Predicting post-surgical functional status in high-grade glioma with resting state fMRI and machine learning.

PURPOSE: High-grade glioma (HGG) is the most common and deadly malignant glioma of the central nervous system. The current standard of care includes surgical resection of the tumor, which can lead to functional and cognitive deficits. The aim of this study is to develop models capable of predicting functional outcomes in HGG patients before surgery, facilitating improved disease management and informed patient care. METHODS: Adult HGG patients (N = 102) from the neurosurgery brain tumor service at Washington University Medical Center were retrospectively recruited. All patients completed structural neuroimaging and resting state functional MRI prior to surgery. Demographics, measures of resting state network connectivity (FC), tumor location, and tumor volume were used to train a random forest classifier to predict functional outcomes based on Karnofsky Performance Status (KPS < 70, KPS ≥ 70). RESULTS: The models achieved a nested cross-validation accuracy of 94.1% and an AUC of 0.97 in classifying KPS. The strongest predictors identified by the model included FC between somatomotor, visual, auditory, and reward networks. Based on location, the relation of the tumor to dorsal attention, cingulo-opercular, and basal ganglia networks were strong predictors of KPS. Age was also a strong predictor. However, tumor volume was only a moderate predictor. CONCLUSION: The current work demonstrates the ability of machine learning to classify postoperative functional outcomes in HGG patients prior to surgery accurately. Our results suggest that both FC and the tumor's location in relation to specific networks can serve as reliable predictors of functional outcomes, leading to personalized therapeutic approaches tailored to individual patients.

Optimal approaches to analyzing functional MRI data in glioma patients.

BACKGROUND: Resting-state fMRI is increasingly used to study the effects of gliomas on the functional organization of the brain. A variety of preprocessing techniques and functional connectivity analyses are represented in the literature. However, there so far has been no systematic comparison of how alternative methods impact observed results. NEW METHOD: We first surveyed current literature and identified alternative analytical approaches commonly used in the field. Following, we systematically compared alternative approaches to atlas registration, parcellation scheme, and choice of graph-theoretical measure as regards differentiating glioma patients (N = 59) from age-matched reference subjects (N = 163). RESULTS: Our results suggest that non-linear, as opposed to affine registration, improves structural match to an atlas, as well as measures of functional connectivity. Functionally- as opposed to anatomically-derived parcellation schemes maximized the contrast between glioma patients and reference subjects. We also demonstrate that graph-theoretic measures strongly depend on parcellation granularity, parcellation scheme, and graph density. COMPARISON WITH EXISTING METHODS AND CONCLUSIONS: Our current work primarily focuses on technical optimization of rs-fMRI analysis in glioma patients and, therefore, is fundamentally different from the bulk of papers discussing glioma-induced functional network changes. We report that the evaluation of glioma-induced alterations in the functional connectome strongly depends on analytical approaches including atlas registration, choice of parcellation scheme, and graph-theoretical measures.

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.

Glioblastoma induces whole-brain spectral change in resting state fMRI: Associations with clinical comorbidities and overall survival.

Glioblastoma, a highly aggressive form of brain tumor, is a brain-wide disease. We evaluated the impact of tumor burden on whole brain resting-state functional magnetic resonance imaging (rs-fMRI) activity. Specifically, we analyzed rs-fMRI signals in the temporal frequency domain in terms of the power-law exponent and fractional amplitude of low-frequency fluctuations (fALFF). We contrasted 189 patients with newly-diagnosed glioblastoma versus 189 age-matched healthy reference participants from an external dataset. The patient and reference datasets were matched for age and head motion. The principal finding was markedly flatter spectra and reduced grey matter fALFF in the patients as compared to the reference dataset. We posit that the whole-brain spectral change is attributable to global dysregulation of excitatory and inhibitory balance and metabolic demand in the tumor-bearing brain. Additionally, we observed that clinical comorbidities, in particular, seizures, and MGMT promoter methylation, were associated with flatter spectra. Notably, the degree of change in spectra was predictive of overall survival. Our findings suggest that frequency domain analysis of rs-fMRI activity provides prognostic information in glioblastoma patients and offers a means of noninvasively studying the effects of glioblastoma on the whole brain.

Data-efficient resting-state functional magnetic resonance imaging brain mapping with deep learning.

OBJECTIVE: Resting-state functional MRI (RS-fMRI) enables the mapping of function within the brain and is emerging as an efficient tool for the presurgical evaluation of eloquent cortex. Models capable of reliable and precise mapping of resting-state networks (RSNs) with a reduced scanning time would lead to improved patient comfort while reducing the cost per scan. The aims of the present study were to develop a deep 3D convolutional neural network (3DCNN) capable of voxel-wise mapping of language (LAN) and motor (MOT) RSNs with minimal quantities of RS-fMRI data. METHODS: Imaging data were gathered from multiple ongoing studies at Washington University School of Medicine and other thoroughly characterized, publicly available data sets. All study participants (n = 2252 healthy adults) were cognitively screened and completed structural neuroimaging and RS-fMRI. Random permutations of RS-fMRI regions of interest were used to train a 3DCNN. After training, model inferences were compared using varying amounts of RS-fMRI data from the control data set as well as 5 patients with glioblastoma multiforme. RESULTS: The trained model achieved 96% out-of-sample validation accuracy on data encompassing a large age range collected on multiple scanner types and varying sequence parameters. Testing on out-of-sample control data showed 97.9% similarity between results generated using either 50 or 200 RS-fMRI time points, corresponding to approximately 2.5 and 10 minutes, respectively (96.9% LAN, 96.3% MOT true-positive rate). In evaluating data from patients with brain tumors, the 3DCNN was able to accurately map LAN and MOT networks despite structural and functional alterations. CONCLUSIONS: Functional maps produced by the 3DCNN can inform surgical planning in patients with brain tumors in a time-efficient manner. The authors present a highly efficient method for presurgical functional mapping and thus improved functional preservation in patients with brain tumors.

Preoperative functional connectivity by magnetic resonance imaging for refractory neocortical epilepsy.

Objective: Patients with refractory epilepsy experience extensive and invasive clinical testing for seizure onset zones treatable by surgical resection. However, surgical resection can fail to provide therapeutic benefit, and patients with neocortical epilepsy have the poorest therapeutic outcomes. This case series studied patients with neocortical epilepsy who were referred for surgical treatment. Prior to surgery, patients volunteered for resting-state functional magnetic resonance imaging (rs-fMRI) in addition to imaging for the clinical standard of care. This work examined the variability of functional connectivity in patients, estimated from rs-fMRI, for associations with surgical outcomes. Methods: This work examined pre-operative structural imaging, pre-operative rs-fMRI, and post-operative structural imaging from seven epilepsy patients. Review of the clinical record provided Engel classifications for surgical outcomes. A novel method assessed pre-operative rs-fMRI from patients using comparative rs-fMRI from a large cohort of healthy control subjects and estimated Gibbs distributions for functional connectivity in patients compared to healthy controls. Results: Three patients had Engel classification Ia, one patient had Engel classification IIa, and three patients had Engel classification IV. Metrics for variability of functional connectivity, including absolute differences of the functional connectivity of each patient from healthy control averages and probabilistic scores for absolute differences, were higher for patients classified as Engel IV, for whom epilepsy surgery provided no meaningful improvement. Significance: This work continues on-going efforts to use rs-fMRI to characterize abnormal functional connectivity in the brain. Preliminary evidence indicates that the topography of variant functional connectivity in epilepsy patients may be clinically relevant for identifying patients unlikely to have favorable outcomes after epilepsy surgery. Widespread topographic variations of functional connectivity also support the hypothesis that epilepsy is a disease of brain resting-state networks.

Deep learning resting state functional magnetic resonance imaging lateralization of temporal lobe epilepsy.

OBJECTIVE: Localization of focal epilepsy is critical for surgical treatment of refractory seizures. There remains a great need for noninvasive techniques to localize seizures for surgical decision-making. We investigate the use of deep learning using resting state functional magnetic resonance imaging (RS-fMRI) to identify the hemisphere of seizure onset in temporal lobe epilepsy (TLE) patients. METHODS: A total of 2132 healthy controls and 32 preoperative TLE patients were studied. All participants underwent structural MRI and RS-fMRI. Healthy control data were used to generate training samples for a three-dimensional convolutional neural network (3DCNN). RS-fMRI was synthetically altered in randomly lateralized regions in the healthy control participants. The model was then trained to classify the hemisphere containing synthetic noise. Finally, the model was tested on TLE patients to assess its performance for detecting biological seizure onset zones, and gradient-weighted class activation mapping (Grad-CAM) identified the strongest predictive regions. RESULTS: The 3DCNN classified healthy control hemispheres known to contain synthetic noise with 96% accuracy, and TLE hemispheres clinically identified to be seizure onset zones with 90.6% accuracy. Grad-CAM identified a range of temporal, frontal, parietal, and subcortical regions that were strong anatomical predictors of the seizure onset zone, and the resting state networks that colocalized with Grad-CAM results included default mode, medial temporal, and dorsal attention networks. Lastly, in an analysis of a subset of patients with postsurgical outcomes, the 3DCNN leveraged a more focal set of regions to achieve classification in patients with Engel Class >I compared to Engel Class I. SIGNIFICANCE: Noninvasive techniques capable of localizing the seizure onset zone could improve presurgical planning in patients with intractable epilepsy. We have demonstrated the ability of deep learning to identify the correct hemisphere of the seizure onset zone in TLE patients using RS-fMRI with high accuracy. This approach represents a novel technique of seizure lateralization that could improve preoperative surgical planning.

Resting state network mapping in individuals using deep learning.

Introduction: Resting state functional MRI (RS-fMRI) is currently used in numerous clinical and research settings. The localization of resting state networks (RSNs) has been utilized in applications ranging from group analysis of neurodegenerative diseases to individual network mapping for pre-surgical planning of tumor resections. Reproducibility of these results has been shown to require a substantial amount of high-quality data, which is not often available in clinical or research settings. Methods: In this work, we report voxelwise mapping of a standard set of RSNs using a novel deep 3D convolutional neural network (3DCNN). The 3DCNN was trained on publicly available functional MRI data acquired in n = 2010 healthy participants. After training, maps that represent the probability of a voxel belonging to a particular RSN were generated for each participant, and then used to calculate mean and standard deviation (STD) probability maps, which are made publicly available. Further, we compared our results to previously published resting state and task-based functional mappings. Results: Our results indicate this method can be applied in individual subjects and is highly resistant to both noisy data and fewer RS-fMRI time points than are typically acquired. Further, our results show core regions within each network that exhibit high average probability and low STD. Discussion: The 3DCNN algorithm can generate individual RSN localization maps, which are necessary for clinical applications. The similarity between 3DCNN mapping results and task-based fMRI responses supports the association of specific functional tasks with RSNs.

Functional connectivity within glioblastoma impacts overall survival.

BACKGROUND: Glioblastoma (GBM; World Health Organization grade IV) assumes a variable appearance on MRI owing to heterogeneous proliferation and infiltration of its cells. As a result, the neurovascular units responsible for functional connectivity (FC) may exist within gross tumor boundaries, albeit with altered magnitude. Therefore, we hypothesize that the strength of FC within GBMs is predictive of overall survival. METHODS: We used predefined FC regions of interest (ROIs) in de novo GBM patients to characterize the presence of within-tumor FC observable via resting-state functional MRI and its relationship to survival outcomes. RESULTS: Fifty-seven GBM patients (mean age, 57.8 ±â€…13.9 y) were analyzed. Functionally connected voxels, not identifiable on conventional structural images, can be routinely found within the tumor mass and was not significantly correlated to tumor size. In patients with known survival times (n = 31), higher intranetwork FC strength within GBM tumors was associated with better overall survival even after accounting for clinical and demographic covariates. CONCLUSIONS: These findings suggest the possibility that functionally intact regions may persist within GBMs and that the extent to which FC is maintained may carry prognostic value and inform treatment planning.

Mapping of the Language Network With Deep Learning.

Background: Pre-surgical functional localization of eloquent cortex with task-based functional MRI (T-fMRI) is part of the current standard of care prior to resection of brain tumors. Resting state fMRI (RS-fMRI) is an alternative method currently under investigation. Here, we compare group level language localization using T-fMRI vs. RS-fMRI analyzed with 3D deep convolutional neural networks (3DCNN). Methods: We analyzed data obtained in 35 patients with brain tumors that had both language T-fMRI and RS-MRI scans during pre-surgical evaluation. The T-fMRI data were analyzed using conventional techniques. The language associated resting state network was mapped using a 3DCNN previously trained with data acquired in >2,700 normal subjects. Group level results obtained by both methods were evaluated using receiver operator characteristic analysis of probability maps of language associated regions, taking as ground truth meta-analytic maps of language T-fMRI responses generated on the Neurosynth platform. Results: Both fMRI methods localized major components of the language system (areas of Broca and Wernicke). Word-stem completion T-fMRI strongly activated Broca's area but also several task-general areas not specific to language. RS-fMRI provided a more specific representation of the language system. Conclusion: 3DCNN was able to accurately localize the language network. Additionally, 3DCNN performance was remarkably tolerant of a limited quantity of RS-fMRI data.

Mapping language function with task-based vs. resting-state functional MRI.

BACKGROUND: Use of functional MRI (fMRI) in pre-surgical planning is a non-invasive method for pre-operative functional mapping for patients with brain tumors, especially tumors located near eloquent cortex. Currently, this practice predominantly involves task-based fMRI (T-fMRI). Resting state fMRI (RS-fMRI) offers an alternative with several methodological advantages. Here, we compare group-level analyses of RS-fMRI vs. T-fMRI as methods for language localization. PURPOSE: To contrast RS-fMRI vs. T-fMRI as techniques for localization of language function. METHODS: We analyzed data obtained in 35 patients who had both T-fMRI and RS-fMRI scans during the course of pre-surgical evaluation. The RS-fMRI data were analyzed using a previously trained resting-state network classifier. The T-fMRI data were analyzed using conventional techniques. Group-level results obtained by both methods were evaluated in terms of two outcome measures: (1) inter-subject variability of response magnitude and (2) sensitivity/specificity analysis of response topography, taking as ground truth previously reported maps of the language system based on intraoperative cortical mapping as well as meta-analytic maps of language task fMRI responses. RESULTS: Both fMRI methods localized major components of the language system (areas of Broca and Wernicke) although not with equal inter-subject consistency. Word-stem completion T-fMRI strongly activated Broca's area but also several task-general areas not specific to language. RS-fMRI provided a more specific representation of the language system. CONCLUSION: We demonstrate several advantages of classifier-based mapping of language representation in the brain. Language T-fMRI activated task-general (i.e., not language-specific) functional systems in addition to areas of Broca and Wernicke. In contrast, classifier-based analysis of RS-fMRI data generated maps confined to language-specific regions of the brain.

Developmental hypomyelination in Wolfram syndrome: new insights from neuroimaging and gene expression analyses.

Wolfram syndrome is a rare multisystem disorder caused by mutations in WFS1 or CISD2 genes leading to brain structural abnormalities and neurological symptoms. These abnormalities appear in early stages of the disease. The pathogenesis of Wolfram syndrome involves abnormalities in the endoplasmic reticulum (ER) and mitochondrial dynamics, which are common features in several other neurodegenerative disorders. Mutations in WFS1 are responsible for the majority of Wolfram syndrome cases. WFS1 encodes for an endoplasmic reticulum (ER) protein, wolframin. It is proposed that wolframin deficiency triggers the unfolded protein response (UPR) pathway resulting in an increased ER stress-mediated neuronal loss. Recent neuroimaging studies showed marked alteration in early brain development, primarily characterized by abnormal white matter myelination. Interestingly, ER stress and the UPR pathway are implicated in the pathogenesis of some inherited myelin disorders like Pelizaeus-Merzbacher disease, and Vanishing White Matter disease. In addition, exploratory gene-expression network-based analyses suggest that WFS1 expression occurs preferentially in oligodendrocytes during early brain development. Therefore, we propose that Wolfram syndrome could belong to a category of neurodevelopmental disorders characterized by ER stress-mediated myelination impairment. Further studies of myelination and oligodendrocyte function in Wolfram syndrome could provide new insights into the underlying mechanisms of the Wolfram syndrome-associated brain changes and identify potential connections between neurodevelopmental disorders and neurodegeneration.