Resting connectivity predicts task activation in pre-surgical populations

Abstract

Injury and disease affect neural processing and increase individual variations in patients when compared with healthy controls. Understanding this increased variability is critical for identifying the anatomical location of eloquent brain areas for pre-surgical planning. Here we show that precise and reliable language maps can be inferred in patient populations from resting scans of idle brain activity. We trained a predictive model on pairs of resting-state and task-evoked data and tested it to predict activation of unseen patients and healthy controls based on their resting-state data alone. A well-validated language task (category fluency) was used in acquiring the task-evoked fMRI data. Although patients showed greater variation in their actual language maps, our models successfully learned variations in both patient and control responses from the individual resting-connectivity features. Importantly, we further demonstrate that a model trained exclusively on the more-homogenous control group can be used to predict task activations in patients. These results are the first to show that resting connectivity robustly predicts individual differences in neural response in cases of pathological variability.

Regression‐based machine‐learning approaches to predict task activation using resting‐state fMRI

“…The correlation between actual and predicted activation was compared across models with a repeated‐measures analysis of variance (ANOVA). Maps were also thresholded for each subject and modeled separately using a mixture model consisting of a Gaussian and two gamma functions (Jones et al, ), and the DC was computed (Equation (3)). The median of the upper gamma was used as the threshold.…”

“…Recent work has shown that resting‐state fMRI (rs‐fMRI) can be used to predict task activation on an individual basis by fitting a general linear model (GLM), where resting‐state network components are mapped to task activation (Parker Jones, Voets, Adcock, Stacey, & Jbabdi, ; Tavor et al, ). These studies work under the assumption that although underlying similarities exist between individuals’ brain responses to certain tasks, these responses differ across subjects in specific, predictable ways.…”

“…They also were able to accurately predict language lateralization. In a follow‐up study, a GLM was used to predict task activation in a clinical population with lower spatial and temporal resolution data (Parker Jones et al, ). Using a covert category fluency task, they were able to accurately predict patients’ activation using a model trained on a group of healthy control subjects.…”

Mapping language with resting‐state functional magnetic resonance imaging: A study on the functional profile of the language network

“…Through methods such as seedbased correlation (Fox et al, 2005) or independent component analyses (Beckmann, DeLuca, Devlin, & Smith, 2005;Damoiseaux et al, 2006), patterns of co-activation can be identified, extracted and used to map well-known networks such as the fronto-parietal network (FPN), the default mode network (DMN) and the language network (Shirer, Ryali, Rykhlevskaia, Menon, & Greicius, 2011). Even though the subject is not performing a task, the obtained mapping results are replicable over time (Branco, Seixas, & Castro, 2018;Shehzad et al, 2009) and consistent across subjects (Damoiseaux et al, 2006), track major cognitive functions (Laird et al, 2011;Smith et al, 2009) and even predict individual task performance (Parker Jones, Voets, Adcock, Stacey, & Jbabdi, 2017;Tavor et al, 2016).…”

Transient spectral events in resting state MEG predict individual time-frequency task responses

“…Potentially, this might be very useful in a clinical setting. For fMRI, the potential clinical usefulness of task-free neuroimaging has already been demonstrated by predicting the location of language-relevant areas in patients from rest and its feasibility for pre-surgical planning (Parker Jones, Voets, Adcock, Stacey, & Jbabdi, 2017). This suggests that something similar might be achieved with M/EEG in a clinical context.…”