Longitudinal Connectome Analyses following Low-Grade Glioma Neurosurgery: Implications for Cognitive Rehabilitation

Abstract

Abstract Aims Low-grade gliomas (LGG) slowly grow and infiltrate the brain's network architecture (the connectome). Unlike strokes that acutely damage the connectome, LGGs intricately remodel it, leading to varying deficits in executive function (i.e. attention, concentration, working memory). By longitudinally mapping the “mesoscale” architecture of the connectome, we may begin to systematically accelerate domain-general cognitive rehabilitation in LGG patients. In this study, we pursued the following aims: 1) track cognitive and connectome trajectories following LGG surgery, 2) determine optimal time period for cognitive rehabilitation, and 3) distinguish patients with perioperative predictors of long-term cognitive deficits (>1 year). Method With MRI and cognitive data from n=629 individuals across the lifespan, we first validated the structural, functional, and topological relevance of the multiple demand (MD) system for higher-order cognition. Next, in n=17 patients undergoing glioma surgery, we longitudinally acquired connectome and cognitive data: pre-surgery, post-surgery Day 1, Month 3, & 12. We assessed how glioma infiltration, surgery, and rehabilitation affected MD system trajectories at the single-subject level. Deploying transcriptomic and graph theoretical analyses, we tested if perioperative connectome modularity can accurately distinguish long-term cognitive trajectories. Results Controlling for age and sex, the MD system’s multi-scale architecture in health was positively associated with higher-order cognition (Catell’s fluid intelligence). Pre-operative glioma infiltration into the MD system was negatively associated with the number of long-term cognitive deficits (OCS-Bridge cognitive battery), suggesting its functional reorganisation. Mixed-effects modelling demonstrated the resilience of the MD system to infiltration and resection, while the early post-operative period was critical for effective neurorehabilitation. Graph analyses revealed perioperative modularity can distinguish patients with long-term cognitive deficits at one-year follow-up. Transcriptomic analyses of inter-module connector hubs revealed increased gene expression for mitochondrial metabolism and synaptic plasticity. Conclusion This is the first serial functional mapping of LGG patient trajectories for domain-general cognition. By assessing the mesoscale architecture, we demonstrate how connectomics can help overcome the intrinsic heterogeneity in LGG patients and predict long-term rehabilitation trajectories. We discuss how to identify neurobiologically-grounded personalised targets for 'interventional neurorehabilitation' following LGG surgery.