging (DTI), Perfusion Weighted Imaging (PWI) and MR spectroscopy (MRS) have all been utilized for this aim with acceptable results. Other advanced MRI approaches, less explored for this task such as Arterial Spin Labelling (ASL), Diffusion Kurtosis Imaging (DKI), T2 relaxometry or Amide Proton Transfer (APT) are also showning promising results in this scenario. In this article, we will discuss the physiopathological basis of peritumoral T2/FLAIR signal abnormality and review potential applications of advanced MRI sequences for its evaluation.

Multimodal Disentangled Variational Autoencoder with Game Theoretic Interpretability for Glioma grading

Effective fusion of multimodal magnetic resonance imaging (MRI) is of great significance to boost the accuracy of glioma grading thanks to the complementary information provided by different imaging modalities. However, how to extract the common and distinctive information from MRI to achieve complementarity is still an open problem in information fusion research. In this study, we propose a deep neural network model termed as multimodal disentangled variational autoencoder (MMD-VAE) for glioma grading based on radiomics features extracted from preoperative multimodal MRI images. Specifically, the radiomics features are quantized and extracted from the region of interest for each modality. Then, the latent representations of variational autoencoder for these features are disentangled into common and distinctive representations to obtain the shared and complementary data among modalities. Afterward, cross-modality reconstruction loss and common-distinctive loss are designed to ensure the effectiveness of the disentangled representations. Finally, the disentangled common and distinctive representations are fused to predict the glioma grades, and SHapley Additive exPlanations (SHAP) is adopted to quantitatively interpret and analyze the contribution of the important features to grading. Experimental results on two benchmark datasets demonstrate that the proposed MMD-VAE model achieves encouraging predictive performance (AUC:0.9939) on a public dataset, and good generalization performance (AUC:0.9611) on a cross-institutional private dataset. These quantitative results and interpretations may help radiologists understand gliomas better and make better treatment decisions for improving clinical outcomes.

High-frequency electrical properties tomography at 9.4T as a novel contrast mechanism for brain tumors

PURPOSE

To establish high-frequency magnetic resonance electrical properties tomography (MREPT) as a novel contrast mechanism for the assessment of glioblastomas using a rat brain tumor model.

METHODS

Six F98 intracranial tumor bearing rats were imaged longitudinally 8, 11 and 14 days after tumor cell inoculation. Conductivity and mean diffusivity maps were generated using MREPT and Diffusion Tensor Imaging. These maps were co-registered with T2 -weighted images and volumes of interests (VOIs) were segmented from the normal brain, ventricles, edema, viable tumor, tumor rim, and tumor core regions. Longitudinal changes in conductivity and mean diffusivity (MD) values were compared in these regions. A correlation analysis was also performed between conductivity and mean diffusivity values.

RESULTS

The conductivity of ventricles, edematous area and tumor regions (tumor rim, viable tumor, tumor core) was significantly higher (P < .01) compared to the contralateral cortex. The conductivity of the tumor increased over time while MD from the tumor did not change. A marginal positive correlation was noted between conductivity and MD values for tumor rim and viable tumor, whereas this correlation was negative for the tumor core.

CONCLUSION

We demonstrate a novel contrast mechanism based on ionic concentration and mobility, which may aid in providing complementary information to water diffusion in probing the microenvironment of brain tumors.

Intra-scanner repeatability of quantitative imaging features in a 3D printed semi-anthropomorphic CT phantom

OBJECTIVES

Radiomics has shown to provide novel diagnostic and predictive disease information based on quantitative image features in study settings. However, limited data yielded contradictory results and important questions regarding the validity of the methods remain to be answered. The purpose of this study was to evaluate how clinical imaging techniques affect the stability of radiomics features by using 3D printed anthropomorphic CT phantom to test for repeatability and reproducibility of quantitative parameters.

METHODS

48 PET/CT validated lymph nodes of prostate cancer patients (24 metastatic, 24 non-metastatic) were used as a template to create a customized 3D printed anthropomorphic phantom. We subsequently scanned the phantom five times with a routine abdominal CT protocol. Images were reconstructed using iterative reconstruction and two soft tissue kernels and one bone kernel. Radiomics features were extracted and assessed for repeatability and susceptibility towards image reconstruction settings using concordance correlation coefficients.

RESULTS

Our analysis revealed 19 of 86 features (22 %) as highly repeatable (CCC ≥ 0.85) with low susceptibility towards image reconstruction protocols. Most features analyzed depicted critical non-repeatability with CCC's < 0.75 even under entirely consistent imaging acquisition settings. Edge enhancing kernels result in higher variances between the scans and differences in repeatability and reproducibility were detected between PSMA-positive and negative lymph nodes with overall more stable features seen in tumor positive lymph nodes.

CONCLUSIONS

Both, repeatability and reproducibility play a crucial role in the validation process of radiomics features in clinical routine. This phantom study shows that most radiomics features in contrast to previous studies, including phantom and clinical, do not depict sufficient intra-scanner repeatability to serve as reliable diagnostic tools.

Refinement of response assessment in neuro-oncology (RANO) using non-enhancing lesion type and contrast enhancement evolution pattern in IDH wild-type glioblastomas

Background

Updated response assessment in neuro-oncology (RANO) does not consider peritumoral non-enhancing lesion (NEL) and baseline (residual) contrast enhancement (CE) volume. The objective of this study is to explore helpful imaging characteristics to refine RANO for assessing early treatment response (pseudoprogression and time-to-progression [TTP]) in patients with IDH wild-type glioblastoma.

Methods

This retrospective study enrolled 86 patients with IDH wild-type glioblastoma who underwent consecutive MRI examinations before and after concurrent chemoradiotherapy (CCRT). NEL was classified as edema- or tumor-dominant type on pre-CCRT MRI. CE evolution was categorized into 4 patterns based on post-operative residual CE (measurable vs. non-measurable) and CE volume change (same criteria with RANO) during CCRT. Multivariable logistic regression, including clinical parameters, NEL type, and CE evolution pattern, was used to analyze pseudoprogression rate. TTP and OS according to NEL type and CE evolution pattern was analyzed by the Kaplan–Meier method.

Results

Pseudoprogression rate was significantly lower (chi-square test, P = .047) and TTP was significantly shorter (hazard ratio [HR] = 2.03, P = .005) for tumor-dominant type than edema-dominant type of NEL. NEL type was the only predictive marker of pseudoprogression on multivariate analysis (odds ratio = 0.26, P = .046). Among CE evolution patterns, TTP and OS was shortest in patients with residual CE compared with those exhibiting new CE (HR = 4.33, P < 0.001 and HR = 3.71, P = .009, respectively). In edema-dominant NEL type, both TTP and OS was stratified by CE evolution pattern (log-rank, P = .001), whereas it was not in tumor-dominant NEL.

Conclusions

NEL type improves prediction of pseudoprogression and, together with CE evolution pattern, further stratifies TTP and OS in patients with IDH wild-type glioblastoma and may become a helpful biomarker for refining RANO.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-021-08414-2.

An Improvement of Survival Stratification in Glioblastoma Patients via Combining Subregional Radiomics Signatures

Purpose

To investigate whether combining multiple radiomics signatures derived from the subregions of glioblastoma (GBM) can improve survival prediction of patients with GBM.

Methods

In total, 129 patients were included in this study and split into training (n = 99) and test (n = 30) cohorts. Radiomics features were extracted from each tumor region then radiomics scores were obtained separately using least absolute shrinkage and selection operator (LASSO) COX regression. A clinical nomogram was also constructed using various clinical risk factors. Radiomics nomograms were constructed by combing a single radiomics signature from the whole tumor region with clinical risk factors or combining three radiomics signatures from three tumor subregions with clinical risk factors. The performance of these models was assessed by the discrimination, calibration and clinical usefulness metrics, and was compared with that of the clinical nomogram.

Results

Incorporating the three radiomics signatures, i.e., Radscores for ET, NET, and ED, into the radiomics-based nomogram improved the performance in estimating survival (C-index: training/test cohort: 0.717/0.655) compared with that of the clinical nomogram (C-index: training/test cohort: 0.633/0.560) and that of the radiomics nomogram based on single region radiomics signatures (C-index: training/test cohort: 0.656/0.535).

Conclusion

The multiregional radiomics nomogram exhibited a favorable survival stratification accuracy.

3D DenseNet Deep Learning Based Preoperative Computed Tomography for Detecting Myasthenia Gravis in Patients With Thymoma

Background

Myasthenia gravis (MG) is the most common paraneoplastic syndromes of thymoma and closely related to thymus abnormalities. Timely detecting of the risk of MG would benefit clinical management and treatment decision for patients with thymoma. Herein, we developed a 3D DenseNet deep learning (DL) model based on preoperative computed tomography (CT) as a non-invasive method to detect MG in thymoma patients.

Methods

A large cohort of 230 thymoma patients in a hospital affiliated with a medical school were enrolled. 182 thymoma patients (81 with MG, 101 without MG) were used for training and model building. 48 cases from another hospital were used for external validation. A 3D-DenseNet-DL model and five radiomic models were performed to detect MG in thymoma patients. A comprehensive analysis by integrating machine learning and semantic CT image features, named 3D-DenseNet-DL-based multi-model, was also performed to establish a more effective prediction model.

Findings

By elaborately comparing the prediction efficacy, the 3D-DenseNet-DL effectively identified MG patients and was superior to other five radiomic models, with a mean area under ROC curve (AUC), accuracy, sensitivity, and specificity of 0.734, 0.724, 0.787, and 0.672, respectively. The effectiveness of the 3D-DenseNet-DL-based multi-model was further improved as evidenced by the following metrics: AUC 0.766, accuracy 0.790, sensitivity 0.739, and specificity 0.801. External verification results confirmed the feasibility of this DL-based multi-model with metrics: AUC 0.730, accuracy 0.732, sensitivity 0.700, and specificity 0.690, respectively.

Interpretation

Our 3D-DenseNet-DL model can effectively detect MG in patients with thymoma based on preoperative CT imaging. This model may serve as a supplement to the conventional diagnostic criteria for identifying thymoma associated MG.

Prognostic Prediction Based on Dynamic Contrast-Enhanced MRI and Dynamic Susceptibility Contrast-Enhanced MRI Parameters from Non-Enhancing, T2-High-Signal-Intensity Lesions in Patients with Glioblastoma

Objective

Few attempts have been made to investigate the prognostic value of dynamic contrast-enhanced (DCE) MRI or dynamic susceptibility contrast (DSC) MRI of non-enhancing, T2-high-signal-intensity (T2-HSI) lesions of glioblastoma multiforme (GBM) in newly diagnosed patients. This study aimed to investigate the prognostic values of DCE MRI and DSC MRI parameters from non-enhancing, T2-HSI lesions of GBM.

Materials and Methods

A total of 76 patients with GBM who underwent preoperative DCE MRI and DSC MRI and standard treatment were retrospectively included. Six months after surgery, the patients were categorized into early progression (n = 15) and non-early progression (n = 61) groups. We extracted and analyzed the permeability and perfusion parameters of both modalities for the non-enhancing, T2-HSI lesions of the tumors. The optimal percentiles of the respective parameters obtained from cumulative histograms were determined using receiver operating characteristic (ROC) curve and univariable Cox regression analyses. The results were compared using multivariable Cox proportional hazards regression analysis of progression-free survival.

Results

The 95th percentile value (PV) of Ktrans, mean Ktrans, and median Ve were significant predictors of early progression as identified by the ROC curve analysis (area under the ROC curve [AUC] = 0.704, p = 0.005; AUC = 0.684, p = 0.021; and AUC = 0.670, p = 0.0325, respectively). Univariable Cox regression analysis of the above three parametric values showed that the 95th PV of Ktrans and the mean Ktrans were significant predictors of early progression (hazard ratio [HR] = 1.06, p = 0.009; HR = 1.25, p = 0.017, respectively). Multivariable Cox regression analysis, which also incorporated clinical parameters, revealed that the 95th PV of Ktrans was the sole significant independent predictor of early progression (HR = 1.062, p < 0.009).

Conclusion

The 95th PV of Ktrans from the non-enhancing, T2-HSI lesions of GBM is a potential prognostic marker for disease progression.

Low conductivity on electrical properties tomography demonstrates unique tumor habitats indicating progression in glioblastoma

OBJECTIVES

Tissue conductivity measurements made with electrical properties tomography (EPT) can be used to define temporal changes in tissue habitats on longitudinal multiparametric MRI. We aimed to demonstrate the added insights for identifying tumor habitats obtained by including EPT with diffusion- and perfusion-weighted MRI, and to evaluate the use of these tumor habitats for determining tumor treatment response in post-treatment glioblastoma.

METHODS

Tumor habitats were developed from EPT, diffusion-weighted, and perfusion-weighted MRI in 60 patients with glioblastoma who underwent concurrent chemoradiotherapy. Voxels from EPT, apparent diffusion coefficient (ADC), and cerebral blood volume (CBV) maps were clustered into habitats, and each habitat was serially examined to assess its temporal change. The usefulness of temporal changes in tumor habitats for diagnosing tumor progression and treatment-related change was investigated using logistic regression. The performance of significant predictors was measured using the area under the curve (AUC) from receiver-operating-characteristics analysis with 1000-fold bootstrapping.

RESULTS

Five tumor habitats were identified, and of these, the hypervascular cellular habitat (odds ratio [OR] 5.45; 95% CI, 1.75-31.42; p = .02), hypovascular low conductivity habitat (OR 2.00; 95% CI, 1.45-3.05; p < .001), and hypovascular intermediate habitat (OR 1.57; 95% CI, 1.18-2.30; p = .006) were predictive of tumor progression. Low EPT and low CBV reflected a unique hypovascular low conductivity habitat that showed the highest diagnostic performance (AUC 0.86; 95% CI, 0.76-0.96). The combined habitats showed high performance (AUC 0.90; 95% CI, 0.82-0.98) in the differentiation of tumor progression from treatment-related change.

CONCLUSION

EPT reveals low conductivity habitats that can improve the diagnosis of tumor progression in post-treatment glioblastoma.

KEY POINTS

• Electrical properties tomography (EPT) demonstrated lower conductivity in tumor progression than in treatment-related change. • EPT allowed identification of a unique hypovascular low conductivity habitat when combined with cerebral blood volume mapping. • Tumor habitats with a hypovascular low conductivity habitat, hypervascular cellular habitat, and hypovascular intermediate habitat yielded high diagnostic performance for diagnosing tumor progression.

Assessment of tumor hypoxia and perfusion in recurrent glioblastoma following bevacizumab failure using MRI and 18F-FMISO PET

Tumoral hypoxia correlates with worse outcomes in glioblastoma (GBM). While bevacizumab is routinely used to treat recurrent GBM, it may exacerbate hypoxia. Evofosfamide is a hypoxia-targeting prodrug being tested for recurrent GBM. To characterize resistance to bevacizumab and identify those with recurrent GBM who may benefit from evofosfamide, we ascertained MRI features and hypoxia in patients with GBM progression receiving both agents. Thirty-three patients with recurrent GBM refractory to bevacizumab were enrolled. Patients underwent MR and ¹⁸F-FMISO PET imaging at baseline and 28 days. Tumor volumes were determined, MRI and ¹⁸F-FMISO PET-derived parameters calculated, and Spearman correlations between parameters assessed. Progression-free survival decreased significantly with hypoxic volume [hazard ratio (HR) = 1.67, 95% confidence interval (CI) 1.14 to 2.46, P = 0.009] and increased significantly with time to the maximum value of the residue (Tmax) (HR = 0.54, 95% CI 0.34 to 0.88, P = 0.01). Overall survival decreased significantly with hypoxic volume (HR = 1.71, 95% CI 1.12 to 12.61, p = 0.01), standardized relative cerebral blood volume (srCBV) (HR = 1.61, 95% CI 1.09 to 2.38, p = 0.02), and increased significantly with Tmax (HR = 0.31, 95% CI 0.15 to 0.62, p < 0.001). Decreases in hypoxic volume correlated with longer overall and progression-free survival, and increases correlated with shorter overall and progression-free survival. Hypoxic volume and volume ratio were positively correlated (r_s = 0.77, P < 0.0001), as were hypoxia volume and T1 enhancing tumor volume (r_s = 0.75, P < 0.0001). Hypoxia is a key biomarker in patients with bevacizumab-refractory GBM. Hypoxia and srCBV were inversely correlated with patient outcomes. These radiographic features may be useful in evaluating treatment and guiding treatment considerations.

Evidence-based recommendations on categories for extent of resection in diffuse glioma

Surgical resection represents the standard of care in diffuse glioma, and more extensive tumour resection appears to be associated with favourable outcome. Up to now, terminology to describe extent of resection has been inconsistently applied across clinical trials which hampers comparative analysis of cohorts between different studies. Based on a comprehensive literature review, we developed evidence-based expert recommendations on categories for extent of resection. Recommendations are formulated for the categories 'biopsy', 'partial resection', 'subtotal resection', 'near total resection', 'complete resection' and 'supramaximal resection'. Definitions rest on reduction of contrast- and non-contrast-enhancing tumour in glioblastoma, and on reduction of T2/FLAIR-hyperintense tumour in gliomas WHO grade 2 or 3. Both relative reduction of tumour volume (in percentage) as a measurement of surgical efficacy and absolute residual tumour volume (in cm³) as a measurement of remaining tumour burden are incorporated into the categories for extent of resection. Class of evidence for the proposed categories ranges from class IIB to IV. Limitations of the suggested categories are discussed. The proposed categories on extent of resection offer a framework to standardize nomenclature based on previous studies, and will need to be evaluated in prospective, molecularly well-defined cohorts. Our categories may eventually help as a stratification factor for future clinical trials.

Differential effect of vascularity between long- and short-term survivors with IDH1/2 wild-type glioblastoma

INTRODUCTION

IDH1/2 wt glioblastoma (GB) represents the most lethal tumour of the central nervous system. Tumour vascularity is associated with overall survival (OS), and the clinical relevance of vascular markers, such as rCBV, has already been validated. Nevertheless, molecular and clinical factors may have different influences on the beneficial effect of a favourable vascular signature.

PURPOSE

To evaluate the association between the rCBV and OS of IDH1/2 wt GB patients for long-term survivors (LTSs) and short-term survivors (STSs). Given that initial high rCBV may affect the patient's OS in follow-up stages, we will assess whether a moderate vascularity is beneficial for OS in both groups of patients.

MATERIALS AND METHODS

Ninety-nine IDH1/2 wt GB patients were divided into LTSs (OS ≥ 400 days) and STSs (OS < 400 days). Mann-Whitney and Fisher, uni- and multiparametric Cox, Aalen's additive regression and Kaplan-Meier tests were carried out. Tumour vascularity was represented by the mean rCBV of the high angiogenic tumour (HAT) habitat computed through the haemodynamic tissue signature methodology (available on the ONCOhabitats platform).

RESULTS

For LTSs, we found a significant association between a moderate value of rCBV_mean and higher OS (uni- and multiparametric Cox and Aalen's regression) (p = 0.0140, HR = 1.19; p = 0.0085, HR = 1.22) and significant stratification capability (p = 0.0343). For the STS group, no association between rCBV_mean and survival was observed. Moreover, no significant differences (p > 0.05) in gender, age, resection status, chemoradiation, or MGMT methylation were observed between LTSs and STSs.

CONCLUSION

We have found different prognostic and stratification effects of the vascular marker for the LTS and STS groups. We propose the use of rCBV_mean at HAT as a vascular marker clinically relevant for LTSs with IDH1/2 wt GB and maybe as a potential target for randomized clinical trials focused on this group of patients.

Estimating Glioblastoma Biophysical Growth Parameters Using Deep Learning Regression

Glioblastoma ( GBM ) is arguably the most aggressive, infiltrative, and heterogeneous type of adult brain tumor. Biophysical modeling of GBM growth has contributed to more informed clinical decision-making. However, deploying a biophysical model to a clinical environment is challenging since underlying computations are quite expensive and can take several hours using existing technologies. Here we present a scheme to accelerate the computation. In particular, we present a deep learning ( DL )-based logistic regression model to estimate the GBM's biophysical growth in seconds. This growth is defined by three tumor-specific parameters: 1) a diffusion coefficient in white matter ( Dw ), which prescribes the rate of infiltration of tumor cells in white matter, 2) a mass-effect parameter ( Mp ), which defines the average tumor expansion, and 3) the estimated time ( T ) in number of days that the tumor has been growing. Preoperative structural multi-parametric MRI ( mpMRI ) scans from n = 135 subjects of the TCGA-GBM imaging collection are used to quantitatively evaluate our approach. We consider the mpMRI intensities within the region defined by the abnormal FLAIR signal envelope for training one DL model for each of the tumor-specific growth parameters. We train and validate the DL-based predictions against parameters derived from biophysical inversion models. The average Pearson correlation coefficients between our DL-based estimations and the biophysical parameters are 0.85 for Dw, 0.90 for Mp, and 0.94 for T, respectively. This study unlocks the power of tumor-specific parameters from biophysical tumor growth estimation. It paves the way towards their clinical translation and opens the door for leveraging advanced radiomic descriptors in future studies by means of a significantly faster parameter reconstruction compared to biophysical growth modeling approaches.

Quantifying eloquent locations for glioblastoma surgery using resection probability maps

OBJECTIVE

Decisions in glioblastoma surgery are often guided by presumed eloquence of the tumor location. The authors introduce the "expected residual tumor volume" (eRV) and the "expected resectability index" (eRI) based on previous decisions aggregated in resection probability maps. The diagnostic accuracy of eRV and eRI to predict biopsy decisions, resectability, functional outcome, and survival was determined.

METHODS

Consecutive patients with first-time glioblastoma surgery in 2012-2013 were included from 12 hospitals. The eRV was calculated from the preoperative MR images of each patient using a resection probability map, and the eRI was derived from the tumor volume. As reference, Sawaya's tumor location eloquence grades (EGs) were classified. Resectability was measured as observed extent of resection (EOR) and residual volume, and functional outcome as change in Karnofsky Performance Scale score. Receiver operating characteristic curves and multivariable logistic regression were applied.

RESULTS

Of 915 patients, 674 (74%) underwent a resection with a median EOR of 97%, functional improvement in 71 (8%), functional decline in 78 (9%), and median survival of 12.8 months. The eRI and eRV identified biopsies and EORs of at least 80%, 90%, or 98% better than EG. The eRV and eRI predicted observed residual volumes under 10, 5, and 1 ml better than EG. The eRV, eRI, and EG had low diagnostic accuracy for functional outcome changes. Higher eRV and lower eRI were strongly associated with shorter survival, independent of known prognostic factors.

CONCLUSIONS

The eRV and eRI predict biopsy decisions, resectability, and survival better than eloquence grading and may be useful preoperative indices to support surgical decisions.

MGMT Promoter Methylation Status in Initial and Recurrent Glioblastoma: Correlation Study with DWI and DSC PWI Features

BACKGROUND AND PURPOSE

O⁶-methylguanine-DNA methyltransferase (MGMT) promoter methylation status in primary and recurrent glioblastoma may change during treatment. The purpose of this study was to correlate MGMT promoter methylation status changes with DWI and DSC PWI features in patients with recurrent glioblastoma after standard treatment.

MATERIALS AND METHODS

Between January 2008 and November 2016, forty patients with histologically confirmed recurrent glioblastoma were enrolled. Patients were divided into 3 groups according to the MGMT promoter methylation status for the initial and recurrent tumors: 2 groups whose MGMT promoter methylation status remained, group methylated (n = 13) or group unmethylated (n = 18), and 1 group whose MGMT promoter methylation status changed from methylated to unmethylated (n = 9). Normalized ADC and normalized relative CBV values were obtained from both the enhancing and nonenhancing regions, from which histogram parameters were calculated. The ANOVA and the Kruskal-Wallis test followed by post hoc tests were performed to compare histogram parameters among the 3 groups. The t test and Mann-Whitney U test were used to compare parameters between group methylated and group methylated to unmethylated. Receiver operating characteristic curve analysis was used to measure the predictive performance of the normalized relative CBV values between the 2 groups.

RESULTS

Group methylated to unmethylated showed significantly higher means and 90th and 95th percentiles of the cumulative normalized relative CBV values of the nonenhancing region of the initial tumor than group methylated and group unmethylated (all P < .05). The mean normalized relative CBV value of the nonenhancing region of the initial tumor was the best predictor of methylation status change (P < .001), with a sensitivity of 77.78% and specificity of 92.31% at a cutoff value of 2.594.

CONCLUSIONS

MGMT promoter methylation status might change in recurrent glioblastoma after standard treatment. The normalized relative CBV values of the nonenhancing region at the first preoperative MR imaging were higher in the MGMT promoter methylation change group from methylation to unmethylation in recurrent glioblastoma.