Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma

Applications of Artificial Intelligence in Neurosurgery for Improving Outcomes Through Diagnostics, Predictive Tools, and Resident Education

BACKGROUND

Artificial intelligence (AI) has become an increasingly prominent tool in the field of neurosurgery, revolutionizing various aspects of patient care and surgical practices. AI-powered systems can provide real-time feedback to surgeons, enhancing precision and reducing the risk of complications during surgical procedures. The objective of this study is to review the role of AI in training neurosurgical residents, improving accuracy during surgery, and reducing complications.

METHODS

The literature search method involved searching PubMed using relevant keywords to identify English literature publications, including full texts, and concerning human subject matter from its inception until May 2024, initially generating 247,747 results. Articles were then screened for topic relevancy by abstract contents. Further articles were retrieved from the sources cited by the initially reviewed articles. A comprehensive review was then performed on various studies, including observational studies, case-control studies, cohort studies, clinical trials, meta-analyses, and reviews by 4 reviewers individually and then collectively.

RESULTS

Studies on AI in neurosurgery reach more than 4000 produced over a decade alone. The majority of studies regarding clinical diagnosis, risk prediction, and intraoperative guidance remain retrospective in nature. In its current form, AI-based paradigm performed inferiorly to neurosurgery residents in test taking.

CONCLUSIONS

AI has potential for broad applications in neurosurgery from use as a diagnostic, predictive, intraoperative, or educational tool. Further research is warranted for prospective use of AI-based technology for delivery of neurosurgical care.

Investigative needle core biopsies support multimodal deep-data generation in glioblastoma

Glioblastoma (GBM) is an aggressive primary brain cancer with few effective therapies. Stereotactic needle biopsies are routinely used for diagnosis; however, the feasibility and utility of investigative biopsies to monitor treatment response remains ill-defined. Here, we demonstrate the depth of data generation possible from routine stereotactic needle core biopsies and perform highly resolved multi-omics analyses, including single-cell RNA sequencing, spatial transcriptomics, metabolomics, proteomics, phosphoproteomics, T-cell clonotype analysis, and MHC Class I immunopeptidomics on standard biopsy tissue obtained intra-operatively. We also examine biopsies taken from different locations and provide a framework for measuring spatial and genomic heterogeneity. Finally, we investigate the utility of stereotactic biopsies as a method for generating patient-derived xenograft (PDX) models. Multimodal dataset integration highlights spatially mapped immune cell-associated metabolic pathways and validates inferred cell-cell ligand-receptor interactions. In conclusion, investigative biopsies provide data-rich insight into disease processes and may be useful in evaluating treatment responses.

A Review of Artificial Intelligence-Based Systems for Non-Invasive Glioblastoma Diagnosis

BACKGROUND

Glioblastoma multiforme (GBM) is an aggressive brain tumor with a poor prognosis. Traditional diagnosis relies on invasive biopsies, which pose surgical risks. Advances in artificial intelligence (AI) and machine learning (ML) have improved non-invasive GBM diagnosis using magnetic resonance imaging (MRI), offering potential advantages in accuracy and efficiency.

OBJECTIVE

This review aims to identify the methodologies and technologies employed in AI-based GBM diagnostics. It further evaluates the performance of AI models using standard metrics, highlighting both their strengths and limitations.

METHODOLOGY

In accordance with the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines, a systematic review was conducted across major academic databases. A total of 104 articles were identified in the initial search, and 15 studies were selected for final analysis after applying inclusion and exclusion criteria.

OUTCOMES

The included studies indicated that the signal T1-weighted imaging (T1WI) is the most frequently used MRI modality in AI-based GBM diagnostics. Multimodal approaches integrating T1WI with diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) have demonstrated improved classification performance. Additionally, AI models have shown potential in surpassing conventional diagnostic methods, enabling automated tumor classification and enhancing prognostic predictions.

Response Assessment in Long-Term Glioblastoma Survivors Using a Multiparametric MRI-Based Prediction Model

Purpose: Early treatment response assessments are crucial, and the results are known to better correlate with prognosis and survival outcomes. The present study was conducted to differentiate true progression (TP) from pseudoprogression (PsP) in long-term-surviving glioblastoma patients using our previously established multiparametric MRI-based predictive model, as well as to identify clinical factors impacting survival outcomes in these patients. Methods: We report six patients with glioblastoma that had an overall survival longer than 5 years. When tumor specimens were available from second-stage surgery, histopathological analyses were used to classify between TP (>25% characteristics of malignant neoplasms; n = 2) and PsP (<25% characteristics of malignant neoplasms; n = 2). In the absence of histopathology, modified RANO criteria were assessed to determine the presence of TP (n = 1) or PsP (n = 1). The predictive probabilities (PPs) of tumor progression were measured from contrast-enhancing regions of neoplasms using a multiparametric MRI-based prediction model. Subsequently, these PP values were used to define each lesion as TP (PP ≥ 50%) or PsP (PP < 50%). Additionally, detailed clinical information was collected. Results: Our predictive model correctly identified all patients with TP (n = 3) and PsP (n = 3) cases, reflecting a significant concordance between histopathology/modified RANO criteria and PP values. The overall survival varied from 5.1 to 12.3 years. Five of the six glioblastoma patients were MGMT promoter methylated. All patients were female, with a median age of 56 years. Moreover, all six patients had a good functional status (KPS ≥ 70), underwent near-total/complete resection, and received alternative therapies. Conclusions: Multiparametric MRI can aid in assessing treatment response in long-term-surviving glioblastoma patients.

Artificial Intelligence for Response Assessment in Neuro Oncology (AI-RANO), part 2: recommendations for standardisation, validation, and good clinical practice

Technological advancements have enabled the extended investigation, development, and application of computational approaches in various domains, including health care. A burgeoning number of diagnostic, predictive, prognostic, and monitoring biomarkers are continuously being explored to improve clinical decision making in neuro-oncology. These advancements describe the increasing incorporation of artificial intelligence (AI) algorithms, including the use of radiomics. However, the broad applicability and clinical translation of AI are restricted by concerns about generalisability, reproducibility, scalability, and validation. This Policy Review intends to serve as the leading resource of recommendations for the standardisation and good clinical practice of AI approaches in health care, particularly in neuro-oncology. To this end, we investigate the repeatability, reproducibility, and stability of AI in response assessment in neuro-oncology in studies on factors affecting such computational approaches, and in publicly available open-source data and computational software tools facilitating these goals. The pathway for standardisation and validation of these approaches is discussed with the view of trustworthy AI enabling the next generation of clinical trials. We conclude with an outlook on the future of AI-enabled neuro-oncology.

Biologically informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post treatment glioblastoma

Intratumoral heterogeneity poses a significant challenge to the diagnosis and treatment of recurrent glioblastoma. This study addresses the need for non-invasive approaches to map heterogeneous landscape of histopathological alterations throughout the entire lesion for each patient. We developed BioNet, a biologically-informed neural network, to predict regional distributions of two primary tissue-specific gene modules: proliferating tumor (Pro) and reactive/inflammatory cells (Inf). BioNet significantly outperforms existing methods (p < 2e-26). In cross-validation, BioNet achieved AUCs of 0.80 (Pro) and 0.81 (Inf), with accuracies of 80% and 75%, respectively. In blind tests, BioNet achieved AUCs of 0.80 (Pro) and 0.76 (Inf), with accuracies of 81% and 74%. Competing methods had AUCs lower or around 0.6 and accuracies lower or around 70%. BioNet's voxel-level prediction maps reveal intratumoral heterogeneity, potentially improving biopsy targeting and treatment evaluation. This non-invasive approach facilitates regular monitoring and timely therapeutic adjustments, highlighting the role of ML in precision medicine.

Integrative Magnetic Resonance Imaging and Metabolomic Characterization of a Glioblastoma Rat Model

Glioblastoma (GBM) stands as the most prevalent and lethal malignant brain tumor, characterized by its highly infiltrative nature. This study aimed to identify additional MRI and metabolomic biomarkers of GBM and its impact on healthy tissue using an advanced-stage C6 glioma rat model. Wistar rats underwent a stereotactic injection of C6 cells (GBM group, n = 10) or cell medium (sham group, n = 4). A multiparametric MRI, including anatomical T2W and T1W images, relaxometry maps (T2, T2*, and T1), the magnetization transfer ratio (MTR), and diffusion tensor imaging (DTI), was performed. Additionally, ex vivo magnetic resonance spectroscopy (MRS) HRMAS spectra were acquired. The MRI analysis revealed significant differences in the T2 maps, T1 maps, MTR, and mean diffusivity parameters between the GBM tumor and the rest of the studied regions, which were the contralateral areas of the GBM rats and both regions of the sham rats (the ipsilateral and contralateral). The ex vivo spectra revealed markers of neuronal loss, apoptosis, and higher glucose uptake by the tumor. Notably, the myo-inositol and phosphocholine levels were elevated in both the tumor and the contralateral regions of the GBM rats compared to the sham rats, suggesting the effects of the tumor on the healthy tissue. The MRI parameters related to inflammation, cellularity, and tissue integrity, along with MRS-detected metabolites, serve as potential biomarkers for the tumor evolution, treatment response, and impact on healthy tissue. These techniques can be potent tools for evaluating new drugs and treatment targets.

Quantifying intra-tumoral genetic heterogeneity of glioblastoma toward precision medicine using MRI and a data-inclusive machine learning algorithm

BACKGROUND AND OBJECTIVE

Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcome.

METHODS

We proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. Classification accuracy of each gene were compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity.

RESULTS

WSO-SVM achieved 0.80 accuracy, 0.79 sensitivity, and 0.81 specificity for classifying EGFR; 0.71 accuracy, 0.70 sensitivity, and 0.72 specificity for classifying PDGFRA; 0.80 accuracy, 0.78 sensitivity, and 0.83 specificity for classifying PTEN; these results significantly outperformed the existing ML algorithms. Using SHAP, we found that the relative contributions of the five contrast images differ between genes, which are consistent with findings in the literature. The prediction maps revealed extensive intra-tumoral region-to-region heterogeneity within each individual tumor in terms of the alteration status of the three genes.

CONCLUSIONS

This study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology.

Biologically-informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post-treatment glioblastoma

Intratumoral heterogeneity poses a significant challenge to the diagnosis and treatment of glioblastoma (GBM). This heterogeneity is further exacerbated during GBM recurrence, as treatment-induced reactive changes produce additional intratumoral heterogeneity that is ambiguous to differentiate on clinical imaging. There is an urgent need to develop non-invasive approaches to map the heterogeneous landscape of histopathological alterations throughout the entire lesion for each patient. We propose to predictively fuse Magnetic Resonance Imaging (MRI) with the underlying intratumoral heterogeneity in recurrent GBM using machine learning (ML) by leveraging image-localized biopsies with their associated locoregional MRI features. To this end, we develop BioNet, a biologically-informed neural network model, to predict regional distributions of three tissue-specific gene modules: proliferating tumor, reactive/inflammatory cells, and infiltrated brain tissue. BioNet offers valuable insights into the integration of multiple implicit and qualitative biological domain knowledge, which are challenging to describe in mathematical formulations. BioNet performs significantly better than a range of existing methods on cross-validation and blind test datasets. Voxel-level prediction maps of the gene modules by BioNet help reveal intratumoral heterogeneity, which can improve surgical targeting of confirmatory biopsies and evaluation of neuro-oncological treatment effectiveness. The non-invasive nature of the approach can potentially facilitate regular monitoring of the gene modules over time, and making timely therapeutic adjustment. These results also highlight the emerging role of ML in precision medicine.

A clinically relevant computed tomography (CT) radiomics strategy for intracranial rodent brain tumour monitoring

Here, we establish a CT-radiomics based method for application in invasive, orthotopic rodent brain tumour models. Twenty four NOD/SCID mice were implanted with U87R-Luc2 GBM cells and longitudinally imaged via contrast enhanced (CE-CT) imaging. Pyradiomics was employed to extract CT-radiomic features from the tumour-implanted hemisphere and non-tumour-implanted hemisphere of acquired CT-scans. Inter-correlated features were removed (Spearman correlation > 0.85) and remaining features underwent predictive analysis (recursive feature elimination or Boruta algorithm). An area under the curve of the receiver operating characteristic curve was implemented to evaluate radiomic features for their capacity to predict defined outcomes. Firstly, we identified a subset of radiomic features which distinguish the tumour-implanted hemisphere and non- tumour-implanted hemisphere (i.e, tumour presence from normal tissue). Secondly, we successfully translate preclinical CT-radiomic pipelines to GBM patient CT scans (n = 10), identifying similar trends in tumour-specific feature intensities (E.g. 'glszm Zone Entropy'), thereby suggesting a mouse-to-human species conservation (a conservation of radiomic features across species). Thirdly, comparison of features across timepoints identify features which support preclinical tumour detection earlier than is possible by visual assessment of CT scans. This work establishes robust, preclinical CT-radiomic pipelines and describes the application of CE-CT for in-depth orthotopic brain tumour monitoring. Overall we provide evidence for the role of pre-clinical 'discovery' radiomics in the neuro-oncology space.

Investigative needle core biopsies for multi-omics in Glioblastoma

Glioblastoma (GBM) is a primary brain cancer with an abysmal prognosis and few effective therapies. The ability to investigate the tumor microenvironment before and during treatment would greatly enhance both understanding of disease response and progression, as well as the delivery and impact of therapeutics. Stereotactic biopsies are a routine surgical procedure performed primarily for diagnostic histopathologic purposes. The role of investigative biopsies - tissue sampling for the purpose of understanding tumor microenvironmental responses to treatment using integrated multi-modal molecular analyses ('Multi-omics") has yet to be defined. Secondly, it is unknown whether comparatively small tissue samples from brain biopsies can yield sufficient information with such methods. Here we adapt stereotactic needle core biopsy tissue in two separate patients. In the first patient with recurrent GBM we performed highly resolved multi-omics analysis methods including single cell RNA sequencing, spatial-transcriptomics, metabolomics, proteomics, phosphoproteomics, T-cell clonotype analysis, and MHC Class I immunopeptidomics from biopsy tissue that was obtained from a single procedure. In a second patient we analyzed multi-regional core biopsies to decipher spatial and genomic variance. We also investigated the utility of stereotactic biopsies as a method for generating patient derived xenograft models in a separate patient cohort. Dataset integration across modalities showed good correspondence between spatial modalities, highlighted immune cell associated metabolic pathways and revealed poor correlation between RNA expression and the tumor MHC Class I immunopeptidome. In conclusion, stereotactic needle biopsy cores are of sufficient quality to generate multi-omics data, provide data rich insight into a patient's disease process and tumor immune microenvironment and can be of value in evaluating treatment responses.

One sentence summary

Integrative multi-omics analysis of stereotactic needle core biopsies in glioblastoma.

Image-localized biopsy mapping of brain tumor heterogeneity: A single-center study protocol

Brain cancers pose a novel set of difficulties due to the limited accessibility of human brain tumor tissue. For this reason, clinical decision-making relies heavily on MR imaging interpretation, yet the mapping between MRI features and underlying biology remains ambiguous. Standard (clinical) tissue sampling fails to capture the full heterogeneity of the disease. Biopsies are required to obtain a pathological diagnosis and are predominantly taken from the tumor core, which often has different traits to the surrounding invasive tumor that typically leads to recurrent disease. One approach to solving this issue is to characterize the spatial heterogeneity of molecular, genetic, and cellular features of glioma through the intraoperative collection of multiple image-localized biopsy samples paired with multi-parametric MRIs. We have adopted this approach and are currently actively enrolling patients for our 'Image-Based Mapping of Brain Tumors' study. Patients are eligible for this research study (IRB #16-002424) if they are 18 years or older and undergoing surgical intervention for a brain lesion. Once identified, candidate patients receive dynamic susceptibility contrast (DSC) perfusion MRI and diffusion tensor imaging (DTI), in addition to standard sequences (T1, T1Gd, T2, T2-FLAIR) at their presurgical scan. During surgery, sample anatomical locations are tracked using neuronavigation. The collected specimens from this research study are used to capture the intra-tumoral heterogeneity across brain tumors including quantification of genetic aberrations through whole-exome and RNA sequencing as well as other tissue analysis techniques. To date, these data (made available through a public portal) have been used to generate, test, and validate predictive regional maps of the spatial distribution of tumor cell density and/or treatment-related key genetic marker status to identify biopsy and/or treatment targets based on insight from the entire tumor makeup. This type of methodology, when delivered within clinically feasible time frames, has the potential to further inform medical decision-making by improving surgical intervention, radiation, and targeted drug therapy for patients with glioma.

Revealing the biology behind MRI signatures in high grade glioma

Magnetic resonance imaging (MRI) measurements are routinely collected during the treatment of high-grade gliomas (HGGs) to characterize tumor boundaries and guide surgical tumor resection. Using spatially matched MRI and transcriptomics we discovered HGG tumor biology captured by MRI measurements. We strategically overlaid the spatially matched omics characterizations onto a pre-existing transcriptional map of glioblastoma multiforme (GBM) to enhance the robustness of our analyses. We discovered that T1+C measurements, designed to capture vasculature and blood brain barrier (BBB) breakdown and subsequent contrast extravasation, also indirectly reveal immune cell infiltration. The disruption of the vasculature and BBB within the tumor creates a permissive infiltrative environment that enables the transmigration of anti-inflammatory macrophages into tumors. These relationships were validated through histology and enrichment of genes associated with immune cell transmigration and proliferation. Additionally, T2-weighted (T2W) and mean diffusivity (MD) measurements were associated with angiogenesis and validated using histology and enrichment of genes involved in neovascularization. Furthermore, we establish an unbiased approach for identifying additional linkages between MRI measurements and tumor biology in future studies, particularly with the integration of novel MRI techniques. Lastly, we illustrated how noninvasive MRI can be used to map HGG biology spatially across a tumor, and this provides a platform to develop diagnostics, prognostics, or treatment efficacy biomarkers to improve patient outcomes.

A general framework to develop a radiomic fingerprint for progression-free survival in cervical cancer

PURPOSE

Treatment of locally advanced cervical cancer patients includes chemoradiation followed by brachytherapy. Our aim is to develop a delta radiomics (DRF) model from MRI-based brachytherapy treatment and assess its association with progression free survival (PFS).

MATERIALS AND METHODS

A retrospective analysis of FIGO stage IB- IV cervical cancer patients between 2012 and 2018 who were treated with definitive chemoradiation followed by MRI-based intracavitary brachytherapy was performed. Clinical factors together with 18 radiomic features extracted from different radiomics matrices were analyzed. The delta radiomic features (DRFs) were extracted from MRI on the first and last brachytherapy fractions. Support Vector Machine (SVM) models were fitted to combinations of 2-3 DRFs found significant after Spearman correlation and Wilcoxon rank sum test statistics. Additional models were tested that included clinical factors together with DRFs.

RESULTS

A total of 39 patients were included in the analysis with a median patient age of 52 years. Progression occurred in 20% of patients (8/39). The significant DRFs using two DRF feature combinations was a model using auto correlation (AC) and sum variance (SV). The best performing three feature model combined mean, AC & SV. Additionally, the inclusion of FIGO stages with the 2- and 3 DRF combination model(s) improved performance compared to models with only DRFs. However, all the clinical factor + DRF models were not significantly different from one another (all AUCs were 0.77).

CONCLUSIONS

Our study shows promising evidence that radiomics metrics are associated with progression free survival in cervical cancer.

Neurosurgical Management of Cerebrospinal Tumors in the Era of Artificial Intelligence : A Scoping Review

Central nervous system tumors are identified as tumors of the brain and spinal cord. The associated morbidity and mortality of cerebrospinal tumors are disproportionately high compared to other malignancies. While minimally invasive techniques have initiated a revolution in neurosurgery, artificial intelligence (AI) is expediting it. Our study aims to analyze AI's role in the neurosurgical management of cerebrospinal tumors. We conducted a scoping review using the Arksey and O'Malley framework. Upon screening, data extraction and analysis were focused on exploring all potential implications of AI, classification of these implications in the management of cerebrospinal tumors. AI has enhanced the precision of diagnosis of these tumors, enables surgeons to excise the tumor margins completely, thereby reducing the risk of recurrence, and helps to make a more accurate prediction of the patient's prognosis than the conventional methods. AI also offers real-time training to neurosurgeons using virtual and 3D simulation, thereby increasing their confidence and skills during procedures. In addition, robotics is integrated into neurosurgery and identified to increase patient outcomes by making surgery less invasive. AI, including machine learning, is rigorously considered for its applications in the neurosurgical management of cerebrospinal tumors. This field requires further research focused on areas clinically essential in improving the outcome that is also economically feasible for clinical use. The authors suggest that data analysts and neurosurgeons collaborate to explore the full potential of AI.

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

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

Integrated molecular and multiparametric MRI mapping of high-grade glioma identifies regional biologic signatures

Sampling restrictions have hindered the comprehensive study of invasive non-enhancing (NE) high-grade glioma (HGG) cell populations driving tumor progression. Here, we present an integrated multi-omic analysis of spatially matched molecular and multi-parametric magnetic resonance imaging (MRI) profiling across 313 multi-regional tumor biopsies, including 111 from the NE, across 68 HGG patients. Whole exome and RNA sequencing uncover unique genomic alterations to unresectable invasive NE tumor, including subclonal events, which inform genomic models predictive of geographic evolution. Infiltrative NE tumor is alternatively enriched with tumor cells exhibiting neuronal or glycolytic/plurimetabolic cellular states, two principal transcriptomic pathway-based glioma subtypes, which respectively demonstrate abundant private mutations or enrichment in immune cell signatures. These NE phenotypes are non-invasively identified through normalized K2 imaging signatures, which discern cell size heterogeneity on dynamic susceptibility contrast (DSC)-MRI. NE tumor populations predicted to display increased cellular proliferation by mean diffusivity (MD) MRI metrics are uniquely associated with EGFR amplification and CDKN2A homozygous deletion. The biophysical mapping of infiltrative HGG potentially enables the clinical recognition of tumor subpopulations with aggressive molecular signatures driving tumor progression, thereby informing precision medicine targeting.

FDA-approved machine learning algorithms in neuroradiology: A systematic review of the current evidence for approval

Over the past decade, machine learning (ML) and artificial intelligence (AI) have become increasingly prevalent in the medical field. In the United States, the Food and Drug Administration (FDA) is responsible for regulating AI algorithms as "medical devices" to ensure patient safety. However, recent work has shown that the FDA approval process may be deficient. In this study, we evaluate the evidence supporting FDA-approved neuroalgorithms, the subset of machine learning algorithms with applications in the central nervous system (CNS), through a systematic review of the primary literature. Articles covering the 53 FDA-approved algorithms with applications in the CNS published in PubMed, EMBASE, Google Scholar and Scopus between database inception and January 25, 2022 were queried. Initial searches identified 1505 studies, of which 92 articles met the criteria for extraction and inclusion. Studies were identified for 26 of the 53 neuroalgorithms, of which 10 algorithms had only a single peer-reviewed publication. Performance metrics were available for 15 algorithms, external validation studies were available for 24 algorithms, and studies exploring the use of algorithms in clinical practice were available for 7 algorithms. Papers studying the clinical utility of these algorithms focused on three domains: workflow efficiency, cost savings, and clinical outcomes. Our analysis suggests that there is a meaningful gap between the FDA approval of machine learning algorithms and their clinical utilization. There appears to be room for process improvement by implementation of the following recommendations: the provision of compelling evidence that algorithms perform as intended, mandating minimum sample sizes, reporting of a predefined set of performance metrics for all algorithms and clinical application of algorithms prior to widespread use. This work will serve as a baseline for future research into the ideal regulatory framework for AI applications worldwide.

Predicting glioblastoma molecular subtypes and prognosis with a multimodal model integrating convolutional neural network, radiomics, and semantics

OBJECTIVE

The aim of this study was to build a convolutional neural network (CNN)-based prediction model of glioblastoma (GBM) molecular subtype diagnosis and prognosis with multimodal features.

METHODS

In total, 222 GBM patients were included in the training set from Sun Yat-sen University Cancer Center (SYSUCC) and 107 GBM patients were included in the validation set from SYSUCC, Xuanwu Hospital Capital Medical University, and the First Hospital of Jilin University. The multimodal model was trained with MR images (pre- and postcontrast T1-weighted images and T2-weighted images), corresponding MRI impression, and clinical patient information. First, the original images were segmented using the Multimodal Brain Tumor Image Segmentation Benchmark toolkit. Convolutional features were extracted using 3D residual deep neural network (ResNet50) and convolutional 3D (C3D). Radiomic features were extracted using pyradiomics. Report texts were converted to word embedding using word2vec. These three types of features were then integrated to train neural networks. Accuracy, precision, recall, and F1-score were used to evaluate the model performance.

RESULTS

The C3D-based model yielded the highest accuracy of 91.11% in the prediction of IDH1 mutation status. Importantly, the addition of semantics improved precision by 11.21% and recall in MGMT promoter methylation status prediction by 14.28%. The areas under the receiver operating characteristic curves of the C3D-based model in the IDH1, ATRX, MGMT, and 1-year prognosis groups were 0.976, 0.953, 0.955, and 0.976, respectively. In external validation, the C3D-based model showed significant improvement in accuracy in the IDH1, ATRX, MGMT, and 1-year prognosis groups, which were 88.30%, 76.67%, 85.71%, and 85.71%, respectively (compared with 3D ResNet50: 83.51%, 66.67%, 82.14%, and 70.79%, respectively).

CONCLUSIONS

The authors propose a novel multimodal model integrating C3D, radiomics, and semantics, which had a great performance in predicting IDH1, ATRX, and MGMT molecular subtypes and the 1-year prognosis of GBM.

Advances in computational and translational approaches for malignant glioma

Gliomas are the most common primary brain tumors in adults and carry a dismal prognosis for patients. Current standard-of-care for gliomas is comprised of maximal safe surgical resection following by a combination of chemotherapy and radiation therapy depending on the grade and type of tumor. Despite decades of research efforts directed towards identifying effective therapies, curative treatments have been largely elusive in the majority of cases. The development and refinement of novel methodologies over recent years that integrate computational techniques with translational paradigms have begun to shed light on features of glioma, previously difficult to study. These methodologies have enabled a number of point-of-care approaches that can provide real-time, patient-specific and tumor-specific diagnostics that may guide the selection and development of therapies including decision-making surrounding surgical resection. Novel methodologies have also demonstrated utility in characterizing glioma-brain network dynamics and in turn early investigations into glioma plasticity and influence on surgical planning at a systems level. Similarly, application of such techniques in the laboratory setting have enhanced the ability to accurately model glioma disease processes and interrogate mechanisms of resistance to therapy. In this review, we highlight representative trends in the integration of computational methodologies including artificial intelligence and modeling with translational approaches in the study and treatment of malignant gliomas both at the point-of-care and outside the operative theater in silico as well as in the laboratory setting.

Assessment and prediction of glioblastoma therapy response: challenges and opportunities

Glioblastoma is the most aggressive type of primary adult brain tumour. The median survival of patients with glioblastoma remains approximately 15 months, and the 5-year survival rate is <10%. Current treatment options are limited, and the standard of care has remained relatively constant since 2011. Over the last decade, a range of different treatment regimens have been investigated with very limited success. Tumour recurrence is almost inevitable with the current treatment strategies, as glioblastoma tumours are highly heterogeneous and invasive. Additionally, another challenging issue facing patients with glioblastoma is how to distinguish between tumour progression and treatment effects, especially when relying on routine diagnostic imaging techniques in the clinic. The specificity of routine imaging for identifying tumour progression early or in a timely manner is poor due to the appearance similarity of post-treatment effects. Here, we concisely describe the current status and challenges in the assessment and early prediction of therapy response and the early detection of tumour progression or recurrence. We also summarize and discuss studies of advanced approaches such as quantitative imaging, liquid biomarker discovery and machine intelligence that hold exceptional potential to aid in the therapy monitoring of this malignancy and early prediction of therapy response, which may decisively transform the conventional detection methods in the era of precision medicine.

Mathematical modelling of the dynamics of image-informed tumor habitats in a murine model of glioma

Tumors exhibit high molecular, phenotypic, and physiological heterogeneity. In this effort, we employ quantitative magnetic resonance imaging (MRI) data to capture this heterogeneity through imaging-based subregions or "habitats" in a murine model of glioma. We then demonstrate the ability to model and predict the growth of the habitats using coupled ordinary differential equations (ODEs) in the presence and absence of radiotherapy. Female Wistar rats (N = 21) were inoculated intracranially with 10⁶ C6 glioma cells, a subset of which received 20 Gy (N = 5) or 40 Gy (N = 8) of radiation. All rats underwent diffusion-weighted and dynamic contrast-enhanced MRI at up to seven time points. All MRI data at each visit were subsequently clustered using k-means to identify physiological tumor habitats. A family of four models consisting of three coupled ODEs were developed and calibrated to the habitat time series of control and treated rats and evaluated for predictive capability. The Akaike Information Criterion was used for model selection, and the normalized sum-of-square-error (SSE) was used to evaluate goodness-of-fit in model calibration and prediction. Three tumor habitats with significantly different imaging data characteristics (p < 0.05) were identified: high-vascularity high-cellularity, low-vascularity high-cellularity, and low-vascularity low-cellularity. Model selection resulted in a five-parameter model whose predictions of habitat dynamics yielded SSEs that were similar to the SSEs from the calibrated model. It is thus feasible to mathematically describe habitat dynamics in a preclinical model of glioma using biology-based ODEs, showing promise for forecasting heterogeneous tumor behavior.

The future of artificial intelligence in neurosurgery: A narrative review

Background:

Artificial intelligence (AI) and machine learning (ML) algorithms are on the tremendous rise for being incorporated into the field of neurosurgery. AI and ML algorithms are different from other technological advances as giving the capability for the computer to learn, reason, and problem-solving skills that a human inherits. This review summarizes the current use of AI in neurosurgery, the challenges that need to be addressed, and what the future holds.

Methods:

A literature review was carried out with a focus on the use of AI in the field of neurosurgery and its future implication in neurosurgical research.

Results:

The online literature on the use of AI in the field of neurosurgery shows the diversity of topics in terms of its current and future implications. The main areas that are being studied are diagnostic, outcomes, and treatment models.

Conclusion:

Wonders of AI in the field of medicine and neurosurgery hold true, yet there are a lot of challenges that need to be addressed before its implications can be seen in the field of neurosurgery from patient privacy, to access to high-quality data and overreliance on surgeons on AI. The future of AI in neurosurgery is pointed toward a patient-centric approach, managing clinical tasks, and helping in diagnosing and preoperative assessment of the patients.

Decoding the Heterogeneity of Malignant Gliomas by PET and MRI for Spatial Habitat Analysis of Hypoxia, Perfusion, and Diffusion Imaging: A Preliminary Study

Background

Tumor heterogeneity poses major clinical challenges in high-grade gliomas (HGGs). Quantitative radiomic analysis with spatial tumor habitat clustering represents an innovative, non-invasive approach to represent and quantify tumor microenvironment heterogeneity. To date, habitat imaging has been applied mainly on conventional magnetic resonance imaging (MRI), although virtually extendible to any imaging modality, including advanced MRI techniques such as perfusion and diffusion MRI as well as positron emission tomography (PET) imaging.

Objectives

This study aims to evaluate an innovative PET and MRI approach for assessing hypoxia, perfusion, and tissue diffusion in HGGs and derive a combined map for clustering of intra-tumor heterogeneity.

Materials and Methods

Seventeen patients harboring HGGs underwent a pre-operative acquisition of MR perfusion (PWI), Diffusion (dMRI) and 18F-labeled fluoroazomycinarabinoside (18F-FAZA) PET imaging to evaluate tumor vascularization, cellularity, and hypoxia, respectively. Tumor volumes were segmented on fluid-attenuated inversion recovery (FLAIR) and T1 post-contrast images, and voxel-wise clustering of each quantitative imaging map identified eight combined PET and physiologic MRI habitats. Habitats’ spatial distribution, quantitative features and histopathological characteristics were analyzed.

Results

A highly reproducible distribution pattern of the clusters was observed among different cases, particularly with respect to morphological landmarks as the necrotic core, contrast-enhancing vital tumor, and peritumoral infiltration and edema, providing valuable supplementary information to conventional imaging. A preliminary analysis, performed on stereotactic bioptic samples where exact intracranial coordinates were available, identified a reliable correlation between the expected microenvironment of the different spatial habitats and the actual histopathological features. A trend toward a higher representation of the most aggressive clusters in WHO (World Health Organization) grade IV compared to WHO III was observed.

Conclusion

Preliminary findings demonstrated high reproducibility of the PET and MRI hypoxia, perfusion, and tissue diffusion spatial habitat maps and correlation with disease-specific histopathological features.

Knowledge-infused Global-Local Data Fusion for Spatial Predictive Modeling in Precision Medicine

The automated capability of generating spatial prediction for a variable of interest is desirable in various science and engineering domains. Take Precision Medicine of cancer as an example, in which the goal is to match patients with treatments based on molecular markers identified in each patient's tumor. A substantial challenge, however, is that the molecular markers can vary significantly at different spatial locations of a tumor. If this spatial distribution could be predicted, the precision of cancer treatment could be greatly improved by adapting treatment to the spatial molecular heterogeneity. This is a challenging task because no technology is available to measure the molecular markers at each spatial location within a tumor. Biopsy samples provide direct measurement, but they are scarce/local. Imaging, such as MRI, is global, but it only provides proxy/indirect measurement. Also available are mechanistic models or domain knowledge, which are often approximate or incomplete. This paper proposes a novel machine learning framework to fuse the three sources of data/information to generate spatial prediction, namely the knowledge-infused global-local data fusion (KGL) model. A novel mathematical formulation is proposed and solved with theoretical study. We present a real-data application of predicting the spatial distribution of Tumor Cell Density (TCD)-an important molecular marker for brain cancer. A total of 82 biopsy samples were acquired from 18 patients with glioblastoma, together with 6 MRI contrast images from each patient and biological knowledge encoded by a PDE simulator-based mechanistic model called Proliferation-Invasion (PI). KGL achieved the highest prediction accuracy and minimum prediction uncertainty compared with a variety of competing methods. The result has important implications for providing individualized, spatially-optimized treatment for each patient.

Weakly Supervised Skull Stripping of Magnetic Resonance Imaging of Brain Tumor Patients

Automatic brain tumor segmentation is particularly challenging on magnetic resonance imaging (MRI) with marked pathologies, such as brain tumors, which usually cause large displacement, abnormal appearance, and deformation of brain tissue. Despite an abundance of previous literature on learning-based methodologies for MRI segmentation, few works have focused on tackling MRI skull stripping of brain tumor patient data. This gap in literature can be associated with the lack of publicly available data (due to concerns about patient identification) and the labor-intensive nature of generating ground truth labels for model training. In this retrospective study, we assessed the performance of Dense-Vnet in skull stripping brain tumor patient MRI trained on our large multi-institutional brain tumor patient dataset. Our data included pretreatment MRI of 668 patients from our in-house institutional review board-approved multi-institutional brain tumor repository. Because of the absence of ground truth, we used imperfect automatically generated training labels using SPM12 software. We trained the network using common MRI sequences in oncology: T1-weighted with gadolinium contrast, T2-weighted fluid-attenuated inversion recovery, or both. We measured model performance against 30 independent brain tumor test cases with available manual brain masks. All images were harmonized for voxel spacing and volumetric dimensions before model training. Model training was performed using the modularly structured deep learning platform NiftyNet that is tailored toward simplifying medical image analysis. Our proposed approach showed the success of a weakly supervised deep learning approach in MRI brain extraction even in the presence of pathology. Our best model achieved an average Dice score, sensitivity, and specificity of, respectively, 94.5, 96.4, and 98.5% on the multi-institutional independent brain tumor test set. To further contextualize our results within existing literature on healthy brain segmentation, we tested the model against healthy subjects from the benchmark LBPA40 dataset. For this dataset, the model achieved an average Dice score, sensitivity, and specificity of 96.2, 96.6, and 99.2%, which are, although comparable to other publications, slightly lower than the performance of models trained on healthy patients. We associate this drop in performance with the use of brain tumor data for model training and its influence on brain appearance.

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.

Advanced MRI Protocols to Discriminate Glioma From Treatment Effects: State of the Art and Future Directions

In the follow-up treatment of high-grade gliomas (HGGs), differentiating true tumor progression from treatment-related effects, such as pseudoprogression and radiation necrosis, presents an ongoing clinical challenge. Conventional MRI with and without intravenous contrast serves as the clinical benchmark for the posttreatment surveillance imaging of HGG. However, many advanced imaging techniques have shown promise in helping better delineate the findings in indeterminate scenarios, as posttreatment effects can often mimic true tumor progression on conventional imaging. These challenges are further confounded by the histologic admixture that can commonly occur between tumor growth and treatment-related effects within the posttreatment bed. This review discusses the current practices in the surveillance imaging of HGG and the role of advanced imaging techniques, including perfusion MRI and metabolic MRI.

Differentiation of Low-Grade Astrocytoma From Anaplastic Astrocytoma Using Radiomics-Based Machine Learning Techniques

Purpose

To investigate the diagnostic ability of radiomics-based machine learning in differentiating atypical low-grade astrocytoma (LGA) from anaplastic astrocytoma (AA).

Methods

The current study involved 175 patients diagnosed with LGA (n = 95) or AA (n = 80) and treated in the Neurosurgery Department of West China Hospital from April 2010 to December 2019. Radiomics features were extracted from pre-treatment contrast-enhanced T1 weighted imaging (T1C). Nine diagnostic models were established with three selection methods [Distance Correlation, least absolute shrinkage, and selection operator (LASSO), and Gradient Boosting Decision Tree (GBDT)] and three classification algorithms [Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and random forest (RF)]. The sensitivity, specificity, accuracy, and areas under receiver operating characteristic curve (AUC) of each model were calculated. Diagnostic ability of each model was evaluated based on these indexes.

Results

Nine radiomics-based machine learning models with promising diagnostic performances were established. For LDA-based models, the optimal one was the combination of LASSO + LDA with AUC of 0.825. For SVM-based modes, Distance Correlation + SVM represented the most promising diagnostic performance with AUC of 0.808. And for RF-based models, Distance Correlation + RF were observed to be the optimal model with AUC of 0.821.

Conclusion

Radiomic-based machine-learning has the potential to be utilized in differentiating atypical LGA from AA with reliable diagnostic performance.

Phosphorous Magnetic Resonance Spectroscopy to Detect Regional Differences of Energy and Membrane Metabolism in Naïve Glioblastoma Multiforme

Simple Summary

Glioblastoma multiforme is a highly aggressive brain tumor, tending to infiltrate even larger zones of brain tissue than visible on conventional magnetic resonance imaging. By application of phosphorus magnetic resonance spectroscopy in patients with naïve glioblastoma multiforme, we tried to demonstrate changes in energy and membrane metabolism not only in affected regions but also in distant brain regions, the opposite brain hemisphere, and in comparison to healthy volunteers. We found reduced energetic states and signs of increased cell membrane turnover in regions of visible tumor and differences to and between the “normal-appearing” brains of glioblastoma patients and the brains of healthy volunteers. Our pilot study confirmed the feasibility of the method, so differences between various genetic mutations or clinical applicability for follow-up monitoring can be assessed in larger cohorts.

Abstract

Background: Glioblastoma multiforme (GBM) is a highly malignant primary brain tumor with infiltration of, on conventional imaging, normal-appearing brain parenchyma. Phosphorus magnetic resonance spectroscopy (31P-MRS) enables the investigation of different energy and membrane metabolites. The aim of this study is to investigate regional differences of 31P-metabolites in GBM brains. Methods: In this study, we investigated 32 patients (13 female and 19 male; mean age 63 years) with naïve GBM using 31P-MRS and conventional MRI. Contrast-enhancing (CE), T2-hyperintense, adjacent and distant ipsilateral areas of the contralateral brain and the brains of age- and gender-matched healthy volunteers were assessed. Moreover, the 31P-MRS results were correlated with quantitative diffusion parameters. Results: Several metabolite ratios between the energy-dependent metabolites and/or the membrane metabolites differed significantly between the CE areas, the T2-hyperintense areas, the more distant areas, and even the brains of healthy volunteers. pH values and Mg²⁺ concentrations were highest in visible tumor areas and decreased with distance from them. These results are in accordance with the literature and correlated with quantitative diffusion parameters. Conclusions: This pilot study shows that 31P-MRS is feasible to show regional differences of energy and membrane metabolism in brains with naïve GBM, particularly between the different “normal-appearing” regions and between the contralateral hemisphere and healthy controls. Differences between various genetic mutations or clinical applicability for follow-up monitoring have to be assessed in a larger cohort.

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

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

Quantitative mapping of individual voxels in the peritumoral region of IDH-wildtype glioblastoma to distinguish between tumor infiltration and edema

PURPOSE

The peritumoral region (PTR) in glioblastoma (GBM) represents a combination of infiltrative tumor and vasogenic edema, which are indistinguishable on magnetic resonance imaging (MRI). We developed a radiomic signature by using imaging data from low grade glioma (LGG) (marker of tumor) and PTR of brain metastasis (BM) (marker of edema) and applied it on the GBM PTR to generate probabilistic maps.

METHODS

270 features were extracted from T1-weighted, T2-weighted, and apparent diffusion coefficient maps in over 3.5 million voxels of LGG (36 segments) and BM (45 segments) scanned in a 1.5T MRI. A support vector machine classifier was used to develop the radiomics model from approximately 50% voxels (downsampled to 10%) and validated with the remaining. The model was applied to over 575,000 voxels of the PTR of 10 patients with GBM to generate a quantitative map using Platt scaling (infiltrative tumor vs. edema).

RESULTS

The radiomics model had an accuracy of 0.92 and 0.79 in the training and test set, respectively (LGG vs. BM). When extrapolated on the GBM PTR, 9 of 10 patients had a higher percentage of voxels with a tumor-like signature over radiological recurrence areas. In 7 of 10 patients, the areas under curves (AUC) were > 0.50 confirming a positive correlation. Including all the voxels from the GBM patients, the infiltration signature had an AUC of 0.61 to predict recurrence.

CONCLUSION

A radiomic signature can demarcate areas of microscopic tumors from edema in the PTR of GBM, which correlates with areas of future recurrence.

Visualizing Glioma Infiltration by the Combination of Multimodality Imaging and Artificial Intelligence, a Systematic Review of the Literature

The aim of this study was to systematically review the literature concerning the integration of multimodality imaging with artificial intelligence methods for visualization of tumor cell infiltration in glioma patients. The review was performed in accordance with the preferred reporting items for systematic reviews and meta-analysis (PRISMA) guidelines. The literature search was conducted in PubMed, Embase, The Cochrane Library and Web of Science and yielded 1304 results. 14 studies were included in the qualitative analysis. The reference standard for tumor infiltration was either histopathology or recurrence on image follow-up. Critical assessment was performed according to the Quality Assessment of Diagnostic Accuracy Studies (QUADAS2). All studies concluded their findings to be of significant value for future clinical practice. Diagnostic test accuracy reached an area under the curve of 0.74–0.91 reported in six studies. There was no consensus with regard to included image modalities, models or training and test strategies. The integration of artificial intelligence with multiparametric imaging shows promise for visualizing tumor cell infiltration in glioma patients. This approach can possibly optimize surgical resection margins and help provide personalized radiotherapy planning.

Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma

Radiogenomics uses machine-learning (ML) to directly connect the morphologic and physiological appearance of tumors on clinical imaging with underlying genomic features. Despite extensive growth in the area of radiogenomics across many cancers, and its potential role in advancing clinical decision making, no published studies have directly addressed uncertainty in these model predictions. We developed a radiogenomics ML model to quantify uncertainty using transductive Gaussian Processes (GP) and a unique dataset of 95 image-localized biopsies with spatially matched MRI from 25 untreated Glioblastoma (GBM) patients. The model generated predictions for regional EGFR amplification status (a common and important target in GBM) to resolve the intratumoral genetic heterogeneity across each individual tumor-a key factor for future personalized therapeutic paradigms. The model used probability distributions for each sample prediction to quantify uncertainty, and used transductive learning to reduce the overall uncertainty. We compared predictive accuracy and uncertainty of the transductive learning GP model against a standard GP model using leave-one-patient-out cross validation. Additionally, we used a separate dataset containing 24 image-localized biopsies from 7 high-grade glioma patients to validate the model. Predictive uncertainty informed the likelihood of achieving an accurate sample prediction. When stratifying predictions based on uncertainty, we observed substantially higher performance in the group cohort (75% accuracy, n = 95) and amongst sample predictions with the lowest uncertainty (83% accuracy, n = 72) compared to predictions with higher uncertainty (48% accuracy, n = 23), due largely to data interpolation (rather than extrapolation). On the separate validation set, our model achieved 78% accuracy amongst the sample predictions with lowest uncertainty. We present a novel approach to quantify radiogenomics uncertainty to enhance model performance and clinical interpretability. This should help integrate more reliable radiogenomics models for improved medical decision-making.

Improved detection of diffuse glioma infiltration with imaging combinations: a diagnostic accuracy study

Background

Surgical resection and irradiation of diffuse glioma are guided by standard MRI: T2/fluid attenuated inversion recovery (FLAIR)–weighted MRI for non-enhancing and T1-weighted gadolinium-enhanced (T1G) MRI for enhancing gliomas. Amino acid PET has been suggested as the new standard. Imaging combinations may improve standard MRI and amino acid PET. The aim of the study was to determine the accuracy of imaging combinations to detect glioma infiltration.

Methods

We included 20 consecutive adults with newly diagnosed non-enhancing glioma (7 diffuse astrocytomas, isocitrate dehydrogenase [IDH] mutant; 1 oligodendroglioma, IDH mutant and 1p/19q codeleted; 1 glioblastoma IDH wildtype) or enhancing glioma (glioblastoma, 9 IDH wildtype and 2 IDH mutant). Standardized preoperative imaging (T1-, T2-, FLAIR-weighted, and T1G MRI, perfusion and diffusion MRI, MR spectroscopy and O-(2-[18F]-fluoroethyl)-L-tyrosine ([¹⁸F]FET) PET) was co-localized with multiregion stereotactic biopsies preceding resection. Tumor presence in the biopsies was assessed by 2 neuropathologists. Diagnostic accuracy was determined using receiver operating characteristic analysis.

Results

A total of 174 biopsies were obtained (63 from 9 non-enhancing and 111 from 11 enhancing gliomas), of which 129 contained tumor (50 from non-enhancing and 79 from enhancing gliomas). In enhancing gliomas, the combination of apparent diffusion coefficient (ADC) with [¹⁸F]FET PET (area under the curve [AUC], 95% CI: 0.89, 0.79‒0.99) detected tumor better than T1G MRI (0.56, 0.39‒0.72; P < 0.001) and [¹⁸F]FET PET (0.76, 0.66‒0.86; P = 0.001). In non-enhancing gliomas, no imaging combination detected tumor significantly better than standard MRI. FLAIR-weighted MRI had an AUC of 0.81 (0.65–0.98) compared with 0.69 (0.56–0.81; P = 0.019) for [¹⁸F]FET PET.

Conclusion

Combining ADC and [¹⁸F]FET PET detects glioma infiltration better than standard MRI and [¹⁸F]FET PET in enhancing gliomas, potentially enabling better guidance of local therapy.

The Practical Application of Emerging Technologies Influencing the Diagnosis and Care of Patients With Primary Brain Tumors

Over the past decade, a variety of new and innovative technologies has led to important advances in the diagnosis and management of patients with primary malignant brain tumors. New approaches to surgical navigation and tumor localization, advanced imaging to define tumor biology and treatment response, and the widespread adoption of a molecularly defined integrated diagnostic paradigm that complements traditional histopathologic diagnosis continue to impact the day-to-day care of these patients. In the neuro-oncology clinic, discussions with patients about the role of tumor treating fields (TTFields) and the incorporation of next-generation sequencing (NGS) data into therapeutic decision-making are now a standard practice. This article summarizes newer applications of technology influencing the pathologic, neuroimaging, neurosurgical, and medical management of patients with malignant primary brain tumors.

Radiomic analysis of magnetic resonance fingerprinting in adult brain tumors

PURPOSE

This is a radiomics study investigating the ability of texture analysis of MRF maps to improve differentiation between intra-axial adult brain tumors and to predict survival in the glioblastoma cohort.

METHODS

Magnetic resonance fingerprinting (MRF) acquisition was performed on 31 patients across 3 groups: 17 glioblastomas, 6 low-grade gliomas, and 8 metastases. Using regions of interest for the solid tumor and peritumoral white matter on T1 and T2 maps, second-order texture features were calculated from gray-level co-occurrence matrices and gray-level run length matrices. Selected features were compared across the three tumor groups using Wilcoxon rank-sum test. Receiver operating characteristic curve analysis was performed for each feature. Kaplan-Meier method was used for survival analysis with log rank tests.

RESULTS

Low-grade gliomas and glioblastomas had significantly higher run percentage, run entropy, and information measure of correlation 1 on T1 than metastases (p < 0.017). The best separation of all three tumor types was seen utilizing inverse difference normalized and homogeneity values for peritumoral white matter in both T1 and T2 maps (p < 0.017). In solid tumor T2 maps, lower values in entropy and higher values of maximum probability and high-gray run emphasis were associated with longer survival in glioblastoma patients (p < 0.05). Several texture features were associated with longer survival in glioblastoma patients on peritumoral white matter T1 maps (p < 0.05).

CONCLUSION

Texture analysis of MRF-derived maps can improve our ability to differentiate common adult brain tumors by characterizing tumor heterogeneity, and may have a role in predicting outcomes in patients with glioblastoma.

MRI radiomic features are associated with survival in melanoma brain metastases treated with immune checkpoint inhibitors

BACKGROUND

Melanoma brain metastases historically portend a dismal prognosis, but recent advances in immune checkpoint inhibitors (ICIs) have been associated with durable responses in some patients. There are no validated imaging biomarkers associated with outcomes in patients with melanoma brain metastases receiving ICIs. We hypothesized that radiomic analysis of magnetic resonance images (MRIs) could identify higher-order features associated with survival.

METHODS

Between 2010 and 2019, we retrospectively reviewed patients with melanoma brain metastases who received ICI. After volumes of interest were drawn, several texture and edge descriptors, including first-order, Haralick, Gabor, Sobel, and Laplacian of Gaussian (LoG) features were extracted. Progression was determined using Response Assessment in Neuro-Oncology Brain Metastases. Univariate Cox regression was performed for each radiomic feature with adjustment for multiple comparisons followed by Lasso regression and multivariate analysis.

RESULTS

Eighty-eight patients with 196 total brain metastases were identified. Median age was 63.5 years (range, 19-91 y). Ninety percent of patients had Eastern Cooperative Oncology Group performance status of 0 or 1 and 35% had elevated lactate dehydrogenase. Sixty-three patients (72%) received ipilimumab, 11 patients (13%) received programmed cell death protein 1 blockade, and 14 patients (16%) received nivolumab plus ipilimumab. Multiple features were associated with increased overall survival (OS), and LoG edge features best explained the variation in outcome (hazard ratio: 0.68, P = 0.001). In multivariate analysis, a similar trend with LoG was seen, but no longer significant with OS. Findings were confirmed in an independent cohort.

CONCLUSION

Higher-order MRI radiomic features in patients with melanoma brain metastases receiving ICI were associated with a trend toward improved OS.

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

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

A Neural Network Approach to Identify the Peritumoral Invasive Areas in Glioblastoma Patients by Using MR Radiomics

The challenge in the treatment of glioblastoma is the failure to identify the cancer invasive area outside the contrast-enhancing tumour which leads to the high local progression rate. Our study aims to identify its progression from the preoperative MR radiomics. 57 newly diagnosed cerebral glioblastoma patients were included. All patients received 5-aminolevulinic acid (5-ALA) fluorescence guidance surgery and postoperative temozolomide concomitant chemoradiotherapy. Preoperative 3 T MRI data including structure MR, perfusion MR, and DTI were obtained. Voxel-based radiomics features extracted from 37 patients were used in the convolutional neural network to train and as internal validation. Another 20 patients of the cohort were tested blindly as external validation. Our results showed that the peritumoural progression areas had higher signal intensity in FLAIR (p = 0.02), rCBV (p = 0.038), and T1C (p = 0.0004), and lower intensity in ADC (p = 0.029) and DTI-p (p = 0.001) compared to non-progression area. The identification of the peritumoural progression area was done by using a supervised convolutional neural network. There was an overall accuracy of 92.6% in the training set and 78.5% in the validation set. Multimodal MR radiomics can demonstrate distinct characteristics in areas of potential progression on preoperative MRI.

Overall survival prediction in glioblastoma patients using structural magnetic resonance imaging (MRI): advanced radiomic features may compensate for lack of advanced MRI modalities

Purpose: Glioblastoma, the most common and aggressive adult brain tumor, is considered noncurative at diagnosis, with 14 to 16 months median survival following treatment. There is increasing evidence that noninvasive integrative analysis of radiomic features can predict overall and progression-free survival, using advanced multiparametric magnetic resonance imaging (Adv-mpMRI). If successfully applicable, such noninvasive markers can considerably influence patient management. However, most patients prior to initiation of therapy typically undergo only basic structural mpMRI (Bas-mpMRI, i.e., T1, T1-Gd, T2, and T2-fluid-attenuated inversion recovery) preoperatively, rather than Adv-mpMRI that provides additional vascularization (dynamic susceptibility contrast-MRI) and cell-density (diffusion tensor imaging) related information. Approach: We assess a retrospective cohort of 101 glioblastoma patients with available Adv-mpMRI from a previous study, which has shown that an initial feature panel (IFP, i.e., intensity, volume, location, and growth model parameters) extracted from Adv-mpMRI can yield accurate overall survival stratification. We focus on demonstrating that equally accurate prediction models can be constructed using augmented radiomic feature panels (ARFPs, i.e., integrating morphology and textural descriptors) extracted solely from widely available Bas-mpMRI, obviating the need for using Adv-mpMRI. We extracted 1612 radiomic features from distinct tumor subregions to build multivariate models that stratified patients as long-, intermediate-, or short-survivors. Results: The classification accuracy of the model utilizing Adv-mpMRI protocols and the IFP was 72.77% and degraded to 60.89% when using only Bas-mpMRI. However, utilizing the ARFP on Bas-mpMRI improved the accuracy to 74.26%. Furthermore, Kaplan-Meier analysis demonstrated superior classification of subjects into short-, intermediate-, and long-survivor classes when using ARFP extracted from Bas-mpMRI. Conclusions: This quantitative evaluation indicates that accurate survival prediction in glioblastoma patients is feasible using solely Bas-mpMRI and integrative advanced radiomic features, which can compensate for the lack of Adv-mpMRI. Our finding holds promise for generalization across multiple institutions that may not have access to Adv-mpMRI and to better inform clinical decision-making about aggressive interventions and clinical trials.

Artificial intelligence in multiparametric prostate cancer imaging with focus on deep-learning methods

Prostate cancer represents today the most typical example of a pathology whose diagnosis requires multiparametric imaging, a strategy where multiple imaging techniques are combined to reach an acceptable diagnostic performance. However, the reviewing, weighing and coupling of multiple images not only places additional burden on the radiologist, it also complicates the reviewing process. Prostate cancer imaging has therefore been an important target for the development of computer-aided diagnostic (CAD) tools. In this survey, we discuss the advances in CAD for prostate cancer over the last decades with special attention to the deep-learning techniques that have been designed in the last few years. Moreover, we elaborate and compare the methods employed to deliver the CAD output to the operator for further medical decision making.

Performance of Standardized Relative CBV for Quantifying Regional Histologic Tumor Burden in Recurrent High-Grade Glioma: Comparison against Normalized Relative CBV Using Image-Localized Stereotactic Biopsies

BACKGROUND AND PURPOSE

Perfusion MR imaging measures of relative CBV can distinguish recurrent tumor from posttreatment radiation effects in high-grade gliomas. Currently, relative CBV measurement requires normalization based on user-defined reference tissues. A recently proposed method of relative CBV standardization eliminates the need for user input. This study compares the predictive performance of relative CBV standardization against relative CBV normalization for quantifying recurrent tumor burden in high-grade gliomas relative to posttreatment radiation effects.

MATERIALS AND METHODS

We recruited 38 previously treated patients with high-grade gliomas (World Health Organization grades III or IV) undergoing surgical re-resection for new contrast-enhancing lesions concerning for recurrent tumor versus posttreatment radiation effects. We recovered 112 image-localized biopsies and quantified the percentage of histologic tumor content versus posttreatment radiation effects for each sample. We measured spatially matched normalized and standardized relative CBV metrics (mean, median) and fractional tumor burden for each biopsy. We compared relative CBV performance to predict tumor content, including the Pearson correlation (r), against histologic tumor content (0%-100%) and the receiver operating characteristic area under the curve for predicting high-versus-low tumor content using binary histologic cutoffs (≥50%; ≥80% tumor).

RESULTS

Across relative CBV metrics, fractional tumor burden showed the highest correlations with tumor content (0%-100%) for normalized (r = 0.63, P < .001) and standardized (r = 0.66, P < .001) values. With binary cutoffs (ie, ≥50%; ≥80% tumor), predictive accuracies were similar for both standardized and normalized metrics and across relative CBV metrics. Median relative CBV achieved the highest area under the curve (normalized = 0.87, standardized = 0.86) for predicting ≥50% tumor, while fractional tumor burden achieved the highest area under the curve (normalized = 0.77, standardized = 0.80) for predicting ≥80% tumor.

CONCLUSIONS

Standardization of relative CBV achieves similar performance compared with normalized relative CBV and offers an important step toward workflow optimization and consensus methodology.

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

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

Imaging of intratumoral heterogeneity in high-grade glioma

High-grade glioma (HGG), and particularly Glioblastoma (GBM), can exhibit pronounced intratumoral heterogeneity that confounds clinical diagnosis and management. While conventional contrast-enhanced MRI lacks the capability to resolve this heterogeneity, advanced MRI techniques and PET imaging offer a spectrum of physiologic and biophysical image features to improve the specificity of imaging diagnoses. Published studies have shown how integrating these advanced techniques can help better define histologically distinct targets for surgical and radiation treatment planning, and help evaluate the regional heterogeneity of tumor recurrence and response assessment following standard adjuvant therapy. Application of texture analysis and machine learning (ML) algorithms has also enabled the emerging field of radiogenomics, which can spatially resolve the regional and genetically distinct subpopulations that coexist within a single GBM tumor. This review focuses on the latest advances in neuro-oncologic imaging and their clinical applications for the assessment of intratumoral heterogeneity.

Amide Proton Transfer Imaging in Predicting Isocitrate Dehydrogenase 1 Mutation Status of Grade II/III Gliomas Based on Support Vector Machine

Background

To compare the efficacies of univariate and radiomics analyses of amide proton transfer weighted (APT_W) imaging in predicting isocitrate dehydrogenase 1 (IDH1) mutation of grade II/III gliomas.

Methods

Fifty-nine grade II/III glioma patients with known IDH1 mutation status were prospectively included (IDH1 wild type, 16; IDH1 mutation, 43). A total of 1044 quantitative radiomics features were extracted from APT_W images. The efficacies of univariate and radiomics analyses in predicting IDH1 mutation were compared. Feature values were compared between two groups with independent t-test and receiver operating characteristic (ROC) analysis was applied to evaluate the predicting efficacy of each feature. Cases were randomly assigned to either the training (n = 49) or test cohort (n = 10) for the radiomics analysis. Support vector machine with recursive feature elimination (SVM-RFE) was adopted to select the optimal feature subset. The adverse impact of the imbalance dataset in the training cohort was solved by synthetic minority oversampling technique (SMOTE). Subsequently, the performance of SVM model was assessed on both training and test cohort.

Results

As for univariate analysis, 18 features were significantly different between IDH1 wild-type and mutant groups (P < 0.05). Among these parameters, High Gray Level Run Emphasis All Direction offset 8 SD achieved the biggest area under the curve (AUC) (0.769) with the accuracy of 0.799. As for radiomics analysis, SVM model was established using 19 features selected with SVM-RFE. The AUC and accuracy for IDH1 mutation on training set were 0.892 and 0.952, while on the testing set were 0.7 and 0.84, respectively.

Conclusion

Radiomics strategy based on APT image features is potentially useful for preoperative estimating IDH1 mutation status.

Imaging-Based Algorithm for the Local Grading of Glioma

BACKGROUND AND PURPOSE

Gliomas are highly heterogeneous tumors, and optimal treatment depends on identifying and locating the highest grade disease present. Imaging techniques for doing so are generally not validated against the histopathologic criterion standard. The purpose of this work was to estimate the local glioma grade using a machine learning model trained on preoperative image data and spatially specific tumor samples. The value of imaging in patients with brain tumor can be enhanced if pathologic data can be estimated from imaging input using predictive models.

MATERIALS AND METHODS

Patients with gliomas were enrolled in a prospective clinical imaging trial between 2013 and 2016. MR imaging was performed with anatomic, diffusion, permeability, and perfusion sequences, followed by image-guided stereotactic biopsy before resection. An imaging description was developed for each biopsy, and multiclass machine learning models were built to predict the World Health Organization grade. Models were assessed on classification accuracy, Cohen κ, precision, and recall.

RESULTS

Twenty-three patients (with 7/9/7 grade II/III/IV gliomas) had analyzable imaging-pathologic pairs, yielding 52 biopsy sites. The random forest method was the best algorithm tested. Tumor grade was predicted at 96% accuracy (κ = 0.93) using 4 inputs (T2, ADC, CBV, and transfer constant from dynamic contrast-enhanced imaging). By means of the conventional imaging only, the overall accuracy decreased (89% overall, κ = 0.79) and 43% of high-grade samples were misclassified as lower-grade disease.

CONCLUSIONS

We found that local pathologic grade can be predicted with a high accuracy using clinical imaging data. Advanced imaging data improved this accuracy, adding value to conventional imaging. Confirmatory imaging trials are justified.

Multiparameter MRI Predictors of Long-Term Survival in Glioblastoma Multiforme

Standard-of-care multiparameter magnetic resonance imaging (MRI) scans of the brain were used to objectively subdivide glioblastoma multiforme (GBM) tumors into regions that correspond to variations in blood flow, interstitial edema, and cellular density. We hypothesized that the distribution of these distinct tumor ecological "habitats" at the time of presentation will impact the course of the disease. We retrospectively analyzed initial MRI scans in 2 groups of patients diagnosed with GBM, a long-term survival group comprising subjects who survived >36 month postdiagnosis, and a short-term survival group comprising subjects who survived ≤19 month postdiagnosis. The single-institution discovery cohort contained 22 subjects in each group, while the multi-institution validation cohort contained 15 subjects per group. MRI voxel intensities were calibrated, and tumor voxels clustered on contrast-enhanced T1-weighted and fluid-attenuated inversion-recovery (FLAIR) images into 6 distinct "habitats" based on low- to medium- to high-contrast enhancement and low-high signal on FLAIR scans. Habitat 6 (high signal on calibrated contrast-enhanced T1-weighted and FLAIR sequences) comprised a significantly higher volume fraction of tumors in the long-term survival group (discovery cohort, 35% ± 6.5%; validation cohort, 34% ± 4.8%) compared with tumors in the short-term survival group (discovery cohort, 17% ± 4.5%, P < .03; validation cohort, 16 ± 4.0%, P < .007). Of the 6 distinct MRI-defined habitats, the fractional tumor volume of habitat 6 at diagnosis was significantly predictive of long- or short-term survival. We discuss a possible mechanistic basis for this association and implications for habitat-driven adaptive therapy of GBM.