Overall survival time prediction for high-grade glioma patients based on large-scale brain functional networks

Brain network topology and its cognitive impact in adult glioma survivors

Structural brain network topology can be altered in case of a brain tumor, due to both the tumor itself and its treatment. In this study, we explored the role of structural whole-brain and nodal network metrics and their association with cognitive functioning. Fifty WHO grade 2-3 adult glioma survivors (> 1-year post-therapy) and 50 matched healthy controls underwent a cognitive assessment, covering six cognitive domains. Raw cognitive assessment scores were transformed into w-scores, corrected for age and education. Furthermore, based on multi-shell diffusion-weighted MRI, whole-brain tractography was performed to create weighted graphs and to estimate whole-brain and nodal graph metrics. Hubs were defined based on nodal strength, betweenness centrality, clustering coefficient and shortest path length in healthy controls. Significant differences in these metrics between patients and controls were tested for the hub nodes (i.e. n = 12) and non-hub nodes (i.e. n = 30) in two mixed-design ANOVAs. Group differences in whole-brain graph measures were explored using Mann-Whitney U tests. Graph metrics that significantly differed were ultimately correlated with the cognitive domain-specific w-scores. Bonferroni correction was applied to correct for multiple testing. In survivors, the bilateral putamen were significantly less frequently observed as a hub (pbonf < 0.001). These nodes' assortativity values were positively correlated with attention (r(90) > 0.573, pbonf < 0.001), and proxy IQ (r(90) > 0.794, pbonf < 0.001). Attention and proxy IQ were significantly more often correlated with assortativity of hubs compared to non-hubs (pbonf < 0.001). Finally, the whole-brain graph measures of clustering coefficient (r = 0.685), global (r = 0.570) and local efficiency (r = 0.500) only correlated with proxy IQ (pbonf < 0.001). This study demonstrated potential reorganization of hubs in glioma survivors. Assortativity of these hubs was specifically associated with cognitive functioning, which could be important to consider in future modeling of cognitive outcomes and risk classification in glioma survivors.

The effect Of vascular related CeRNA genes and corresponding imaging biomarkers on survival in lower grade glioma

BACKGROUND & AIMS

To investigate the differential expression of vascular related ceRNA regulatory genes in LGG with different mutations of IDH1 and MGMT, and to verify imaging gene markers that can be closely associated with vascular related ceRNA regulatory genes.

METHOD

Five hundred fifteen patients with LGG were collected from TCGA database. CeRNA network analysis, GO analysis and Cox risk regression were used to find vascular ceRNA regulatory genes and their genetic markers related to survival. The preoperative MRI image data and postoperative tumor tissues of 14 patients with WHO grade III glioma were collected for full transcriptome analysis. The correlation between image characteristics of LGG and survival related vascular ceRNA regulatory genes was compared using nonparametric U test and Pearson correlation coefficient analysis.

RESULTS

Vascular related genes ranked first in the functional enrichment analysis of differentially expressed genes in LGG. EPHA2, ETS1, YAP1 and MEIS1 could significantly affect the survival of patients in each group of LGG. The volume of enhanced region was negatively correlated with IDH1 (r = -0.622, P = 0.009) mutation and TMEM100 (r = -0.535, P = 0.024), and positively correlated with MEIS1 (r = 0.551, P = 0.021), rCBFmax value was negatively correlated with TMEM100 (r = -0.492, P = 0.037).

CONCLUSIONS

Under different IDH1 mutations, lncRNA-dominated vascular-related ceRNA regulatory genes were the first differentially expressed subset of each group, and could be used as an effective risk factor affecting the survival of LGG. The image characteristics of LGG was an ideal image gene marker. It was a reliable imaging biological marker which can truly reflect the pathophysiological characteristics of glioma.

Functional MRI in Neuro-Oncology: State of the Art and Future Directions

Since its discovery in the early 1990s, functional MRI (fMRI) has been used to study human brain function. One well-established application of fMRI in the clinical setting is the neurosurgical planning of patients with brain tumors near eloquent cortical areas. Clinical fMRI aims to preoperatively identify eloquent cortices that serve essential functions in daily life, such as hand movement and language. The primary goal of neurosurgery is to maximize tumor resection while sparing eloquent cortices adjacent to the tumor. When a lesion presents in the vicinity of an eloquent cortex, surgeons may use fMRI to plan their best surgical approach by determining the proximity of the lesion to regions of activation, providing guidance for awake brain surgery and intraoperative brain mapping. The acquisition of fMRI requires patient preparation prior to imaging, determination of functional paradigms, monitoring of patient performance, and both processing and analysis of images. Interpretation of fMRI maps requires a strong understanding of functional neuroanatomy and familiarity with the technical limitations frequently present in brain tumor imaging, including neurovascular uncoupling, patient compliance, and data analysis. This review discusses clinical fMRI in neuro-oncology, relevant ongoing research topics, and prospective future developments in this exciting discipline.

Predicting survival in glioblastoma with multimodal neuroimaging and machine learning

PURPOSE

Glioblastoma (GBM) is the most common and aggressive malignant glioma, with an overall median survival of less than two years. The ability to predict survival before treatment in GBM patients would lead to improved disease management, clinical trial enrollment, and patient care.

METHODS

GBM patients (N = 133, mean age 60.8 years, median survival 14.1 months, 57.9% male) were retrospectively recruited from the neurosurgery brain tumor service at Washington University Medical Center. All patients completed structural neuroimaging and resting state functional MRI (RS-fMRI) before surgery. Demographics, measures of cortical thickness (CT), and resting state functional network connectivity (FC) were used to train a deep neural network to classify patients based on survival (< 1y, 1-2y, >2y). Permutation feature importance identified the strongest predictors of survival based on the trained models.

RESULTS

The models achieved a combined cross-validation and hold out accuracy of 90.6% in classifying survival (< 1y, 1-2y, >2y). The strongest demographic predictors were age at diagnosis and sex. The strongest CT predictors of survival included the superior temporal sulcus, parahippocampal gyrus, pericalcarine, pars triangularis, and middle temporal regions. The strongest FC features primarily involved dorsal and inferior somatomotor, visual, and cingulo-opercular networks.

CONCLUSION

We demonstrate that machine learning can accurately classify survival in GBM patients based on multimodal neuroimaging before any surgical or medical intervention. These results were achieved without information regarding presentation symptoms, treatments, postsurgical outcomes, or tumor genomic information. Our results suggest GBMs have a global effect on the brain's structural and functional organization, which is predictive of survival.

Patterns of gray and white matter functional networks involvement in glioblastoma patients: indirect mapping from clinical MRI scans

Background

Resting-state functional-MRI studies identified several cortical gray matter functional networks (GMNs) and white matter functional networks (WMNs) with precise anatomical localization. Here, we aimed at describing the relationships between brain's functional topological organization and glioblastoma (GBM) location. Furthermore, we assessed whether GBM distribution across these networks was associated with overall survival (OS).

Materials and methods

We included patients with histopathological diagnosis of IDH-wildtype GBM, presurgical MRI and survival data. For each patient, we recorded clinical-prognostic variables. GBM core and edema were segmented and normalized to a standard space. Pre-existing functional connectivity-based atlases were used to define network parcellations: 17 GMNs and 12 WMNs were considered in particular. We computed the percentage of lesion overlap with GMNs and WMNs, both for core and edema. Differences between overlap percentages were assessed through descriptive statistics, ANOVA, post-hoc tests, Pearson's correlation tests and canonical correlations. Multiple linear and non-linear regression tests were employed to explore relationships with OS.

Results

99 patients were included (70 males, mean age 62  years). The most involved GMNs included ventral somatomotor, salient ventral attention and default-mode networks; the most involved WMNs were ventral frontoparietal tracts, deep frontal white matter, and superior longitudinal fasciculus system. Superior longitudinal fasciculus system and dorsal frontoparietal tracts were significantly more included in the edema (p < 0.001). 5 main patterns of GBM core distribution across functional networks were found, while edema localization was less classifiable. ANOVA showed significant differences between mean overlap percentages, separately for GMNs and WMNs (p-values<0.0001). Core-N12 overlap predicts higher OS, although its inclusion does not increase the explained OS variance.

Discussion and conclusion

Both GBM core and edema preferentially overlap with specific GMNs and WMNs, especially associative networks, and GBM core follows five main distribution patterns. Some inter-related GMNs and WMNs were co-lesioned by GBM, suggesting that GBM distribution is not independent of the brain's structural and functional organization. Although the involvement of ventral frontoparietal tracts (N12) seems to have some role in predicting survival, network-topology information is overall scarcely informative about OS. fMRI-based approaches may more effectively demonstrate the effects of GBM on brain networks and survival.

Brain Tumor at Diagnosis: From Cognition and Behavior to Quality of Life

BACKGROUND

The present narrative review aims to discuss cognitive-emotional-behavioral symptoms in adults with brain tumors at the time of diagnosis.

METHODS

The PubMed database was searched considering glioma, pituitary adenoma, and meningioma in adulthood as pathologies, together with cognitive, neuropsychological, or behavioral aspects.

RESULTS

Although a significant number of studies describe cognitive impairment after surgery or treatment in adults with brain tumors, only few focus on cognitive-emotional-behavioral symptoms at diagnosis. Furthermore, the importance of an effective communication and its impact on patients' quality of life and compliance with treatment are seldom discussed.

CONCLUSIONS

Adults with brain tumors have needs in terms of cognitive-emotional-behavioral features that are detectable at the time of diagnosis; more research is needed to identify effective communication protocols in order to allow a higher perceived quality of life in these patients.

Radiomics-Based Machine Learning to Predict Recurrence in Glioma Patients Using Magnetic Resonance Imaging

OBJECTIVE

Recurrence is a major factor in the poor prognosis of patients with glioma. The aim of this study was to predict glioma recurrence using machine learning based on radiomic features.

METHODS

We recruited 77 glioma patients, consisting of 57 newly diagnosed patients and 20 patients with recurrence. After extracting the radiomic features from T2-weighted images, the data set was randomly divided into training (58 patients) and testing (19 patients) cohorts. An automated machine learning method (the Tree-based Pipeline Optimization Tool) was applied to generate 10 independent recurrence prediction models. The final model was determined based on the area under the curve (AUC) and average specificity. Moreover, an independent validation set of 20 patients with glioma was used to verify the model performance.

RESULTS

Recurrence in glioma patients was successfully predicting by machine learning using radiomic features. Among the 10 recurrence prediction models, the best model achieved an accuracy of 0.81, an AUC value of 0.85, and a specificity of 0.69 in the testing cohort, but an accuracy of 0.75 and an AUC value of 0.87 in the independent validation set.

CONCLUSIONS

Our algorithm that is generated by machine learning exhibits promising power and may predict recurrence noninvasively, thereby offering potential value for the early development of interventions to delay or prevent recurrence in glioma patients.

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.

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.

RP-Rs-fMRIomics as a Novel Imaging Analysis Strategy to Empower Diagnosis of Brain Gliomas

Rs-fMRI can provide rich information about functional processes in the brain with a large array of imaging parameters and is also suitable for investigating the biological processes in cerebral gliomas. We aimed to propose an imaging analysis method of RP-Rs-fMRIomics by adopting omics analysis on rs-fMRI with exhaustive regional parameters and subsequently estimating its feasibility on the prediction diagnosis of gliomas. In this retrospective study, preoperative rs-fMRI data were acquired from patients confirmed with diffuse gliomas (n = 176). A total of 420 features were extracted through measuring 14 regional parameters of rs-fMRI as much as available currently in 10 specific narrow frequency bins and three parts of gliomas. With a randomly split training and testing dataset (ratio 7:3), four classifiers were implemented to construct and optimize RP-Rs-fMRIomics models for predicting glioma grade, IDH status and Karnofsky Performance Status scores. The RP-Rs-fMRIomics models (AUROC 0.988, 0.905, 0.801) were superior to the corresponding traditional single rs-fMRI index (AUROC 0.803, 0.731, 0.632) in predicting glioma grade, IDH and survival. The RP-Rs-fMRIomics analysis, featuring high interpretability, was competitive for prediction of glioma grading, IDH genotype and prognosis. The method expanded the clinical application of rs-fMRI and also contributed a new imaging analysis for brain tumor research.

Neural alterations in opioid-exposed infants revealed by edge-centric brain functional networks

Prenatal opioid exposure has been linked to adverse effects spanning multiple neurodevelopmental domains, including cognition, motor development, attention, and vision. However, the neural basis of these abnormalities is largely unknown. A total of 49 infants, including 21 opioid-exposed and 28 controls, were enrolled and underwent MRI (43 ± 6 days old) after birth, including resting state functional MRI. Edge-centric functional networks based on dynamic functional connections were constructed, and machine-learning methods were employed to identify neural features distinguishing opioid-exposed infants from unexposed controls. An accuracy of 73.6% (sensitivity 76.25% and specificity 69.33%) was achieved using 10 times 10-fold cross-validation, which substantially outperformed those obtained using conventional static functional connections (accuracy 56.9%). More importantly, we identified that prenatal opioid exposure preferentially affects inter- rather than intra-network dynamic functional connections, particularly with the visual, subcortical, and default mode networks. Consistent results at the brain regional and connection levels were also observed, where the brain regions and connections associated with visual and higher order cognitive functions played pivotal roles in distinguishing opioid-exposed infants from controls. Our findings support the clinical phenotype of infants exposed to opioids in utero and may potentially explain the higher rates of visual and emotional problems observed in this population. Finally, our findings suggested that edge-centric networks could better capture the neural differences between opioid-exposed infants and controls by abstracting the intrinsic co-fluctuation along edges, which may provide a promising tool for future studies focusing on investigating the effects of prenatal opioid exposure on neurodevelopment.

Divergent and convergent imaging markers between bipolar and unipolar depression based on Machine Learning

Distinguishing bipolar depression (BD) from unipolar depression (UD) based on symptoms only is challenging. Brain functional connectivity (FC), especially dynamic FC, has emerged as a promising approach to identify possible imaging markers for differentiating BD from UD. However, most of such studies utilized conventional FC and group-level statistical comparisons, which may not be sensitive enough to quantify subtle changes in the FC dynamics between BD and UD. In this paper, we present a more effective individualized differentiation model based on machine learning and the whole-brain high-order functional connectivity (HOFC) network. The HOFC, capturing temporal synchronization among the dynamic FC time series, a more complex chronnectome metric compared to the conventional FC, was used to classify 52 BD, 73 UD, and 76 healthy controls (HC). We achieved a satisfactory accuracy (70.40%) in BD vs. UD differentiation. The resultant contributing features revealed the involvement of the coordinated flexible interactions among sensory (e.g., olfaction, vision, and audition), motor, and cognitive systems. Despite sharing common chronnectome of cognitive and affective impairments, BD and UD also demonstrated unique dynamic FC synchronization patterns. UD is more associated with abnormal visual-somatomotor inter-network connections, while BD is more related to impaired ventral attention-frontoparietal inter-network connections. Moreover, we found that the illness duration modulated the BD vs. UD separation, with the differentiation performance hampered by the secondary disease effects. Our findings suggest that BD and UD may have divergent and convergent neural substrates, which further expand our knowledge of the two different mental disorders.

Individual-specific networks for prediction modelling – A scoping review of methods

Background

Recent advances in biotechnology enable the acquisition of high-dimensional data on individuals, posing challenges for prediction models which traditionally use covariates such as clinical patient characteristics. Alternative forms of covariate representations for the features derived from these modern data modalities should be considered that can utilize their intrinsic interconnection. The connectivity information between these features can be represented as an individual-specific network defined by a set of nodes and edges, the strength of which can vary from individual to individual. Global or local graph-theoretical features describing the network may constitute potential prognostic biomarkers instead of or in addition to traditional covariates and may replace the often unsuccessful search for individual biomarkers in a high-dimensional predictor space.

Methods

We conducted a scoping review to identify, collate and critically appraise the state-of-art in the use of individual-specific networks for prediction modelling in medicine and applied health research, published during 2000–2020 in the electronic databases PubMed, Scopus and Embase.

Results

Our scoping review revealed the main application areas namely neurology and pathopsychology, followed by cancer research, cardiology and pathology (N = 148). Network construction was mainly based on Pearson correlation coefficients of repeated measurements, but also alternative approaches (e.g. partial correlation, visibility graphs) were found. For covariates measured only once per individual, network construction was mostly based on quantifying an individual’s contribution to the overall group-level structure. Despite the multitude of identified methodological approaches for individual-specific network inference, the number of studies that were intended to enable the prediction of clinical outcomes for future individuals was quite limited, and most of the models served as proof of concept that network characteristics can in principle be useful for prediction.

Conclusion

The current body of research clearly demonstrates the value of individual-specific network analysis for prediction modelling, but it has not yet been considered as a general tool outside the current areas of application. More methodological research is still needed on well-founded strategies for network inference, especially on adequate network sparsification and outcome-guided graph-theoretical feature extraction and selection, and on how networks can be exploited efficiently for prediction modelling.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-022-01544-6.

Classification of type 2 diabetes mellitus with or without cognitive impairment from healthy controls using high-order functional connectivity

Type 2 diabetes mellitus (T2DM) is associated with cognitive impairment and may progress to dementia. However, the brain functional mechanism of T2DM-related dementia is still less understood. Recent resting-state functional magnetic resonance imaging functional connectivity (FC) studies have proved its potential value in the study of T2DM with cognitive impairment (T2DM-CI). However, they mainly used a mass-univariate statistical analysis that was not suitable to reveal the altered FC "pattern" in T2DM-CI, due to lower sensitivity. In this study, we proposed to use high-order FC to reveal the abnormal connectomics pattern in T2DM-CI with a multivariate, machine learning-based strategy. We also investigated whether such patterns were different between T2DM-CI and T2DM without cognitive impairment (T2DM-noCI) to better understand T2DM-induced cognitive impairment, on 23 T2DM-CI and 27 T2DM-noCI patients, as well as 50 healthy controls (HCs). We first built the large-scale high-order brain networks based on temporal synchronization of the dynamic FC time series among multiple brain region pairs and then used this information to classify the T2DM-CI (as well as T2DM-noCI) from the matched HC based on support vector machine. Our model achieved an accuracy of 79.17% in T2DM-CI versus HC differentiation, but only 59.62% in T2DM-noCI versus HC classification. We found abnormal high-order FC patterns in T2DM-CI compared to HC, which was different from that in T2DM-noCI. Our study indicates that there could be widespread connectivity alterations underlying the T2DM-induced cognitive impairment. The results help to better understand the changes in the central neural system due to T2DM.

Characterization of cognitive function in survivors of diffuse gliomas using resting-state functional MRI (rs-fMRI)

As treatments for diffuse gliomas have advanced, survival for patients with gliomas has also increased. However, there remains limited knowledge on the relationships between brain connectivity and the lasting changes to cognitive function that glioma survivors often experience long after completing treatment. This resting-state functional magnetic resonance imaging (rs-fMRI) study explored functional connectivity (FC) alterations associated with cognitive function in survivors of gliomas. In this pilot study, 22 patients (mean age 43.8 ± 11.9) with diffuse gliomas who completed treatment within the past 10 years were evaluated using rs-fMRI and neuropsychological measures. Novel rs-fMRI analysis methods were used to account for missing brain in the resection cavity. FC relationships were assessed between cognitively impaired and non-impaired glioma patients, along with self-reported cognitive impairment, non-work daily functioning, and time with surgery. In the cognitively non-impaired patients, FC was stronger in the medial prefrontal cortex, rostral prefrontal cortex, and intraparietal sulcus compared to the impaired survivors. When examining non-work daily functioning, a positive correlation with FC was observed between the accumbens and the intracalcarine cortices, while a negative correlation with FC was observed between the parietal operculum cortex and the cerebellum. Additionally, worse self-reported cognitive impairment and worse non-work daily functioning were associated with increased FC between regions involved in cognition and sensorimotor processing. These preliminary findings suggest that neural correlates for cognitive and daily functioning in glioma patients can be revealed using rs-fMRI. Resting-state network alterations may serve as a biomarker for patients’ cognition and functioning.

Functional Disruptions of the Brain in Low Back Pain: A Potential Imaging Biomarker of Functional Disability

Chronic low back pain (LBP) is one of the leading causes of disability worldwide. While LBP research has largely focused on the spine, many studies have demonstrated a restructuring of human brain architecture accompanying LBP and other chronic pain states. Brain imaging presents a promising source for discovering noninvasive biomarkers that can improve diagnostic and prognostication outcomes for chronic LBP. This study evaluated graph theory measures derived from brain resting-state functional connectivity (rsFC) as prospective noninvasive biomarkers of LBP. We also proposed and tested a hybrid feature selection method (Enet-subset) that combines Elastic Net and an optimal subset selection method. We collected resting-state functional MRI scans from 24 LBP patients and 27 age-matched healthy controls (HC). We then derived graph-theoretical features and trained a support vector machine (SVM) to classify patient group. The degree centrality (DC), clustering coefficient (CC), and betweenness centrality (BC) were found to be significant predictors of patient group. We achieved an average classification accuracy of 83.1% (p < 0.004) and AUC of 0.937 (p < 0.002), respectively. Similarly, we achieved a sensitivity and specificity of 87.0 and 79.7%. The classification results from this study suggest that graph matrices derived from rsFC can be used as biomarkers of LBP. In addition, our findings suggest that the proposed feature selection method, Enet-subset, might act as a better technique to remove redundant variables and improve the performance of the machine learning classifier.

Graph Theoretical Analysis of Brain Network Characteristics in Brain Tumor Patients: A Systematic Review

Graph theory is a branch of mathematics that allows for the characterization of complex networks, and has rapidly grown in popularity in network neuroscience in recent years. Researchers have begun to use graph theory to describe the brain networks of individuals with brain tumors to shed light on disrupted networks. This systematic review summarizes the current literature on graph theoretical analysis of magnetic resonance imaging data in the brain tumor population with particular attention paid to treatment effects and other clinical factors. Included papers were published through June 24^th, 2020. Searches were conducted on Pubmed, PsycInfo, and Web of Science using the search terms (graph theory OR graph analysis) AND (brain tumor OR brain tumour OR brain neoplasm) AND (MRI OR EEG OR MEG). Studies were eligible for inclusion if they: evaluated participants with a primary brain tumor, used graph theoretical analyses on structural or functional MRI data, MEG, or EEG, were in English, and were an empirical research study. Seventeen papers met criteria for inclusion. Results suggest alterations in network properties are often found in people with brain tumors, although the directions of differences are inconsistent and few studies reported effect sizes. The most consistent finding suggests increased network segregation. Changes are most prominent with more intense treatment, in hub regions, and with factors such as faster tumor growth. The use of graph theory to study brain tumor patients is in its infancy, though some conclusions can be drawn. Future studies should focus on treatment factors, changes over time, and correlations with functional outcomes to better identify those in need of early intervention.

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.

Machine Learning Analytics of Resting-State Functional Connectivity Predicts Survival Outcomes of Glioblastoma Multiforme Patients

Glioblastoma multiforme (GBM) is the most frequently occurring brain malignancy. Due to its poor prognosis with currently available treatments, there is a pressing need for easily accessible, non-invasive techniques to help inform pre-treatment planning, patient counseling, and improve outcomes. In this study we determined the feasibility of resting-state functional connectivity (rsFC) to classify GBM patients into short-term and long-term survival groups with respect to reported median survival (14.6 months). We used a support vector machine with rsFC between regions of interest as predictive features. We employed a novel hybrid feature selection method whereby features were first filtered using correlations between rsFC and OS, and then using the established method of recursive feature elimination (RFE) to select the optimal feature subset. Leave-one-subject-out cross-validation evaluated the performance of models. Classification between short- and long-term survival accuracy was 71.9%. Sensitivity and specificity were 77.1 and 65.5%, respectively. The area under the receiver operating characteristic curve was 0.752 (95% CI, 0.62–0.88). These findings suggest that highly specific features of rsFC may predict GBM survival. Taken together, the findings of this study support that resting-state fMRI and machine learning analytics could enable a radiomic biomarker for GBM, augmenting care and planning for individual patients.

Machine learning classifiers for predicting 3-year progression-free survival and overall survival in patients with gliomas after surgery

Background: To develop machine-learning based models to predict the progression-free survival (PFS) and overall survival (OS) in patients with gliomas and explore the effect of different feature selection methods on the prediction.

Methods: We included 505 patients (training cohort, n = 354; validation cohort, n = 151) with gliomas between January 1, 2011 and December 31, 2016. The clinical, neuroimaging, and molecular genetic data of patients were retrospectively collected. The multi-causes discovering with structure learning (McDSL) algorithm, least absolute shrinkage and selection operator regression (LASSO), and Cox proportional hazards regression model were employed to discover the predictors for 3-year PFS and OS, respectively. Eight machine learning classifiers with 5-fold cross-validation were developed to predict 3-year PFS and OS. The area under the curve (AUC) was used to evaluate the prognostic performance of classifiers.

Results: McDSL identified four causal factors (tumor location, WHO grade, histologic type, and molecular genetic group) for 3-year PFS and OS, whereas LASSO and Cox identified wide-range number of factors associated with 3-year PFS and OS. The performance of each machine learning classifier based on McDSL, LASSO, and Cox was not significantly different. Logistic regression yielded the optimal performance in predicting 3-year PFS based on the McDSL (AUC, 0.872, 95% confidence interval [CI]: 0.828-0.916) and 3-year OS based on the LASSO (AUC, 0.901, 95% CI: 0.861-0.940).

Conclusions: McDSL is more reproducible than LASSO and Cox model in the feature selection process. Logistic regression model may have the highest performance in predicting 3-year PFS and OS of gliomas.

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.

Contrahemispheric Cortex Predicts Survival and Molecular Markers in Patients With Unilateral High-Grade Gliomas

Background: Malignant high-grade gliomas are characterized by infiltration and destruction of surrounding brain tissue. Alterations in the contrahemispheric brain structure and their roles that may offer prognostically valuable information have not been investigated in high-grade gliomas. Methods: In total, 153 patients with unilateral glioma (low-grade, n = 77; high-grade, n = 76) and 115 healthy controls (HCs) were recruited and scanned with 3-D T1 imaging. The gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) volume in the contrahemisphere were examined. Partial correlation, logistic regression, and multivariate Cox's regression analyses were performed. Results: The contrahemispheric GM volume (CHGMV) in the high-grade glioma patients was significantly decreased compared to that in the HCs/low-grade gliomas (one-way ANOVA, Bonferroni corrected, p < 0.05). The CHGMV is significantly correlated with the WHO grade (r = -0.22, p < 0.05) and contrast-enhanced volume (r = -0.33, p < 0.01). In the high-grade gliomas, the binary logistic regression revealed that the CHGMV can independently predict isocitrate dehydrogenase 1 (IDH1) and P53 mutations. The survival curves revealed that the patients with a low CHGMV had a shorter overall survival (OS) than the patients with a high CHGMV (p = 0.001). The multivariate Cox's regression analysis showed that a low CHGMV can independently predict unfavorable OS with a hazard ratio of 2.883 (p = 0.035). Conclusions: Volume of the contrahemispheric cortex can be potentially used in clinical practice as an imaging biomarker to predict survival and molecular markers in patients with unilateral high-grade gliomas.

A toolbox for brain network construction and classification (BrainNetClass)

Brain functional network has been increasingly used in understanding brain functions and diseases. While many network construction methods have been proposed, the progress in the field still largely relies on static pairwise Pearson's correlation-based functional network and group-level comparisons. We introduce a "Brain Network Construction and Classification (BrainNetClass)" toolbox to promote more advanced brain network construction methods to the filed, including some state-of-the-art methods that were recently developed to capture complex and high-order interactions among brain regions. The toolbox also integrates a well-accepted and rigorous classification framework based on brain connectome features toward individualized disease diagnosis in a hope that the advanced network modeling could boost the subsequent classification. BrainNetClass is a MATLAB-based, open-source, cross-platform toolbox with both graphical user-friendly interfaces and a command line mode targeting cognitive neuroscientists and clinicians for promoting reliability, reproducibility, and interpretability of connectome-based, computer-aided diagnosis. It generates abundant classification-related results from network presentations to contributing features that have been largely ignored by most studies to grant users the ability of evaluating the disease diagnostic model and its robustness and generalizability. We demonstrate the effectiveness of the toolbox on real resting-state functional MRI datasets. BrainNetClass (v1.0) is available at https://github.com/zzstefan/BrainNetClass.

Deep Learning of Imaging Phenotype and Genotype for Predicting Overall Survival Time of Glioblastoma Patients

Glioblastoma (GBM) is the most common and deadly malignant brain tumor. For personalized treatment, an accurate pre-operative prognosis for GBM patients is highly desired. Recently, many machine learning-based methods have been adopted to predict overall survival (OS) time based on the pre-operative mono- or multi-modal imaging phenotype. The genotypic information of GBM has been proven to be strongly indicative of the prognosis; however, this has not been considered in the existing imaging-based OS prediction methods. The main reason is that the tumor genotype is unavailable pre-operatively unless deriving from craniotomy. In this paper, we propose a new deep learning-based OS prediction method for GBM patients, which can derive tumor genotype-related features from pre-operative multimodal magnetic resonance imaging (MRI) brain data and feed them to OS prediction. Specifically, we propose a multi-task convolutional neural network (CNN) to accomplish both tumor genotype and OS prediction tasks jointly. As the network can benefit from learning tumor genotype-related features for genotype prediction, the accuracy of predicting OS time can be prominently improved. In the experiments, multimodal MRI brain dataset of 120 GBM patients, with as many as four different genotypic/molecular biomarkers, are used to evaluate our method. Our method achieves the highest OS prediction accuracy compared to other state-of-the-art methods.

Brain Tumor Segmentation and Survival Prediction Using Multimodal MRI Scans With Deep Learning

Gliomas are the most common primary brain malignancies. Accurate and robust tumor segmentation and prediction of patients' overall survival are important for diagnosis, treatment planning and risk factor identification. Here we present a deep learning-based framework for brain tumor segmentation and survival prediction in glioma, using multimodal MRI scans. For tumor segmentation, we use ensembles of three different 3D CNN architectures for robust performance through a majority rule. This approach can effectively reduce model bias and boost performance. For survival prediction, we extract 4,524 radiomic features from segmented tumor regions, then, a decision tree and cross validation are used to select potent features. Finally, a random forest model is trained to predict the overall survival of patients. The 2018 MICCAI Multimodal Brain Tumor Segmentation Challenge (BraTS), ranks our method at 2nd and 5th place out of 60+ participating teams for survival prediction tasks and segmentation tasks respectively, achieving a promising 61.0% accuracy on the classification of short-survivors, mid-survivors and long-survivors.