Deep generative computed perfusion-deficit mapping of ischaemic stroke

TL;DR

This paper introduces a deep generative inference method to analyze CT angiography-derived perfusion maps in acute ischemic stroke, enabling early prediction of neural deficits and revealing neural substrates without relying on lesion data.

Contribution

The study presents a novel deep generative approach that localizes neural substrates of stroke deficits from perfusion maps, outperforming traditional lesion-based predictions.

Findings

Replicates known lesion-deficit relations

Reveals novel neural dependents

Achieves high anatomical fidelity

Abstract

Focal deficits in ischaemic stroke result from impaired perfusion downstream of a critical vascular occlusion. While parenchymal lesions are traditionally used to predict clinical deficits, the underlying pattern of disrupted perfusion provides information upstream of the lesion, potentially yielding earlier predictive and localizing signals. Such perfusion maps can be derived from routine CT angiography (CTA) widely deployed in clinical practice. Analysing computed perfusion maps from 1,393 CTA-imaged-patients with acute ischaemic stroke, we use deep generative inference to localise neural substrates of NIHSS sub-scores. We show that our approach replicates known lesion-deficit relations without knowledge of the lesion itself and reveals novel neural dependents. The high achieved anatomical fidelity suggests acute CTA-derived computed perfusion maps may be of substantial clinical-and-scientific value in rich phenotyping of acute stroke. Using only hyperacute imaging, deep generative inference could power highly expressive models of functional anatomical relations in ischaemic stroke within the pre-interventional window.