Virtual brain twins: from basic neuroscience to clinical use

Abstract

Virtual brain twins are personalized, generative and adaptive brain models based on data from an individual's brain for scientific and clinical use. After a description of the key elements of virtual brain twins, we present the standard model for personalized whole-brain network models. The personalization is accomplished using a subject's brain imaging data by three means: (1) assemble cortical and subcortical areas in the subject-specific brain space; (2) directly map connectivity into the brain models, which can be generalized to other parameters; and (3) estimate relevant parameters through model inversion, typically using probabilistic machine learning. We present the use of personalized whole-brain network models in healthy ageing and five clinical diseases: epilepsy, Alzheimer's disease, multiple sclerosis, Parkinson's disease and psychiatric disorders. Specifically, we introduce spatial masks for relevant parameters and demonstrate their use based on the physiological and pathophysiological hypotheses. Finally, we pinpoint the key challenges and future directions.

Keywords: brain disorder; inference; neuroscience; personalized modeling; virtual brain twin.

Figure 1.

The key elements of virtual brain twins. The brain activity, denoted ψ at position x at time t, of virtual brain twins can be computed using model F and the set of control parameters {k}. Simulated brain activity data are mapped on sensor data through the forward solution O. We map real-world data D, observed in the human brain, onto the space of the virtual brain and personalize its control parameters k. Clinical interventions represent any external operation capable of influencing the brain dynamics. Virtual brain twins generate predictions by simulating under various conditions.

Figure 2.

The spatial masks of six clinical uses and their control parameters {k} = {e_i, β_i, G_ij, τ_ij, η_ij, σ_i}. (a) In epilepsy, the control parameter set is composed of regional excitability e_i of the local dynamics. The nodes in red with high e_i belong to an epileptogenic network. (b) In Alzheimer’s disease, the control parameter set is composed of the regional parameter β_i of the local dynamics. The nodes in different colors and sizes show that β_i depends on amyloid β or tau depositions (Braak stages). (c) In ageing, the control parameter set is composed of the structural connectivity G_ij, illustrated by the network links in white. (d) In multiple sclerosis, the control parameter set is composed of time delays τ_ij. The affected links are colored blue. (e) In Parkinson’s disease, the control parameter set is the link weight η_ij imposed to link from region i to region j. The affected links are illustrated in blue and the affected nodes in red represent the basal ganglia-thalamocortical circuit. (f) In schizophrenia, the control parameter set is composed of both the link weight η_ij and the regional parameter σ_i. The affected links are illustrated in blue and the regional parameter σ_i in different colors is determined by the balance of excitation and inhibition of region i.

Figure 3.

A workflow of a virtual brain twin in epilepsy: virtual epileptic patient (VEP). In the middle is a personalized whole-brain network model, defined by the network of regions. The computational neuronal source activity model in Equation 2 works on each brain region (blue and red spheres) defined by the VEP atlas. The brain regions are connected through the connectome (yellow lines). The brain geometry data from T1-MRI defined distinct brain regions according to the VEP atlas. Tractography was used to estimate the length and density of white matter fibres from DW-MRI (yellow lines in the virtual brain model), which establishes the connectome that specifies the connection strength and time delays via signal propagation between two brain regions. The control parameter {k} is the excitability of brain region e_i. The probabilistic machine learning methods are able to obtain the control parameters from SEEG, EEG or MEG. The healthy regions are shown as blue squares and epileptogenic networks as red squares. The VEP can be used for epileptogenic network estimation, virtual surgery and virtual stimulation.