Connectivity-based parcellation of normal and anatomically distorted human cerebral cortex

Translational Connectomics: overview of machine learning in macroscale Connectomics for clinical insights

Connectomics is a neuroscience paradigm focused on noninvasively mapping highly intricate and organized networks of neurons. The advent of neuroimaging has led to extensive mapping of the brain functional and structural connectome on a macroscale level through modalities such as functional and diffusion MRI. In parallel, the healthcare field has witnessed a surge in the application of machine learning and artificial intelligence for diagnostics, especially in imaging. While reviews covering machine learn ing and macroscale connectomics exist for specific disorders, none provide an overview that captures their evolving role, especially through the lens of clinical application and translation. The applications include understanding disorders, classification, identifying neuroimaging biomarkers, assessing severity, predicting outcomes and intervention response, identifying potential targets for brain stimulation, and evaluating the effects of stimulation intervention on the brain and connectome mapping in patients before neurosurgery. The covered studies span neurodegenerative, neurodevelopmental, neuropsychiatric, and neurological disorders. Along with applications, the review provides a brief of common ML methods to set context. Conjointly, limitations in ML studies within connectomics and strategies to mitigate them have been covered.

Discernible interindividual patterns of global efficiency decline during theoretical brain surgery

The concept of functional localization within the brain and the associated risk of resecting these areas during removal of infiltrating tumors, such as diffuse gliomas, are well established in neurosurgery. Global efficiency (GE) is a graph theory concept that can be used to simulate connectome disruption following tumor resection. Structural connectivity graphs were created from diffusion tractography obtained from the brains of 80 healthy adults. These graphs were then used to simulate parcellation resection in every gross anatomical region of the cerebrum by identifying every possible combination of adjacent nodes in a graph and then measuring the drop in GE following nodal deletion. Progressive removal of brain parcellations led to patterns of GE decline that were reasonably predictable but had inter-subject differences. Additionally, as expected, there were deletion of some nodes that were worse than others. However, in each lobe examined in every subject, some deletion combinations were worse for GE than removing a greater number of nodes in a different region of the brain. Among certain patients, patterns of common nodes which exhibited worst GE upon removal were identified as "connectotypes". Given some evidence in the literature linking GE to certain aspects of neuro-cognitive abilities, investigating these connectotypes could potentially mitigate the impact of brain surgery on cognition.

Application of individual brain connectome in chronic ischemia: mapping symptoms before and after reperfusion

How brain functions in the distorted ischemic state before and after reperfusion is unclear. It is also uncertain whether there are any indicators within ischemic brain that could predict surgical outcomes. To alleviate these issues, we applied individual brain connectome in chronic steno-occlusive vasculopathy (CSOV) to map both ischemic symptoms and their postbypass changes. A total of 499 bypasses in 455 CSOV patients were collected and followed up for 47.8 ± 20.5 months. Using multimodal parcellation with connectivity-based and pathological distortion-independent approach, areal MR features of brain connectome were generated with three measurements of functional connectivity (FC), structural connectivity, and PageRank centrality at the single-subject level. Thirty-three machine-learning models were then trained with clinical and areal MR features to obtain acceptable classifiers for both ischemic symptoms and their postbypass changes, among which, 11 were deemed acceptable (AUC > 0.7). Notably, the FC feature-based model for long-term neurological outcomes performed very well (AUC > 0.8). Finally, a Shapley additive explanations plot was adopted to extract important individual features in acceptable models to generate "fingerprints" of brain connectome. This study not only establishes brain connectomic fingerprint databases for brain ischemia with distortion, but also provides informative insights for how brain functions before and after reperfusion.

DDParcel: Deep Learning Anatomical Brain Parcellation From Diffusion MRI

Parcellation of anatomically segregated cortical and subcortical brain regions is required in diffusion MRI (dMRI) analysis for region-specific quantification and better anatomical specificity of tractography. Most current dMRI parcellation approaches compute the parcellation from anatomical MRI (T1- or T2-weighted) data, using tools such as FreeSurfer or CAT12, and then register it to the diffusion space. However, the registration is challenging due to image distortions and low resolution of dMRI data, often resulting in mislabeling in the derived brain parcellation. Furthermore, these approaches are not applicable when anatomical MRI data is unavailable. As an alternative we developed the Deep Diffusion Parcellation (DDParcel), a deep learning method for fast and accurate parcellation of brain anatomical regions directly from dMRI data. The input to DDParcel are dMRI parameter maps and the output are labels for 101 anatomical regions corresponding to the FreeSurfer Desikan-Killiany (DK) parcellation. A multi-level fusion network leverages complementary information in the different input maps, at three network levels: input, intermediate layer, and output. DDParcel learns the registration of diffusion features to anatomical MRI from the high-quality Human Connectome Project data. Then, to predict brain parcellation for a new subject, the DDParcel network no longer requires anatomical MRI data but only the dMRI data. Comparing DDParcel's parcellation with T1w-based parcellation shows higher test-retest reproducibility and a higher regional homogeneity, while requiring much less computational time. Generalizability is demonstrated on a range of populations and dMRI acquisition protocols. Utility of DDParcel's parcellation is demonstrated on tractography analysis for fiber tract identification.

Intrinsic and Microenvironmental Drivers of Glioblastoma Invasion

Gliomas are diffusely infiltrating brain tumors whose prognosis is strongly influenced by their extent of invasion into the surrounding brain tissue. While lower-grade gliomas present more circumscribed borders, high-grade gliomas are aggressive tumors with widespread brain infiltration and dissemination. Glioblastoma (GBM) is known for its high invasiveness and association with poor prognosis. Its low survival rate is due to the certainty of its recurrence, caused by microscopic brain infiltration which makes surgical eradication unattainable. New insights into GBM biology at the single-cell level have enabled the identification of mechanisms exploited by glioma cells for brain invasion. In this review, we explore the current understanding of several molecular pathways and mechanisms used by tumor cells to invade normal brain tissue. We address the intrinsic biological drivers of tumor cell invasion, by tackling how tumor cells interact with each other and with the tumor microenvironment (TME). We focus on the recently discovered neuronal niche in the TME, including local as well as distant neurons, contributing to glioma growth and invasion. We then address the mechanisms of invasion promoted by astrocytes and immune cells. Finally, we review the current literature on the therapeutic targeting of the molecular mechanisms of invasion.

[Whole-brain parcellation for macaque brain magnetic resonance images based on attention mechanism and multi-modality feature fusion]

OBJECTIVE

We propose a novel deep learning algorithm based on attention mechanism and multimodality feature fusion (DDAM) to achieve whole-brain parcellation of macaque brain magnetic resonance (MR) images.

METHODS

We collected multimodality brain MR images of 68 macaques (aged 13 to 36 months) with corresponding ground truth labels. To address the complexity and complementary nature of the multimodality data, we employed a multi- encoder structure to adapt to different modalities and performed feature extraction. In the decoder, an attention mechanism was introduced to construct the Attention-based Multimodality Feature Fusion module (AMFF). Leveraging the rich and complementary information between modalities, AMFF effectively integrated multimodality features of varying scales and complexities to enhance the performance of parcellation. We conducted ablation experiments and statistically analyzed the results.

RESULTS

The incorporation of the multi- encoder structure and attention mechanism significantly improved the performance of the network for integrating the multimodality features, and achieved an average DSC of 0.904 and an ASD as low as 0.131 for macaque whole-brain parcellation (P < 0.05). The ablation experiments validated the effectiveness of each component of the DDAM method.

CONCLUSION

The proposed DDAM method, with its enhanced ability to extract and integrate multimodality features, can significantly improve the accuracy of whole-brain MR image segmentation.

Altered morphological characteristics and structural covariance connectivity associated with verbal working memory performance in ADHD children

OBJECTIVES

Deficits in verbal working memory (VWM) observed in attention deficit hyperactivity disorder (ADHD) children can persist into adulthood. Although previous studies have identified brain regions that are activated during VWM tasks, the neural mechanisms underlying the relationship between VWM deficits remain unclear. The objective of this study was to investigate the structural covariance network connectivity and brain morphology changes that are associated with VWM performance in ADHD children.

METHODS

For this study, we selected 26 ADHD children and 26 healthy control (HC) participants. Participants were instructed to perform an n-back VWM task and their accuracy and response times were subsequently recorded. This research utilised voxel-based morphometry to measure the grey matter (GM) volume and conducted structural covariance connectivity network analysis to explore the changes of brain in ADHD.

RESULTS

Voxel-based morphometry analysis showed that lower GM volume in the right cerebellum lobule VI and the left parahippocampal gryus in ADHD children. Moreover, a positive correlation was found between the GM volume in the right cerebellum lobule VI and the accuracy of 2-back VWM task with verbal, small reward, and delayed feedback (VSD). Structural covariance network analysis found decreased structural connectivity between right cerebellum lobule VI and right precentral gyrus, right postcentral gyrus, left paracentral lobule, right superior parietal gyrus, and left hippocampus in ADHD children.

CONCLUSIONS

The low GM volume and altered structural covariance connectivity in the right cerebellum lobule VI might potentially affect VWM performance in ADHD children.

ADVANCES IN KNOWLEDGE

The innovation of this study lies in its more focused discussion on the morphological characteristics and structural covariance connectivity of VWM deficits in ADHD children, and the innovative finding of a positive correlation between grey matter volume in the right cerebellum lobule VI and accuracy in completing the 2-back VWM task with verbal instructions, small reward, and delayed feedback (VSD). This expands upon previous research by elucidating the specific brain structures involved in VWM deficits in ADHD children and highlights the potential importance of the cerebellum in this cognitive process. Overall, these innovative findings advance our understanding of the neural basis of ADHD and may have important implications for the development of targeted interventions for VWM deficits.

Incorporation of Brain Connectomics for Stereotactic Radiosurgery Treatment Planning

BACKGROUND AND IMPORTANCE

Neurosurgeons have integrated neuroanatomy-based tractography to avoid critical structures during dose planning. However, they have yet to integrate more comprehensive connectome networks for radiosurgical planning.

CLINICAL PRESENTATION

A young man presented with a Spetzler-Martin Grade 3 right temporal arteriovenous malformation.

DISCUSSION

As proof of concept, we incorporated connectomic networks including default mode network, optic radiation and central executive network into the Gamma Knife radiosurgical treatment planning workflow. Connectome networks were created from T1 anatomic and diffusion-weighted images magnetic resonance images using Quicktome software. The resulting networks were voxel-encoded in the magnetic resonance images, imported into GammaPlan, and segmented by image thresholding. The GammaPlan Lightning optimizer was used to create radiosurgical plans with a dose of 20 Gy to the 50% isodose line delivered to the arteriovenous malformation nidus both with and without treating these networks as risk structures. When taking into account the connectome networks, a maximum dose restriction of 14 Gy was placed on each network during lightning dose planning. With default mode network, optic radiation, and central executive network as risk structures, the maximum dose and V 12Gy were reduced by 23.4% and 88.3%, 20% and 34.3%, and 29.8% and 63.2%, respectively.

CONCLUSION

We were able to incorporate connectomes into radiosurgical dose planning approaches. This allowed for dose reductions to the networks while still achieving delivery of a therapeutic dose to the target volume.

Functional connectivity reveals different brain networks underlying the idiopathic foreign accent syndrome

Foreign accent syndrome (FAS) is characterized by new onset speech that is perceived as foreign. Available data from acquired cases suggests focal brain damage in language and sensorimotor brain networks, but little remains known about abnormal functional connectivity in idiopathic cases of FAS without structural damage. Here, connectomic analyses were completed on three patients with idiopathic FAS to investigate unique functional connectivity abnormalities underlying accent change for the first time. Machine learning (ML)-based algorithms generated personalized brain connectomes based on a validated parcellation scheme from the Human Connectome Project (HCP). Diffusion tractography was performed on each patient to rule out structural fiber damage to the language system. Resting-state-fMRI was assessed with ML-based software to examine functional connectivity between individual parcellations within language and sensorimotor networks and subcortical structures. Functional connectivity matrices were created and compared against a dataset of 200 healthy subjects to identify abnormally connected parcellations. Three female patients (28-42 years) who presented with accent changes from Australian English to Irish (n = 2) or American English to British English (n = 1) demonstrated fully intact language system structural connectivity. All patients demonstrated functional connectivity anomalies within language and sensorimotor networks in numerous left frontal regions and between subcortical structures in one patient. Few commonalities in functional connectivity anomalies were identified between all three patients, specifically 3 internal-network parcellation pairs. No common inter-network functional connectivity anomalies were identified between all patients. The current study demonstrates specific language, and sensorimotor functional connectivity abnormalities can exist and be quantitatively shown in the absence of structural damage for future study.

Large-scale brain networks and intra-axial tumor surgery: a narrative review of functional mapping techniques, critical needs, and scientific opportunities

In recent years, a paradigm shift in neuroscience has been occurring from "localizationism," or the idea that the brain is organized into separately functioning modules, toward "connectomics," or the idea that interconnected nodes form networks as the underlying substrates of behavior and thought. Accordingly, our understanding of mechanisms of neurological function, dysfunction, and recovery has evolved to include connections, disconnections, and reconnections. Brain tumors provide a unique opportunity to probe large-scale neural networks with focal and sometimes reversible lesions, allowing neuroscientists the unique opportunity to directly test newly formed hypotheses about underlying brain structural-functional relationships and network properties. Moreover, if a more complete model of neurological dysfunction is to be defined as a "disconnectome," potential avenues for recovery might be mapped through a "reconnectome." Such insight may open the door to novel therapeutic approaches where previous attempts have failed. In this review, we briefly delve into the most clinically relevant neural networks and brain mapping techniques, and we examine how they are being applied to modern neurosurgical brain tumor practices. We then explore how brain tumors might teach us more about mechanisms of global brain dysfunction and recovery through pre- and postoperative longitudinal connectomic and behavioral analyses.

Connectomic insight into unique stroke patient recovery after rTMS treatment

An improved understanding of the neuroplastic potential of the brain has allowed advancements in neuromodulatory treatments for acute stroke patients. However, there remains a poor understanding of individual differences in treatment-induced recovery. Individualized information on connectivity disturbances may help predict differences in treatment response and recovery phenotypes. We studied the medical data of 22 ischemic stroke patients who received MRI scans and started repetitive transcranial magnetic stimulation (rTMS) treatment on the same day. The functional and motor outcomes were assessed at admission day, 1 day after treatment, 30 days after treatment, and 90 days after treatment using four validated standardized stroke outcome scales. Each patient underwent detailed baseline connectivity analyses to identify structural and functional connectivity disturbances. An unsupervised machine learning (ML) agglomerative hierarchical clustering method was utilized to group patients according to outcomes at four-time points to identify individual phenotypes in recovery trajectory. Differences in connectivity features were examined between individual clusters. Patients were a median age of 64, 50% female, and had a median hospital length of stay of 9.5 days. A significant improvement between all time points was demonstrated post treatment in three of four validated stroke scales utilized. ML-based analyses identified distinct clusters representing unique patient trajectories for each scale. Quantitative differences were found to exist in structural and functional connectivity analyses of the motor network and subcortical structures between individual clusters which could explain these unique trajectories on the Barthel Index (BI) scale but not on other stroke scales. This study demonstrates for the first time the feasibility of using individualized connectivity analyses in differentiating unique phenotypes in rTMS treatment responses and recovery. This personalized connectomic approach may be utilized in the future to better understand patient recovery trajectories with neuromodulatory treatment.

Non-traditional cognitive brain network involvement in insulo-Sylvian gliomas: a case series study and clinical experience using Quicktome

BACKGROUND

Patients with insulo-Sylvian gliomas continue to present with severe morbidity in cognitive functions primarily due to neurosurgeons' lack of familiarity with non-traditional brain networks. We sought to identify the frequency of invasion and proximity of gliomas to portions of these networks.

METHODS

We retrospectively analyzed data from 45 patients undergoing glioma surgery centered in the insular lobe. Tumors were categorized based on their proximity and invasiveness of non-traditional cognitive networks and traditionally eloquent structures. Diffusion tensor imaging tractography was completed by creating a personalized brain atlas using Quicktome to determine eloquent and non-eloquent networks in each patient. Additionally, we prospectively collected neuropsychological data on 7 patients to compare tumor-network involvement with change in cognition. Lastly, 2 prospective patients had their surgical plan influenced by network mapping determined by Quicktome.

RESULTS

Forty-four of 45 patients demonstrated tumor involvement (< 1 cm proximity or invasion) with components of non-traditional brain networks involved in cognition such as the salience network (SN, 60%) and the central executive network (CEN, 56%). Of the seven prospective patients, all had tumors involved with the SN, CEN (5/7, 71%), and language network (5/7, 71%). The mean scores of MMSE and MOCA before surgery were 18.71 ± 6.94 and 17.29 ± 6.26, respectively. The two cases who received preoperative planning with Quicktome had a postoperative performance that was anticipated.

CONCLUSIONS

Non-traditional brain networks involved in cognition are encountered during surgical resection of insulo-Sylvian gliomas. Quicktome can improve the understanding of the presence of these networks and allow for more informed surgical decisions based on patient functional goals.

Functional connectivity analysis of the depression connectome provides potential markers and targets for transcranial magnetic stimulation

BACKGROUND

Despite efforts to improve targeting accuracy of the dorsolateral prefrontal cortex (DLPFC) as a repetitive transcranial magnetic stimulation (rTMS) target for Major Depressive Disorder (MDD), the heterogeneity in clinical response remains unexplained.

OBJECTIVE

We sought to compare the patterns of functional connectivity from the DLPFC treatment site in patients with MDD who were TMS responders to those who were TMS non-responders.

METHODS

Baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI, and diffusion weighted imaging scans were obtained from 37 participants before they underwent a course of rTMS to left Brodmann area 46. A novel machine learning method was utilized to identify brain regions associated with each item of the Beck's Depression Inventory II (BDI-II), and for 26 participants who underwent rTMS treatment over the left Brodmann area 46, identify regions differentiating rTMS responders and non-responders.

RESULTS

Nine parcels of the Human Connectome Project Multimodal Parcellation Atlas matched to at least three items of the Beck's Depression Inventory II (BDI-II) as predictors of response to rTMS, with many in the temporal, parietal and cingulate cortices. Additionally, pre-treatment mapping for 17 items of the BDI-II demonstrated significant variability in symptom to parcel mapping. When parcels associated with symptom presence and symptom resolution were compared, 15 parcels were uniquely associated with resolution (potential targets), and 12 parcels were associated with both symptom presence and resolution (blockers or biomarkers).

CONCLUSIONS

Machine learning approaches show promise for the development of pathoanatomical diagnosis and treatment algorithms for MDD. Prospective studies are required to facilitate clinical translation.

Intraoperative awake language mapping correlates to preoperative connectomics imaging: An instructive case

Connectomics enables the study of structural-functional relationships in the brain, and machine learning technologies have enabled connectome maps to be developed for individual brain tumor patients. We report our experience using connectomics to plan and guide an awake craniotomy for a tumor impinging on the language area. Preoperative connectomics imaging demonstrated proximity of the tumor to parcellations of the language area. Intraoperative awake language mapping was performed, revealing speech arrest and paraphasic errors at areas of the tumor boundary correlating to functional regions that explained these findings. This instructive case highlights the potential benefits of implementing connectomics into neurosurgical planning.

Functional connectivity of the language area in migraine: a preliminary classification model

BACKGROUND

Migraine is a complex disorder characterized by debilitating headaches. Despite its prevalence, its pathophysiology remains unknown, with subsequent gaps in diagnosis and treatment. We combined machine learning with connectivity analysis and applied a whole-brain network approach to identify potential targets for migraine diagnosis and treatment.

METHODS

Baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI(rfMRI), and diffusion weighted scans were obtained from 31 patients with migraine, and 17 controls. A recently developed machine learning technique, Hollow Tree Super (HoTS) was used to classify subjects into diagnostic groups based on functional connectivity (FC) and derive networks and parcels contributing to the model. PageRank centrality analysis was also performed on the structural connectome to identify changes in hubness.

RESULTS

Our model attained an area under the receiver operating characteristic curve (AUC-ROC) of 0.68, which rose to 0.86 following hyperparameter tuning. FC of the language network was most predictive of the model's classification, though patients with migraine also demonstrated differences in the accessory language, visual and medial temporal regions. Several analogous regions in the right hemisphere demonstrated changes in PageRank centrality, suggesting possible compensation.

CONCLUSIONS

Although our small sample size demands caution, our preliminary findings demonstrate the utility of our method in providing a network-based perspective to diagnosis and treatment of migraine.

Real world demonstration of hand motor mapping using the structural connectivity atlas

BACKGROUND

Locating the hand-motor-cortex (HMC) is an essential component within many neurosurgeries. Despite advancements in these localization methods there are still downfalls for each. Additionally, the importance of presurgical planning calls for increasingly accurate and efficient methods of locating specific cortical regions.

OBJECTIVE

In this study we aimed to test the ability of the Structural Connectivity Atlas (SCA), a machine-learning based method to parcellate the human cortex, to locate the HMC in a small cohort study.

METHODS

Using MRI and DTI images obtained from adult subjects (n = 11), personalized brain maps were created for each individual based on a SCA paired with the Brainnetome region for the HMC. Subjects received single pulse TMS, over the HMC region through the use of a neuronavigation system. If they responded with motor movement, this was recorded. The SCA identified HMC region was compared to the visual-determined HMC through identifying the Omega fold on the Precentral Gyrus, which was completed by a trained neuroanatomist. A Kendall's Tau B correlation was conducted between anatomical match and visual movement.

RESULTS

This study concluded that the SCA was capable of locating the HMC in healthy and distorted brains. Overall, the SCA defined the anatomical area of the HMC in 90 % of subjects and triggered a motor response in 61 %.

CONCLUSION

The SCA could be suitable for incorporation into presurgical planning practices due to its ability to map anatomically abnormal brains. Further studies on larger cohorts and targeting different areas of cortex could be beneficial.

Graph Theory Measures and Their Application to Neurosurgical Eloquence

Improving patient safety and preserving eloquent brain are crucial in neurosurgery. Since there is significant clinical variability in post-operative lesions suffered by patients who undergo surgery in the same areas deemed compensable, there is an unknown degree of inter-individual variability in brain 'eloquence'. Advances in connectomic mapping efforts through diffusion tractography allow for utilization of non-invasive imaging and statistical modeling to graphically represent the brain. Extending the definition of brain eloquence to graph theory measures of hubness and centrality may help to improve our understanding of individual variability in brain eloquence and lesion responses. While functional deficits cannot be immediately determined intra-operatively, there has been potential shown by emerging technologies in mapping of hub nodes as an add-on to existing surgical navigation modalities to improve individual surgical outcomes. This review aims to outline and review current research surrounding novel graph theoretical concepts of hubness, centrality, and eloquence and specifically its relevance to brain mapping for pre-operative planning and intra-operative navigation in neurosurgery.

Connectomics underlying motor functional outcomes in the acute period following stroke

Objective

Stroke remains the number one cause of morbidity in many developing countries, and while effective neurorehabilitation strategies exist, it remains difficult to predict the individual trajectories of patients in the acute period, making personalized therapies difficult. Sophisticated and data-driven methods are necessary to identify markers of functional outcomes.

Methods

Baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI (rsfMRI), and diffusion weighted scans were obtained from 79 patients following stroke. Sixteen models were constructed to predict performance across six tests of motor impairment, spasticity, and activities of daily living, using either whole-brain structural or functional connectivity. Feature importance analysis was also performed to identify brain regions and networks associated with performance in each test.

Results

The area under the receiver operating characteristic curve ranged from 0.650 to 0.868. Models utilizing functional connectivity tended to have better performance than those utilizing structural connectivity. The Dorsal and Ventral Attention Networks were among the top three features in several structural and functional models, while the Language and Accessory Language Networks were most commonly implicated in structural models.

Conclusions

Our study highlights the potential of machine learning methods combined with connectivity analysis in predicting outcomes in neurorehabilitation and disentangling the neural correlates of functional impairments, though further longitudinal studies are necessary.

Brain functional activity-based classification of autism spectrum disorder using an attention-based graph neural network combined with gene expression

Autism spectrum disorder (ASD) is a complex brain neurodevelopmental disorder related to brain activity and genetics. Most of the ASD diagnostic models perform feature selection at the group level without considering individualized information. Evidence has shown the unique topology of the individual brain has a fundamental impact on brain diseases. Thus, a data-constructing method fusing individual topological information and a corresponding classification model is crucial in ASD diagnosis and biomarker discovery. In this work, we trained an attention-based graph neural network (GNN) to perform the ASD diagnosis with the fusion of graph data. The results achieved an accuracy of 79.78%. Moreover, we found the model paid high attention to brain regions mainly involved in the social-brain circuit, default-mode network, and sensory perception network. Furthermore, by analyzing the covariation between functional magnetic resonance imaging data and gene expression, current studies detected several ASD-related genes (i.e. MUTYH, AADAT, and MAP2), and further revealed their links to image biomarkers. Our work demonstrated that the ASD diagnostic framework based on graph data and attention-based GNN could be an effective tool for ASD diagnosis. The identified functional features with high attention values may serve as imaging biomarkers for ASD.

High-resolution cortical parcellation based on conserved brain landmarks for localization of multimodal data to the nearest centimeter

Precise cortical brain localization presents an important challenge in the literature. Brain atlases provide data-guided parcellation based on functional and structural brain metrics, and each atlas has its own unique benefits for localization. We offer a parcellation guided by intracranial electroencephalography, a technique which has historically provided pioneering advances in our understanding of brain structure-function relationships. We used a consensus boundary mapping approach combining anatomical designations in Duvernoy's Atlas of the Human Brain, a widely recognized textbook of human brain anatomy, with the anatomy of the MNI152 template and the magnetic resonance imaging scans of an epilepsy surgery cohort. The Yale Brain Atlas consists of 690 one-square centimeter parcels based around conserved anatomical features and each with a unique identifier to communicate anatomically unambiguous localization. We report on the methodology we used to create the Atlas along with the findings of a neuroimaging study assessing the accuracy and clinical usefulness of cortical localization using the Atlas. We also share our vision for the Atlas as a tool in the clinical and research neurosciences, where it may facilitate precise localization of data on the cortex, accurate description of anatomical locations, and modern data science approaches using standardized brain regions.

Use of machine learning to identify functional connectivity changes in a clinical cohort of patients at risk for dementia

Objective

Progressive conditions characterized by cognitive decline, including mild cognitive impairment (MCI) and subjective cognitive decline (SCD) are clinical conditions representing a major risk factor to develop dementia, however, the diagnosis of these pre-dementia conditions remains a challenge given the heterogeneity in clinical trajectories. Earlier diagnosis requires data-driven approaches for improved and targeted treatment modalities.

Methods

Neuropsychological tests, baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI (rsfMRI), and diffusion weighted scans were obtained from 35 patients with SCD, 19 with MCI, and 36 age-matched healthy controls (HC). A recently developed machine learning technique, Hollow Tree Super (HoTS) was utilized to classify subjects into diagnostic categories based on their FC, and derive network and parcel-based FC features contributing to each model. The same approach was used to identify features associated with performance in a range of neuropsychological tests. We concluded our analysis by looking at changes in PageRank centrality (a measure of node hubness) between the diagnostic groups.

Results

Subjects were classified into diagnostic categories with a high area under the receiver operating characteristic curve (AUC-ROC), ranging from 0.73 to 0.84. The language networks were most notably associated with classification. Several central networks and sensory brain regions were predictors of poor performance in neuropsychological tests, suggesting maladaptive compensation. PageRank analysis highlighted that basal and limbic deep brain region, along with the frontal operculum demonstrated a reduction in centrality in both SCD and MCI patients compared to controls.

Conclusion

Our methods highlight the potential to explore the underlying neural networks contributing to the cognitive changes and neuroplastic responses in prodromal dementia.

Connectomic disturbances underlying insomnia disorder and predictors of treatment response

Objective

Despite its prevalence, insomnia disorder (ID) remains poorly understood. In this study, we used machine learning to analyze the functional connectivity (FC) disturbances underlying ID, and identify potential predictors of treatment response through recurrent transcranial magnetic stimulation (rTMS) and pharmacotherapy.

Materials and methods

51 adult patients with chronic insomnia and 42 healthy age and education matched controls underwent baseline anatomical T1 magnetic resonance imaging (MRI), resting-stage functional MRI (rsfMRI), and diffusion weighted imaging (DWI). Imaging was repeated for 24 ID patients following four weeks of treatment with pharmacotherapy, with or without rTMS. A recently developed machine learning technique, Hollow Tree Super (HoTS) was used to classify subjects into ID and control groups based on their FC, and derive network and parcel-based FC features contributing to each model. The number of FC anomalies within each network was also compared between responders and non-responders using median absolute deviation at baseline and follow-up.

Results

Subjects were classified into ID and control with an area under the receiver operating characteristic curve (AUC-ROC) of 0.828. Baseline FC anomaly counts were higher in responders than non-responders. Response as measured by the Insomnia Severity Index (ISI) was associated with a decrease in anomaly counts across all networks, while all networks showed an increase in anomaly counts when response was measured using the Pittsburgh Sleep Quality Index. Overall, responders also showed greater change in all networks, with the Default Mode Network demonstrating the greatest change.

Conclusion

Machine learning analysis into the functional connectome in ID may provide useful insight into diagnostic and therapeutic targets.

Neurosurgical Clinical Trials for Glioblastoma: Current and Future Directions

The mainstays of glioblastoma treatment, maximal safe resection, radiotherapy preserving neurological function, and temozolomide (TMZ) chemotherapy have not changed for the past 17 years despite significant advances in the understanding of the genetics and molecular biology of glioblastoma. This review highlights the neurosurgical foundation for glioblastoma therapy. Here, we review the neurosurgeon’s role in several new and clinically-approved treatments for glioblastoma. We describe delivery techniques such as blood–brain barrier disruption and convection-enhanced delivery (CED) that may be used to deliver therapeutic agents to tumor tissue in higher concentrations than oral or intravenous delivery. We mention pivotal clinical trials of immunotherapy for glioblastoma and explain their outcomes. Finally, we take a glimpse at ongoing clinical trials and promising translational studies to predict ways that new therapies may improve the prognosis of patients with glioblastoma.

Machine Learning Decomposition of the Anatomy of Neuropsychological Deficit in Alzheimer’s Disease and Mild Cognitive Impairment

Objective

Alzheimer’s Disease (AD) is a progressive condition characterized by cognitive decline. AD is often preceded by mild cognitive impairment (MCI), though the diagnosis of both conditions remains a challenge. Early diagnosis of AD, and prediction of MCI progression require data-driven approaches to improve patient selection for treatment. We used a machine learning tool to predict performance in neuropsychological tests in AD and MCI based on functional connectivity using a whole-brain connectome, in an attempt to identify network substrates of cognitive deficits in AD.

Methods

Neuropsychological tests, baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI, and diffusion weighted imaging scans were obtained from 149 MCI, and 85 AD patients; and 140 cognitively unimpaired geriatric participants. A novel machine learning tool, Hollow Tree Super (HoTS) was utilized to extract feature importance from each machine learning model to identify brain regions that were associated with deficit and absence of deficit for 11 neuropsychological tests.

Results

11 models attained an area under the receiver operating curve (AUC-ROC) greater than 0.65, while five models had an AUC-ROC ≥ 0.7. 20 parcels of the Human Connectome Project Multimodal Parcelation Atlas matched to poor performance in at least two neuropsychological tests, while 14 parcels were associated with good performance in at least two tests. At a network level, most parcels predictive of both presence and absence of deficit were affiliated with the Central Executive Network, Default Mode Network, and the Sensorimotor Networks. Segregating predictors by the cognitive domain associated with each test revealed areas of coherent overlap between cognitive domains, with the parcels providing possible markers to screen for cognitive impairment.

Conclusion

Approaches such as ours which incorporate whole-brain functional connectivity and harness feature importance in machine learning models may aid in identifying diagnostic and therapeutic targets in AD.

Interventional neurorehabilitation for promoting functional recovery post-craniotomy: a proof-of-concept

The human brain is a highly plastic ‘complex’ network—it is highly resilient to damage and capable of self-reorganisation after a large perturbation. Clinically, neurological deficits secondary to iatrogenic injury have very few active treatments. New imaging and stimulation technologies, though, offer promising therapeutic avenues to accelerate post-operative recovery trajectories. In this study, we sought to establish the safety profile for ‘interventional neurorehabilitation’: connectome-based therapeutic brain stimulation to drive cortical reorganisation and promote functional recovery post-craniotomy. In n = 34 glioma patients who experienced post-operative motor or language deficits, we used connectomics to construct single-subject cortical networks. Based on their clinical and connectivity deficit, patients underwent network-specific transcranial magnetic stimulation (TMS) sessions daily over five consecutive days. Patients were then assessed for TMS-related side effects and improvements. 31/34 (91%) patients were successfully recruited and enrolled for TMS treatment within two weeks of glioma surgery. No seizures or serious complications occurred during TMS rehabilitation and 1-week post-stimulation. Transient headaches were reported in 4/31 patients but improved after a single session. No neurological worsening was observed while a clinically and statistically significant benefit was noted in 28/31 patients post-TMS. We present two clinical vignettes and a video demonstration of interventional neurorehabilitation. For the first time, we demonstrate the safety profile and ability to recruit, enroll, and complete TMS acutely post-craniotomy in a high seizure risk population. Given the lack of randomisation and controls in this study, prospective randomised sham-controlled stimulation trials are now warranted to establish the efficacy of interventional neurorehabilitation following craniotomy.

Eigenvector PageRank difference as a measure to reveal topological characteristics of the brain connectome for neurosurgery

PURPOSE

Applying graph theory to the human brain has the potential to help prognosticate the impacts of intracerebral surgery. Eigenvector (EC) and PageRank (PR) centrality are two related, but uniquely different measures of nodal centrality which may be utilized together to reveal varying neuroanatomical characteristics of the brain connectome.

METHODS

We obtained diffusion neuroimaging data from a healthy cohort (UCLA consortium for neuropsychiatric phenomics) and applied a personalized parcellation scheme to them. We ranked parcels based on weighted EC and PR, and then calculated the difference (EP difference) and correlation between the two metrics. We also compared the difference between the two metrics to the clustering coefficient.

RESULTS

While EC and PR were consistent for top and bottom ranking parcels, they differed for mid-ranking parcels. Parcels with a high EC centrality but low PR tended to be in the medial temporal and temporooccipital regions, whereas PR conferred greater importance to multi-modal association areas in the frontal, parietal and insular cortices. The EP difference showed a weak correlation with clustering coefficient, though there was significant individual variation.

CONCLUSIONS

The relationship between PageRank and eigenvector centrality can identify distinct topological characteristics of the brain connectome such as the presence of unimodal or multimodal association cortices. These results highlight how different graph theory metrics can be used alone or in combination to reveal unique neuroanatomical features for further clinical study.