Combining multimodal imaging and treatment features improves machine learning-based prognostic assessment in patients with glioblastoma multiforme

Uses of artificial intelligence in glioma: A systematic review

Glioma is the most prevalent type of primary brain tumor in adults. The use of artificial intelligence (AI) in glioma is increasing and has exhibited promising results. The present study performed a systematic review of the applications of AI in glioma as regards diagnosis, grading, prediction of genotype, progression and treatment response using different databases. The aim of the present study was to demonstrate the trends (main directions) of the recent applications of AI within the field of glioma, and to highlight emerging challenges in integrating AI within clinical practice. A search in four databases (Scopus, PubMed, Wiley and Google Scholar) yielded a total of 42 articles specifically using AI in glioma and glioblastoma. The articles were retrieved and reviewed, and the data were summarized and analyzed. The majority of the articles were from the USA (n=18) followed by China (n=11). The number of articles increased by year reaching the maximum number in 2022. The majority of the articles studied glioma as opposed to glioblastoma. In terms of grading, the majority of the articles were about both low-grade glioma (LGG) and high-grade glioma (HGG) (n=23), followed by HGG/glioblastoma (n=13). Additionally, three articles were about LGG only; two articles did not specify the grade. It was found that one article had the highest sample size among the other studies, reaching 897 samples. Despite the limitations and challenges that face AI, the use of AI in glioma has increased in recent years with promising results, with a variety of applications ranging from diagnosis, grading, prognosis prediction, and reaching to treatment and post-operative care.

Clinical Feature Ranking Based on Ensemble Machine Learning Reveals Top Survival Factors for Glioblastoma Multiforme

Glioblastoma multiforme (GM) is a malignant tumor of the central nervous system considered to be highly aggressive and often carrying a terrible survival prognosis. An accurate prognosis is therefore pivotal for deciding a good treatment plan for patients. In this context, computational intelligence applied to data of electronic health records (EHRs) of patients diagnosed with this disease can be useful to predict the patients' survival time. In this study, we evaluated different machine learning models to predict survival time in patients suffering from glioblastoma and further investigated which features were the most predictive for survival time. We applied our computational methods to three different independent open datasets of EHRs of patients with glioblastoma: the Shieh dataset of 84 patients, the Berendsen dataset of 647 patients, and the Lammer dataset of 60 patients. Our survival time prediction techniques obtained concordance index (C-index) = 0.583 in the Shieh dataset, C-index = 0.776 in the Berendsen dataset, and C-index = 0.64 in the Lammer dataset, as best results in each dataset. Since the original studies regarding the three datasets analyzed here did not provide insights about the most predictive clinical features for survival time, we investigated the feature importance among these datasets. To this end, we then utilized Random Survival Forests, which is a decision tree-based algorithm able to model non-linear interaction between different features and might be able to better capture the highly complex clinical and genetic status of these patients. Our discoveries can impact clinical practice, aiding clinicians and patients alike to decide which therapy plan is best suited for their unique clinical status.

Beyond invasive biopsies: using VASARI MRI features to predict grade and molecular parameters in gliomas

BACKGROUND

Gliomas present a significant economic burden and patient management challenge. The 2021 WHO classification incorporates molecular parameters, which guide treatment decisions. However, acquiring these molecular data involves invasive biopsies, prompting a need for non-invasive diagnostic methods. This study aims to assess the potential of Visually AcceSAble Rembrandt Images (VASARI) MRI features to predict glioma characteristics such as grade, IDH mutation, and MGMT methylation status.

METHODS

This study enrolled 107 glioma patients treated between 2017 and 2022, meeting specific criteria including the absence of prior chemotherapy/radiation therapy, and the presence of molecular and MRI data. Images were assessed using the 27 VASARI MRI features by two blinded radiologists. Pathological and molecular assessments were conducted according to WHO 2021 CNS Tumor classification. Cross-validation Least Absolute Shrinkage and Selection Operator (CV-LASSO) logistic regression was applied for statistical analysis to identify significant VASARI features in determining glioma grade, IDH mutation, and MGMT methylation status.

RESULTS

The study demonstrated substantial observer agreement in VASARI feature evaluation (inter- and intra-observer κ = 0.714 - 0.831 and 0.910, respectively). Patient imaging characteristics varied significantly with glioma grade, IDH mutation, and MGMT methylation. A predictive model was established using VASARI features for glioma grade prediction, exhibiting an AUC of 0.995 (95% CI = 0.986 - 0.998), 100% sensitivity, and 92.86% specificity. IDH mutation status was predicted with AUC 0.930 (95% CI = 0.882 - 0.977), and improved slightly to 0.933 with 'age-at-diagnosis' added. A model predicting MGMT methylation had a satisfactory performance (AUC 0.757, 95% CI = 0.645 - 0.868), improving to 0.791 when 'age-at-diagnosis' was added.

CONCLUSIONS

The T1/FLAIR ratio, enhancement quality, hemorrhage, and proportion enhancing predict glioma grade with excellent accuracy. The proportion enhancing, thickness of enhancing margin, and T1/FLAIR ratio are significant predictors for IDH mutation status. Lastly, MGMT methylation is related to the longest diameter of the lesion, edema crossing the midline, and the proportion of the non-enhancing lesion. VASARI MRI features offer non-invasive and accurate predictive models for glioma grade, IDH mutation, and MGMT methylation status, enhancing glioma patient management.

Clinical and Magnetic Resonance Imaging Radiomics-Based Survival Prediction in Glioblastoma Using Multiparametric Magnetic Resonance Imaging

INTRODUCTION

Survival prediction in glioblastoma remains challenging, and identification of robust imaging markers could help with this relevant clinical problem. We evaluated multiparametric magnetic resonance imaging-derived radiomics to assess prediction of overall survival (OS) and progression-free survival (PFS).

METHODOLOGY

A retrospective, institutional review board-approved study was performed. There were 93 eligible patients, of which 55 underwent gross tumor resection and chemoradiation (GTR-CR). Overall survival and PFS were assessed in the entire cohort and the GTR-CR cohort using multiple machine learning pipelines. A model based on multiple clinical variables was also developed. Survival prediction was assessed using the radiomics-only, clinical-only, and the radiomics and clinical combined models.

RESULTS

For all patients combined, the clinical feature-derived model outperformed the best radiomics model for both OS (C-index, 0.706 vs 0.597; P < 0.0001) and PFS prediction (C-index, 0.675 vs 0.588; P < 0.001). Within the GTR-CR cohort, the radiomics model showed nonstatistically improved performance over the clinical model for predicting OS (C-index, 0.638 vs 0.588; P = 0.4). However, the radiomics model outperformed the clinical feature model for predicting PFS in GTR-CR cohort (C-index, 0.641 vs 0.550; P = 0.004). Combined clinical and radiomics model did not yield superior prediction when compared with the best model in each case.

CONCLUSIONS

When considering all patients, regardless of therapy, the radiomics-derived prediction of OS and PFS is inferior to that from a model derived from clinical features alone. However, in patients with GTR-CR, radiomics-only model outperforms clinical feature-derived model for predicting PFS.

The importance of planning CT-based imaging features for machine learning-based prediction of pain response

Patients suffering from painful spinal bone metastases (PSBMs) often undergo palliative radiation therapy (RT), with an efficacy of approximately two thirds of patients. In this exploratory investigation, we assessed the effectiveness of machine learning (ML) models trained on radiomics, semantic and clinical features to estimate complete pain response. Gross tumour volumes (GTV) and clinical target volumes (CTV) of 261 PSBMs were segmented on planning computed tomography (CT) scans. Radiomics, semantic and clinical features were collected for all patients. Random forest (RFC) and support vector machine (SVM) classifiers were compared using repeated nested cross-validation. The best radiomics classifier was trained on CTV with an area under the receiver-operator curve (AUROC) of 0.62 ± 0.01 (RFC; 95% confidence interval). The semantic model achieved a comparable AUROC of 0.63 ± 0.01 (RFC), significantly below the clinical model (SVM, AUROC: 0.80 ± 0.01); and slightly lower than the spinal instability neoplastic score (SINS; LR, AUROC: 0.65 ± 0.01). A combined model did not improve performance (AUROC: 0,74 ± 0,01). We could demonstrate that radiomics and semantic analyses of planning CTs allowed for limited prediction of therapy response to palliative RT. ML predictions based on established clinical parameters achieved the best results.

Magnetic resonance imaging findings of intracranial extraventricular ependymoma: A retrospective multi-center cohort study of 114 cases

BACKGROUND

Intracranial extraventricular ependymoma (IEE) is an ependymoma located in the brain parenchyma outside the ventricles. IEE has overlapping clinical and imaging characteristics with glioblastoma multiforme (GBM) but different treatment strategy and prognosis. Therefore, an accurate preoperative diagnosis is necessary for optimizing therapy for IEE.

METHODS

A retrospective multicenter cohort of IEE and GBM was identified. MR imaging characteristics assessed with the Visually Accessible Rembrandt Images (VASARI) feature set and clinicopathological findings were recorded. Independent predictors for IEE were identified using multivariate logistic regression, which was used to construct a diagnostic score for differentiating IEE from GBM.

RESULTS

Compared to GBM, IEE tended to occur in younger patients. Multivariate logistic regression analysis identified seven independent predictors for IEE. Among them, 3 predictors including tumor necrosis rate (F7), age, and tumor-enhancing margin thickness (F11), demonstrated higher diagnostic performance with an Area Under Curve (AUC) of more than 70% in distinguishing IEE from GBM. The AUC was 0.85, 0.78, and 0.70, with sensitivity of 92.98%, 72.81%, and 96.49%, and specificity of 65.50%, 73.64%, and 43.41%, for F7, age, and F11, respectively.

CONCLUSION

We identified specific MR imaging features such as tumor necrosis and thickness of enhancing tumor margins that could help to differentiate IEE from GBM. Our study results should be helpful to assist in diagnosis and clinical management of this rare brain tumor.

Multimodal machine learning in precision health: A scoping review

Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.

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

AIM OF STUDY

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

METHODOLOGY/APPROACH

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

OUTCOMES OF STUDY

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

Perfusion MR prior to radiotherapy is a strong predictor of survival in high-grade gliomas after proton and carbon ion radiotherapy

Background

To assess the survival predictability of perfusion magnetic resonance imaging (MRI) by the normalized cerebral blood volume (nCBV) prior to particle beam radiotherapy (PBRT) in high-grade glioma (HGG) patients underwent particle therapy.

Methods

The study retrieved dynamic susceptibility contrast MRI acquired prior to PBRT between 6/2015 and 3/2019 in 45 patients with HGG. Maximum nCBV (nCBVmax) within or adjacent to surgical/tumor bed was measured using 'hot-spot' method. The predictive values of nCBVmax for progression-free survival (PFS) and overall survival (OS) were assessed in univariate Kaplan-Meier curve and multivariate Cox proportional hazards (CPH) models. Nomograms based on CPH results were constructed to individualize the predicted probability of OS and PFS.

Results

The Kaplan-Meier curves and all CPH models based on nCBVmax as continuous variable (nCBVmax-C), group by cut-off derived from median value and Youden-index method showed that nCBVmax prior to radiotherapy was a strong predictor for both PFS and OS in HGG patients who underwent PBRT. Nomograms built on CPH models showed similar excellent performance in both discrimination and calibration.

Conclusions

Perfusion imaging prior to PBRT is a strong predictor of survival in HGG. Novel perfusion MR-based nomogram with prospective validation could potentially be formally used in future clinical practice to individualize survival probability.

Artificial intelligence-based methods for fusion of electronic health records and imaging data

Healthcare data are inherently multimodal, including electronic health records (EHR), medical images, and multi-omics data. Combining these multimodal data sources contributes to a better understanding of human health and provides optimal personalized healthcare. The most important question when using multimodal data is how to fuse them-a field of growing interest among researchers. Advances in artificial intelligence (AI) technologies, particularly machine learning (ML), enable the fusion of these different data modalities to provide multimodal insights. To this end, in this scoping review, we focus on synthesizing and analyzing the literature that uses AI techniques to fuse multimodal medical data for different clinical applications. More specifically, we focus on studies that only fused EHR with medical imaging data to develop various AI methods for clinical applications. We present a comprehensive analysis of the various fusion strategies, the diseases and clinical outcomes for which multimodal fusion was used, the ML algorithms used to perform multimodal fusion for each clinical application, and the available multimodal medical datasets. We followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We searched Embase, PubMed, Scopus, and Google Scholar to retrieve relevant studies. After pre-processing and screening, we extracted data from 34 studies that fulfilled the inclusion criteria. We found that studies fusing imaging data with EHR are increasing and doubling from 2020 to 2021. In our analysis, a typical workflow was observed: feeding raw data, fusing different data modalities by applying conventional machine learning (ML) or deep learning (DL) algorithms, and finally, evaluating the multimodal fusion through clinical outcome predictions. Specifically, early fusion was the most used technique in most applications for multimodal learning (22 out of 34 studies). We found that multimodality fusion models outperformed traditional single-modality models for the same task. Disease diagnosis and prediction were the most common clinical outcomes (reported in 20 and 10 studies, respectively) from a clinical outcome perspective. Neurological disorders were the dominant category (16 studies). From an AI perspective, conventional ML models were the most used (19 studies), followed by DL models (16 studies). Multimodal data used in the included studies were mostly from private repositories (21 studies). Through this scoping review, we offer new insights for researchers interested in knowing the current state of knowledge within this research field.

Machine learning based survival prediction in Glioma using large-scale registry data

Gliomas are the most common central nervous system tumors exhibiting poor clinical outcomes. The ability to estimate prognosis is crucial for both patients and providers in order to select the most appropriate treatment. Machine learning (ML) allows for sophisticated approaches to survival prediction using real world clinical parameters needed to achieve superior predictive accuracy. We employed Cox Proportional hazards (CPH) model, Support Vector Machine (SVM) model, Random Forest (RF) model in a large glioma dataset (3462 patients, diagnosed 2000-2018) to explore the most optimal approach to survival prediction. Features employed were age, sex, surgical resection status, tumor histology and tumor site, administration of radiation therapy (RT) and chemotherapy status. Concordance index (c-index) was employed to assess the accuracy of survival time prediction. All three models performed well with prediction accuracy (CI 0.767, 0.771, 0.57 for CPH, SVM, RF models respectively) with the best performance achieved when incorporating RT and chemotherapy administration status which emerged as key predictive features. Within the subset of glioblastoma patients, similar prediction accuracy was achieved. These findings should prompt stricter clinician oversight over registry data accuracy through quality assurance as we move towards meaningful predictive ability using ML approaches in glioma.

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.

Construction of an immune-related gene signature for the prognosis and diagnosis of glioblastoma multiforme

Background

Increasing evidence has suggested that inflammation is related to tumorigenesis and tumor progression. However, the roles of immune-related genes in the occurrence, development, and prognosis of glioblastoma multiforme (GBM) remain to be studied.

Methods

The GBM-related RNA sequencing (RNA-seq), survival, and clinical data were acquired from The Cancer Genome Atlas (TCGA), Genotype-Tissue Expression (GTEx), Chinese Glioma Genome Atlas (CGGA), and Gene Expression Omnibus (GEO) databases. Immune-related genes were obtained from the Molecular Signatures Database (MSigDB). Differently expressed immune-related genes (DE-IRGs) between GBM and normal samples were identified. Prognostic genes associated with GBM were selected by Kaplan–Meier survival analysis, Least Absolute Shrinkage and Selection Operator (LASSO)-penalized Cox regression analysis, and multivariate Cox analysis. An immune-related gene signature was developed and validated in TCGA and CGGA databases separately. The Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were performed to explore biological functions of the signature. The correlation between immune cell infiltration and the signature was analyzed by single-sample gene set enrichment analysis (ssGSEA), and the diagnostic value was investigated. The gene set enrichment analysis (GSEA) was performed to explore the potential function of the signature genes in GBM, and the protein–protein interaction (PPI) network was constructed.

Results

Three DE-IRGs [Pentraxin 3 (PTX3), TNFSF9, and bone morphogenetic protein 2 (BMP2)] were used to construct an immune-related gene signature. Receiver operating characteristic (ROC) curves and Cox analyses confirmed that the 3-gene-based prognostic signature was a good independent prognostic factor for GBM patients. We found that the signature was mainly involved in immune-related biological processes and pathways, and multiple immune cells were disordered between the high- and low-risk groups. GSEA suggested that PTX3 and TNFSF9 were mainly correlated with interleukin (IL)-17 signaling pathway, nuclear factor kappa B (NF-κB) signaling pathway, tumor necrosis factor (TNF) signaling pathway, and Toll-like receptor signaling pathway, and the PPI network indicated that they could interact directly or indirectly with inflammatory pathway proteins. Quantitative real-time PCR (qRT-PCR) indicated that the three genes were significantly different between target tissues.

Conclusion

The signature with three immune-related genes might be an independent prognostic factor for GBM patients and could be associated with the immune cell infiltration of GBM patients.

Artificial Intelligence for Survival Prediction in Brain Tumors on Neuroimaging

Survival prediction of patients affected by brain tumors provides essential information to guide surgical planning, adjuvant treatment selection, and patient counseling. Current reliance on clinical factors, such as Karnofsky Performance Status Scale, and simplistic radiological characteristics are, however, inadequate for survival prediction in tumors such as glioma that demonstrate molecular and clinical heterogeneity with variable survival outcomes. Advances in the domain of artificial intelligence have afforded powerful tools to capture a large number of hidden high-dimensional imaging features that reflect abundant information about tumor structure and physiology. Here, we provide an overview of current literature that apply computational analysis tools such as radiomics and machine learning methods to the pipeline of image preprocessing, tumor segmentation, feature extraction, and construction of classifiers to establish survival prediction models based on neuroimaging. We also discuss challenges relating to the development and evaluation of such models and explore ethical issues surrounding the future use of machine learning predictions.

Altered Structural and Functional Patterns Within Executive Control Network Distinguish Frontal Glioma-Related Epilepsy

Background

The tumor invasion of the frontal lobe induces changes in the executive control network (ECN). It remains unclear whether epileptic seizures in frontal glioma patients exacerbate the structural and functional alterations within the ECN, and whether these changes can be used to identify glioma-related seizures at an early stage. This study aimed to investigate the altered structural and functional patterns of ECN in frontal gliomas without epilepsy (non-FGep) and frontal gliomas with epilepsy (FGep) and to evaluate whether the patterns can accurately distinguish glioma-related epilepsy.

Methods

We measured gray matter (GM) volume, regional homogeneity (ReHo), and functional connectivity (FC) within the ECN to identify the structural and functional changes in 50 patients with frontal gliomas (29 non-FGep and 21 FGep) and 39 healthy controls (CN). We assessed the relationships between the structural and functional changes and cognitive function using partial correlation analysis. Finally, we applied a pattern classification approach to test whether structural and functional abnormalities within the ECN can distinguish non-FGep and FGep from CN subjects.

Results

Within the ECN, non-FGep and FGep showed increased local structure (GM) and function (ReHo), and decreased FC between brain regions compared to CN. Also, non-FGep and FGep showed differential patterns of structural and functional abnormalities within the ECN, and these abnormalities are more severe in FGep than in non-FGep. Lastly, FC between the right superior frontal gyrus and right dorsolateral prefrontal cortex was positively correlated with episodic memory scores in non-FGep and FGep. In particular, the support vector machine (SVM) classifier based on structural and functional abnormalities within ECN could accurately distinguish non-FGep and FGep from CN, and FGep from non-FGep on an individual basis with very high accuracy, area under the curve (AUC), sensitivity, and specificity.

Conclusion

Tumor invasion of the frontal lobe induces local structural and functional reorganization within the ECN, exacerbated by the accompanying epileptic seizures. The ECN abnormalities can accurately distinguish the presence or absence of epileptic seizures in frontal glioma patients. These findings suggest that differential ECN patterns can assist in the early identification and intervention of epileptic seizures in frontal glioma patients.

A Comparative and Summative Study of Radiomics-based Overall Survival Prediction in Glioblastoma Patients

PURPOSE

This study aimed to assess different machine learning models based on radiomic features, Visually Accessible Rembrandt Images features and clinical characteristics in overall survival prediction of glioblastoma and to identify the reproducible features.

MATERIALS AND METHODS

Patients with preoperative magnetic resonance scans were allocated into 3 data sets. The Least Absolute Shrinkage and Selection Operator was used for feature selection. The prediction models were built by random survival forest (RSF) and Cox regression. C-index and integrated Brier scores were calculated to compare model performances.

RESULTS

Patients with cortical involvement had shorter survival times in the training set (P = 0.006). Random survival forest showed higher C-index than Cox, and the RSF model based on the radiomic features was the best one (testing set: C-index = 0.935 ± 0.023). Ten reproducible radiomic features were summarized.

CONCLUSIONS

The RSF model based on radiomic features had promising potential in predicting overall survival of glioblastoma. Ten reproducible features were identified.

Learning-based Cancer Treatment Outcome Prognosis using Multimodal Biomarkers

Predicting early in treatment whether a tumor is likely to be responsive is a difficult yet important task to support clinical decision-making. Studies have shown that multimodal biomarkers could provide complementary information and lead to more accurate treatment outcome prognosis than unimodal biomarkers. However, the prognosis accuracy could be affected by multimodal data heterogeneity and incompleteness. The small-sized and imbalance datasets also bring additional challenges for training a designed prognosis model. In this study, a modular framework employing multimodal biomarkers for cancer treatment outcome prediction was proposed. It includes four modules of synthetic data generation, deep feature extraction, multimodal feature fusion, and classification to address the challenges described above. The feasibility and advantages of the designed framework were demonstrated through an example study, in which the goal was to stratify oropharyngeal squamous cell carcinoma (OPSCC) patients with low- and high-risks of treatment failures by use of positron emission tomography (PET) image data and microRNA (miRNA) biomarkers. The superior prognosis performance and the comparison with other methods demonstrated the efficiency of the proposed framework and its ability of enabling seamless integration, validation and comparison of various algorithms in each module of the framework. The limitation and future work was discussed as well.

Optimizing management of the elderly patient with glioblastoma: Survival prediction online tool based on BC Cancer Registry real-world data

BACKGROUND

Glioblastoma (GBM) is associated with fatal outcomes and devastating neurological presentations especially impacting the elderly. Management remains controversial and representation in clinical trials poor. We generated 2 nomograms and a clinical decision making web tool using real-world data.

METHODS

Patients ≥60 years of age with histologically confirmed GBM (ICD-O-3 histology codes 9440/3, 9441/3, and 9442/3) diagnosed 2005-2015 were identified from the BC Cancer Registry (n = 822). Seven hundred and twenty-nine patients for which performance status was captured were included in the analysis. Age, performance and resection status, administration of radiation therapy (RT), and chemotherapy were reviewed. Nomograms predicting 6- and 12-month overall survival (OS) probability were developed using Cox proportional hazards regression internally validated by c-index. A web tool powered by JavaScript was developed to calculate the survival probability.

RESULTS

Median OS was 6.6 months (95% confidence interval [CI] 6-7.2 months). Management involved concurrent chemoradiation (34%), RT alone (42%), and chemo alone (2.3%). Twenty-one percent of patients did not receive treatment beyond surgical intervention. Age, performance status, extent of resection, chemotherapy, and RT administration were all significant independent predictors of OS. Patients <80 years old who received RT had a significant survival advantage, regardless of extent of resection (hazard ratio range from 0.22 to 0.60, CI 0.15-0.95). A nomogram was constructed from all 729 patients (Harrell's Concordance Index = 0.78 [CI 0.71-0.84]) with a second nomogram based on subgroup analysis of the 452 patients who underwent RT (Harrell's Concordance Index = 0.81 [CI 0.70-0.90]). An online calculator based on both nomograms was generated for clinical use.

CONCLUSIONS

Two nomograms and accompanying web tool incorporating commonly captured clinical features were generated based on real-world data to optimize decision making in the clinic.

Measurements of Functional Network Connectivity Using Resting State Arterial Spin Labeling During Neurosurgery

In neurosurgery, an exact delineation of functional areas is of great interest to spare important regions to ensure the best possible outcome for the patient (i.e., maximum removal while maintaining the highest possible quality of life). Preoperative imaging is routinely performed, including the visualization of not only structural but also functional information. During surgery, however, brain shift can occur, leading to an offset between the previously defined and the real position. Real-time imaging during the procedure is therefore desired to obtain this information while performing surgery. In this study 15 patients suffering from glioblastoma multiforme were included. These patients underwent structural and perfusion imaging using arterial spin labeling during the procedure. The latter has been used for gathering information about tumor residual perfusion. However, special postprocessing of this data allows for additional mapping of resting state networks and is intended to be used to gather deeper insights to aid the surgeon in planning the procedure. The data of each patient could be successfully postprocessed and used to map different resting state networks alongside the default mode network. On the basis of this study, it is feasible to use the information obtained from perfusion imaging to visualize not only vascular signal but also functional activation of resting state networks without acquiring any additional data besides the already available information. This may help guide the neurosurgeon in real time to adjust the surgical plan.

Precision Neurosurgery: A Path Forward

Since the inception of their profession, neurosurgeons have defined themselves as physicians with a surgical practice. Throughout time, neurosurgery has always taken advantage of technological advances to provide better and safer care for patients. In the ongoing precision medicine surge that drives patient-centric healthcare, neurosurgery strives to effectively embrace the era of data-driven medicine. Neuro-oncology best illustrates this convergence between surgery and precision medicine with the advent of molecular profiling, imaging and data analytics. This convenient convergence paves the way for new preventive, diagnostic, prognostic and targeted therapeutic perspectives. The prominent advances in healthcare and big data forcefully challenge the medical community to deeply rethink current and future medical practice. This work provides a historical perspective on neurosurgery. It also discusses the impact of the conceptual shift of precision medicine on neurosurgery through the lens of neuro-oncology.

Reproducible imaging-based prediction of molecular subtype and risk stratification of gliomas across different experience levels using a structured reporting system

OBJECTIVES

To determine reproducible MRI parameters predictive of molecular subtype and risk stratification in glioma and develop a structured reporting system.

METHODS

All study patients were initially diagnosed with glioma, 141 from the Cancer Genome Atlas and 131 from our tertiary institution, as training and validation sets, respectively. Images were analyzed by three neuroradiologists with 1-7 years of experience. MRI features including contrast enhancement pattern, necrosis, margin, edema, T2/FLAIR mismatch, internal cyst, and cerebral blood volume higher than normal cortex were reported using a structured reporting system. The pathology was stratified into five risk types: (1) oligodendroglioma, isocitrate dehydrogenase [IDH]-mutant, 1p19q co-deleted; (2) diffuse astrocytoma, IDH-mutant, grade II-III; (3) glioblastoma, IDH-mutant, grade IV; (4) diffuse astrocytoma, IDH-wild, grade II-III; and (5) glioblastoma, IDH-wild, grade IV. Significant predictors were selected using multivariate logistic regression, and diagnostic performance was tested using a validation set.

RESULTS

Reproducible imaging parameters exhibiting > 50% agreement across readers included the presence of necrosis, T2/FLAIR mismatch, internal cyst, and predominant contrast enhancement. In the validation set, prediction of risk type 5 exhibited the highest diagnostic performance with AUCs of 0.92 (reader 1) and 0.93 (reader 2) with predominant enhancement, followed by risk type 2 with AUCs of 0.95 and 0.95 with T2/FLAIR mismatch sign and no necrosis, and risk type 1 with AUCs of 0.84 and 0.83 with internal cyst or necrosis. Risk types 3 and 4 were difficult to visually predict.

CONCLUSIONS

Imaging parameters with high reproducibility enabling prediction of IDH-wild-type glioblastoma, IDH-mutant/1p19q co-deletion oligodendroglioma, and IDH-mutant diffuse astrocytoma were identified.

KEY POINTS

• Reproducible MRI parameters for determining molecular subtypes of glioma included the presence of necrosis, T2/FLAIR mismatch, internal cyst, and predominant contrast enhancement. • IDH-wild type glioblastoma, IDH-mutant/1p19q co-deletion oligodendroglioma, and IDH-mutant low-grade astrocytoma were identified using MRI parameters with high inter-reader reproducibility. • Identification of IDH-wild type low-grade glioma and IDH-mutant glioblastoma was difficult by visual analysis.

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.

Prognostic Assessment in High-Grade Soft-Tissue Sarcoma Patients: A Comparison of Semantic Image Analysis and Radiomics

BACKGROUND

In patients with soft-tissue sarcomas of the extremities, the treatment decision is currently regularly based on tumor grading and size. The imaging-based analysis may pose an alternative way to stratify patients' risk. In this work, we compared the value of MRI-based radiomics with expert-derived semantic imaging features for the prediction of overall survival (OS).

METHODS

Fat-saturated T2-weighted sequences (T2FS) and contrast-enhanced T1-weighted fat-saturated (T1FSGd) sequences were collected from two independent retrospective cohorts (training: 108 patients; testing: 71 patients). After preprocessing, 105 radiomic features were extracted. Semantic imaging features were determined by three independent radiologists. Three machine learning techniques (elastic net regression (ENR), least absolute shrinkage and selection operator, and random survival forest) were compared to predict OS.

RESULTS

ENR models achieved the best predictive performance. Histologies and clinical staging differed significantly between both cohorts. The semantic prognostic model achieved a predictive performance with a C-index of 0.58 within the test set. This was worse compared to a clinical staging system (C-index: 0.61) and the radiomic models (C-indices: T1FSGd: 0.64, T2FS: 0.63). Both radiomic models achieved significant patient stratification.

CONCLUSIONS

T2FS and T1FSGd-based radiomic models outperformed semantic imaging features for prognostic assessment.

Diagnosis and Management of Glioblastoma: A Comprehensive Perspective

Glioblastoma is the most common malignant brain tumor in adults. The current management relies on surgical resection and adjuvant radiotherapy and chemotherapy. Despite advances in our understanding of glioblastoma onset, we are still faced with an increased incidence, an altered quality of life and a poor prognosis, its relapse and a median overall survival of 15 months. For the past few years, the understanding of glioblastoma physiopathology has experienced an exponential acceleration and yielded significant insights and new treatments perspectives. In this review, through an original R-based literature analysis, we summarize the clinical presentation, current standards of care and outcomes in patients diagnosed with glioblastoma. We also present the recent advances and perspectives regarding pathophysiological bases as well as new therapeutic approaches such as cancer vaccination and personalized treatments.

Prognostic and Predictive Value of Integrated Qualitative and Quantitative Magnetic Resonance Imaging Analysis in Glioblastoma

Simple Summary

Glioblastoma (GBM) is the most malignant primary brain tumor, for which improving patient outcome is limited by a substantial amount of tumor heterogeneity. Magnetic resonance imaging (MRI) in combination with machine learning offers the possibility to collect qualitative and quantitative imaging features which can be used to predict patient prognosis and relevant tumor markers which can aid in selecting the right treatment. This study showed that combining these MRI features with clinical features has the highest prognostic value for GBM patients; this model performed similarly in an independent GBM cohort, showing its reproducibility. The prediction of tumor markers showed promising results in the training set but not could be validated in the independent dataset. This study shows the potential of using MRI to predict prognosis and tumor markers, but further optimization and prospective studies are warranted.

Abstract

Glioblastoma (GBM) is the most malignant primary brain tumor for which no curative treatment options exist. Non-invasive qualitative (Visually Accessible Rembrandt Images (VASARI)) and quantitative (radiomics) imaging features to predict prognosis and clinically relevant markers for GBM patients are needed to guide clinicians. A retrospective analysis of GBM patients in two neuro-oncology centers was conducted. The multimodal Cox-regression model to predict overall survival (OS) was developed using clinical features with VASARI and radiomics features in isocitrate dehydrogenase (IDH)-wild type GBM. Predictive models for IDH-mutation, 06-methylguanine-DNA-methyltransferase (MGMT)-methylation and epidermal growth factor receptor (EGFR) amplification using imaging features were developed using machine learning. The performance of the prognostic model improved upon addition of clinical, VASARI and radiomics features, for which the combined model performed best. This could be reproduced after external validation (C-index 0.711 95% CI 0.64–0.78) and used to stratify Kaplan–Meijer curves in two survival groups (p-value < 0.001). The predictive models performed significantly in the external validation for EGFR amplification (area-under-the-curve (AUC) 0.707, 95% CI 0.582–8.25) and MGMT-methylation (AUC 0.667, 95% CI 0.522–0.82) but not for IDH-mutation (AUC 0.695, 95% CI 0.436–0.927). The integrated clinical and imaging prognostic model was shown to be robust and of potential clinical relevance. The prediction of molecular markers showed promising results in the training set but could not be validated after external validation in a clinically relevant manner. Overall, these results show the potential of combining clinical features with imaging features for prognostic and predictive models in GBM, but further optimization and larger prospective studies are warranted.

Conventional and advanced imaging throughout the cycle of care of gliomas

Although imaging of gliomas has evolved tremendously over the last decades, published techniques and protocols are not always implemented into clinical practice. Furthermore, most of the published literature focuses on specific timepoints in glioma management. This article reviews the current literature on conventional and advanced imaging techniques and chronologically outlines their practical relevance for the clinical management of gliomas throughout the cycle of care. Relevant articles were located through the Pubmed/Medline database and included in this review. Interpretation of conventional and advanced imaging techniques is crucial along the entire process of glioma care, from diagnosis to follow-up. In addition to the described currently existing techniques, we expect deep learning or machine learning approaches to assist each step of glioma management through tumor segmentation, radiogenomics, prognostication, and characterization of pseudoprogression. Thorough knowledge of the specific performance, possibilities, and limitations of each imaging modality is key for their adequate use in glioma management.

3D Printing of Diffuse Low-Grade Gliomas Involving Eloquent Cortical Areas and Subcortical Functional Pathways: Technical Note

BACKGROUND

Surgical resection of diffuse low-grade gliomas (DLGGs) involving cortical eloquent areas and subcortical functional pathways represents a challenge in neurosurgery. Patient-specific, 3-dimensional (3D)-printed models of head and brain structures have emerged in recent years as an educational and clinical tool for patients, doctors, and surgical residents.

METHODS

Using multimodal high-definition magnetic resonance imaging data, which incorporates information from specific task-based functional neuroimaging and diffusion tensor imaging tractography and rapid prototyping technologies with specialized software and "in-house" 3D printing, we were able to generate 3D-printed head models that were used for preoperative patient education and consultation, surgical planning, and resident training in 2 complicated DLGG surgeries.

RESULTS

This 3D-printed model is rapid prototyped and shows a means to model individualized, diffuse, low-level glioma in 3D space with respect to cortical eloquent areas and subcortical pathways. Survey results from 8 surgeons with different levels of expertise strongly support the use of this model for surgical planning, intraoperative surgical guidance, doctor-patient communication, and surgical training (>95% acceptance).

CONCLUSIONS

Spatial proximity of DLGG to cortical eloquent areas and subcortical tracts can be readily assessed in patient-specific 3D printed models with high fidelity. 3D-printed multimodal models could be helpful in preoperative patient consultation, surgical planning, and resident training.

Are Thinking Machines Breaking New Frontiers in Neuro-Oncology? A Narrative Review on the Emerging Role of Machine Learning in Neuro-Oncological Practice

Medical science in general and oncology in particular are dynamic, rapidly evolving subjects. Brain and spine tumors, whether primary or secondary, constitute a significant number of cases in any oncological practice. With the rapid influx of data in all aspects of neuro-oncological care, it is almost impossible for practicing clinicians to remain abreast with the current trends, or to synthesize the available data for it to be maximally beneficial for their patients. Machine-learning (ML) tools are fast gaining acceptance as an alternative to conventional reliance on online data. ML uses artificial intelligence to provide a computer algorithm-based information to clinicians. Different ML models have been proposed in the literature with a variable degree of precision and database requirements. ML can potentially solve the aforementioned problems for practicing clinicians by not just extracting and analyzing useful data, by minimizing or eliminating certain potential areas of human error, by creating patient-specific treatment plans, and also by predicting outcomes with reasonable accuracy. Current information on ML in neuro-oncology is scattered, and this literature review is an attempt to consolidate it and provide recent updates.

Exploratory Analysis of Qualitative MR Imaging Features for the Differentiation of Glioblastoma and Brain Metastases

OBJECTIVES

To identify qualitative VASARI (Visually AcceSIble Rembrandt Images) Magnetic Resonance (MR) Imaging features for differentiation of glioblastoma (GBM) and brain metastasis (BM) of different primary tumors.

MATERIALS AND METHODS

T1-weighted pre- and post-contrast, T2-weighted, and T2-weighted, fluid attenuated inversion recovery (FLAIR) MR images of a total of 239 lesions from 109 patients with either GBM or BM (breast cancer, non-small cell (NSCLC) adenocarcinoma, NSCLC squamous cell carcinoma, small-cell lung cancer (SCLC)) were included. A set of adapted, qualitative VASARI MR features describing tumor appearance and location was scored (binary; 1 = presence of feature, 0 = absence of feature). Exploratory data analysis was performed on binary scores using a combination of descriptive statistics (proportions with 95% binomial confidence intervals), unsupervised methods and supervised methods including multivariate feature ranking using either repeated fitting or recursive feature elimination with Support Vector Machines (SVMs).

RESULTS

GBMs were found to involve all lobes of the cerebrum with a fronto-occipital gradient, often affected the corpus callosum (32.4%, 95% CI 19.1-49.2), and showed a strong preference for the right hemisphere (79.4%, 95% CI 63.2-89.7). BMs occurred most frequently in the frontal lobe (35.1%, 95% CI 28.9-41.9) and cerebellum (28.3%, 95% CI 22.6-34.8). The appearance of GBMs was characterized by preference for well-defined non-enhancing tumor margin (100%, 89.8-100), ependymal extension (52.9%, 36.7-68.5) and substantially less enhancing foci than BMs (44.1%, 28.9-60.6 vs. 75.1%, 68.8-80.5). Unsupervised and supervised analyses showed that GBMs are distinctively different from BMs and that this difference is driven by definition of non-enhancing tumor margin, ependymal extension and features describing laterality. Differentiation of histological subtypes of BMs was driven by the presence of well-defined enhancing and non-enhancing tumor margins and localization in the vision center. SVM models with optimal hyperparameters led to weighted F1-score of 0.865 for differentiation of GBMs from BMs and weighted F1-score of 0.326 for differentiation of BM subtypes.

CONCLUSION

VASARI MR imaging features related to definition of non-enhancing margin, ependymal extension, and tumor localization may serve as potential imaging biomarkers to differentiate GBMs from BMs.

Survival prediction of glioblastoma patients-are we there yet? A systematic review of prognostic modeling for glioblastoma and its clinical potential

Glioblastoma is associated with a poor prognosis. Even though survival statistics are well-described at the population level, it remains challenging to predict the prognosis of an individual patient despite the increasing number of prognostic models. The aim of this study is to systematically review the literature on prognostic modeling in glioblastoma patients. A systematic literature search was performed to identify all relevant studies that developed a prognostic model for predicting overall survival in glioblastoma patients following the PRISMA guidelines. Participants, type of input, algorithm type, validation, and testing procedures were reviewed per prognostic model. Among 595 citations, 27 studies were included for qualitative review. The included studies developed and evaluated a total of 59 models, of which only seven were externally validated in a different patient cohort. The predictive performance among these studies varied widely according to the AUC (0.58-0.98), accuracy (0.69-0.98), and C-index (0.66-0.70). Three studies deployed their model as an online prediction tool, all of which were based on a statistical algorithm. The increasing performance of survival prediction models will aid personalized clinical decision-making in glioblastoma patients. The scientific realm is gravitating towards the use of machine learning models developed on high-dimensional data, often with promising results. However, none of these models has been implemented into clinical care. To facilitate the clinical implementation of high-performing survival prediction models, future efforts should focus on harmonizing data acquisition methods, improving model interpretability, and externally validating these models in multicentered, prospective fashion.

A Comparison Study of Machine Learning (Random Survival Forest) and Classic Statistic (Cox Proportional Hazards) for Predicting Progression in High-Grade Glioma after Proton and Carbon Ion Radiotherapy

Background

Machine learning (ML) algorithms are increasingly explored in glioma prognostication. Random survival forest (RSF) is a common ML approach in analyzing time-to-event survival data. However, it is controversial which method between RSF and traditional cornerstone method Cox proportional hazards (CPH) is better fitted. The purpose of this study was to compare RSF and CPH in predicting tumor progression of high-grade glioma (HGG) after particle beam radiotherapy (PBRT).

Methods

The study enrolled 82 consecutive HGG patients who were treated with PBRT at Shanghai Proton and Heavy Ion Center between 6/2015 and 11/2019. The entire cohort was split into the training and testing set in an 80/20 ratio. Ten variables from patient-related, tumor-related and treatment-related information were utilized for developing CPH and RSF for predicting progression-free survival (PFS). The model performance was compared in concordance index (C-index) for discrimination (accuracy), brier score (BS) for calibration (precision) and variable importance for interpretability.

Results

The CPH model demonstrated a better performance in terms of integrated C-index (62.9%) and BS (0.159) compared to RSF model (C-index = 61.1%, BS = 0.174). In the context of variable importance, CPH model indicated that age (P = 0.024), WHO grade (P = 0.020), IDH gene (P = 0.019), and MGMT promoter status (P = 0.040) were significantly correlated with PFS in the univariate analysis; multivariate analysis showed that age (P = 0.041), surgical completeness (P = 0.084), IDH gene (P = 0.057), and MGMT promoter (P = 0.092) had a significant or trend toward the relation with PFS. RSF showed that merely IDH and age were of positive importance for predicting PFS. A final nomogram was developed to predict tumor progression at the individual level based on CPH model.

Conclusions

In a relatively small dataset with HGG patients treated with PBRT, CPH outperformed RSF for predicting tumor progression. A comprehensive criterion with accuracy, precision, and interpretability is recommended in evaluating ML prognostication approaches for clinical deployment.

The SHORT Score for Preoperative Assessment of the Risk for Short-Term Survival in Glioblastoma

BACKGROUND

Despite recent improvements in treatment of glioblastoma (GBM), some patients still have a short survival. We sought to develop a new risk score for preoperative assessment of short-term survival (STS) (<6 months) in patients with GBM.

METHODS

All adult patients who underwent surgical resection of GBM between 2004 and 2014 were included (N = 379). Demographic and clinical parameters, which were available at admission, were assessed. Variables were evaluated in univariate and multivariate analyses. The score was validated in a separate cohort of patients with GBM who underwent surgical resection between 2015 and 2018.

RESULTS

The following independent predictors of STS were integrated into a new score: body height (<169 cm, 1 point), arterial hypertension (1 point), age (≤54 years, 0 points; 55-74 years, 1 points; ≥75 years, 2 points), and poor clinical status (Karnofsky performance scale [KPS] score: ≤60%, 2 points; 70%-80%, 1 point; ≥90%, 0 points). The new risk score, SHORT (Small body height, Hypertension, Older age, Reduced KPS score, short-Term survival), ranged from 0 to 6 points and showed good accuracy of risk estimation for STS in GBM (area under the curve: 0.715). STS rates were 9.7%, 23.1%, and 70% in patients with GBM scoring <2 points, 2-4 points, and >4 points (P < 0.0001). The score was successfully validated (area under the curve: 0.770).

CONCLUSIONS

This study presents the SHORT score for preoperative assessment of STS risk in patients with GBM. This risk score needs external validation in larger patient cohorts from other institutions. Our score might be a tool to facilitate treatment decisions in patients with GBM before surgery.

Image-Guided Radiooncology: The Potential of Radiomics in Clinical Application

Medical imaging plays an imminent role in today's radiation oncology workflow. Predominantly based on semantic image analysis, malignant tumors are diagnosed, staged, and therapy decisions are made. The field of "radiomics" promises to extract complementary, objective information from medical images. In radiomics, predefined quantitative features including intensity statistics, texture, shape, or filtering techniques are combined into statistical or machine learning models to predict clinical or biological outcomes. Alternatively, deep neural networks can directly analyze medical images and provide predictions. A large number of research studies could demonstrate that radiomics prediction models may provide significant benefits in the radiation oncology workflow including diagnostics, tumor characterization, target volume segmentation, prognostic stratification, and prediction of therapy response or treatment-related toxicities. This chapter provides an overview of techniques within the radiomics toolbox, potential clinical application, and current limitations. A literature overview of four selected malignant entities including non-small cell lung cancer, head and neck squamous cell carcinomas, soft tissue sarcomas, and gliomas is given.

Digital biomarkers: Importance of patient stratification for re-irradiation of glioma patients - Review of latest developments regarding scoring assessment

PURPOSE

To review scoring assessments in re-irradiation of high-grade glioma (HGG) patients and how to use scoring for patient stratification. The next aim was to investigate the different approaches employed by the scoring systems and the way they can be applied to build homogeneous patient groups for a reliable prognosis.

METHODS

We searched the Medline/Pubmed and Web of science databases for relevant articles regarding scores for re-irradiation of recurrent HGG. All references were divided into the following groups: novel score establishment (n = 5), score validation (n = 6), not relevant to this evaluation (n = 26).

RESULTS

We identified five scoring systems. Two are modifications of an already existing score. Calculations differ immensely from easy point addition to a more complex formula with including three up to 10 individual parameters. Six validation articles were found for three of the scores; one was validated four times. Two scores were never validated.

CONCLUSION

For recurrent HGG, the clinical situation remains demanding. Due to the heterogeneity of data at re-irradiation, patient stratification is important. Several scoring systems have been developed to predict prognosis. As a digital biomarker, scores are of high value regarding quick patient assessment and therapy decision making. For the next generation of digital biomarkers, easy calculation, and inclusion of easily available parameters are crucial.

Combining multimodal imaging and treatment features improves machine learning-based prognostic assessment in patients with glioblastoma multiforme

Background

For Glioblastoma (GBM), various prognostic nomograms have been proposed. This study aims to evaluate machine learning models to predict patients' overall survival (OS) and progression‐free survival (PFS) on the basis of clinical, pathological, semantic MRI‐based, and FET‐PET/CT‐derived information. Finally, the value of adding treatment features was evaluated.

Methods

One hundred and eighty‐nine patients were retrospectively analyzed. We assessed clinical, pathological, and treatment information. The VASARI set of semantic imaging features was determined on MRIs. Metabolic information was retained from preoperative FET‐PET/CT images. We generated multiple random survival forest prediction models on a patient training set and performed internal validation. Single feature class models were created including "clinical," "pathological," "MRI‐based," and "FET‐PET/CT‐based" models, as well as combinations. Treatment features were combined with all other features.

Results

Of all single feature class models, the MRI‐based model had the highest prediction performance on the validation set for OS (C‐index: 0.61 [95% confidence interval: 0.51‐0.72]) and PFS (C‐index: 0.61 [0.50‐0.72]). The combination of all features did increase performance above all single feature class models up to C‐indices of 0.70 (0.59‐0.84) and 0.68 (0.57‐0.78) for OS and PFS, respectively. Adding treatment information further increased prognostic performance up to C‐indices of 0.73 (0.62‐0.84) and 0.71 (0.60‐0.81) on the validation set for OS and PFS, respectively, allowing significant stratification of patient groups for OS.

Conclusions

MRI‐based features were the most relevant feature class for prognostic assessment. Combining clinical, pathological, and imaging information increased predictive power for OS and PFS. A further increase was achieved by adding treatment features.