Radiomics-Derived Brain Age Predicts Functional Outcome After Acute Ischemic Stroke

Abstract

Background and Objectives:While chronological age is one of the most influential determinants of post-stroke outcomes, little is known of the impact of neuroimaging-derived biological “brain age”. We hypothesized that radiomics analyses of T2-FLAIR images texture would provide brain age estimates and that advanced brain age of stroke patients will be associated with cardiovascular risk factors and worse functional outcomes.Methods:We extracted radiomics from T2-FLAIR images acquired during acute stroke clinical evaluation. Brain age was determined from brain parenchyma radiomics using an ElasticNet linear regression model. Subsequently, relative brain age (RBA), which expresses brain age in comparison to chronological age-matched peers, was estimated. Finally, we built a linear regression model of RBA using clinical cardiovascular characteristics as inputs, and a logistic regression model of favorable functional outcomes taking RBA as input.Results:We reviewed 4,163 patients from a large multisite ischemic stroke cohort (mean age=62.8 years, 42.0% females). T2-FLAIR radiomics predicted chronological ages (mean absolute error=6.9 years, r=0.81). After adjustment for covariates, RBA was higher and therefore described older-appearing brains in patients with hypertension, diabetes mellitus, a history of smoking, and a history of a prior stroke. In multivariate analyses, age, RBA, NIHSS, and a history of prior stroke were all significantly associated with functional outcome (respective adjusted Odds-Ratios: 0.58, 0.76, 0.48, 0.55; all p-values<0.001). Moreover, the negative effect of RBA on outcome was especially pronounced in minor strokes.Discussion:T2-FLAIR radiomics can be used to predict brain age and derive RBA. Older appearing brains, characterized by a higher RBA, reflect cardiovascular risk factor accumulation and are linked to worse outcomes after stroke.

Association of Brain Atrophy With Functional Outcome and Recovery Trajectories After Thrombectomy

“…The latter was specifically adapted to the acute stroke setting, minimizing contamination by ipsilateral AIS-induced edema or hemorrhage. 21 Such pragmatic use of simple, readily available measures on routinely acquired imaging without the need for postprocessing, as opposed to advanced imaging features involving volumetrics 14 or radiomics, 26 further corroborates the clinical relevance of our study.…”

“…White matter lesions were rated through visual assessment using the Fazekas scale, 23 adopted to NCCT, which has been performed previously. 24-26 Both periventricular and deep Fazekas scores were combined to generate a “total white matter disease (WMD)-burden score.” To avoid interference with acute ischemic lesions, assessments were performed on the contralateral hemisphere.…”

Dopaminergic mesolimbic structural reserve is positively linked to better outcome after severe stroke

“…the pre-morbid state of the brain, have been successfully linked to outcome variability. Examples are relative brain age 15-17 or more directly accessible estimates of brain health, such as white matter hyperintensity burden or the degree of brain atrophy. 18-20 Besides these global parameters, other studies have focused on measures of focal structural brain reserve of distinct regions, such as the cerebellum 21 or the cortex of the contralesional hemisphere.…”

Application of radiomics in ischemic stroke

“…To predict the probability of stroke based on risk factors, Bretzner et al 26 asymptomatic lacunar infarction patients using radiomic feature extraction from CT images; they identified that factors including age, blood lipids, and multiple infarctions were independently associated with future ischemic stroke. 27 When considering the diagnosis of stroke at an early stage, evidence supports the benefits of intravenous tissue plasminogen activator administration within 4.5 hours after symptom onset in ischemic stroke patients.…”

“…To predict the probability of stroke based on risk factors, Bretzner et al. 26 proposed predicting stroke risk using the relative brain age, derived from T2-fluid-attenuated inversion recovery images acquired during acute stroke clinical assessments. These authors established that T2-fluid-attenuated inversion recovery-related radiomic features can be used to predict brain age and calculate relative brain age; the predicted brain age then serves as an indicator of cumulative cardiovascular risk factors and post-stroke outcomes.…”