Individual-Level Lesion-Network Mapping to Visualize the Effects of a Stroke Lesion on the Brain Network: Connectograms in Stroke Syndromes

Abstract

Background and purpose: Similar-sized stroke lesions at similar locations can have different prognoses in clinical practice. Lesion-network mapping elucidates network-level effects of lesions that cause specific neurologic symptoms and signs, and also provides a group-level understanding. This study visualized the effects of stroke lesions on the functional brain networks of individual patients.

Methods: We enrolled patients with ischemic stroke who were hospitalized within 1 week of the stroke occurrence. Resting-state functional magnetic resonance imaging was performed 3 months after the index stroke. For image preprocessing, acute stroke lesions were visually delineated based on diffusion-weighted images obtained at admission, and the lesion mask was drawn using MRIcron software. Correlation matrices were calculated from 280 brain regions using the Brainnetome Atlas, and connectograms were visualized using in-house MATLAB code.

Results: We found characteristic differences in connectograms between pairs of patients who had comparable splenial, frontal cortical, cerebellar, and thalamocapsular lesions. Two representative patients with bilateral thalamic infarctions showed significant differences in their reconstructed connectograms. The cognitive function had recovered well at 3 months after stroke occurrence in patients with well-maintained interhemispheric and intrahemispheric connectivities.

Conclusions: This pilot study has visualized the effects of stroke lesions on the functional brain networks of individual patients. Consideration of the neurobiologic mechanisms underlying the differences between their connectograms has yielded new hypotheses about differences in the effects of stroke lesions.

Keywords: cerebral infarction; connectome; functional neuroimaging; magnetic resonance imaging.

Fig. 1. Representative functional connectivity patterns from patients 1 and 2. The left and right sides of each circle represent the left and right brain hemispheres, respectively. The parcellated cortical area is defined outside the circle. Lesions are shown in black on the innermost circle. Representative network attributes are shown at each point on the circle, and the connectivity of each part is visualized by a line inside the circle. The presence or absence of a line indicates the presence or absence of suprathreshold functional connections, and the thickness of the line indicates the strength of the connection. To reduce noise and find meaningful connections, the global threshold density was set to the highest 1% of values of the network density.

Fig. 2. Comparison of the connectograms of representative patients. Index-stroke lesions are shown in red on the standard template.