The value of arterial spin labelling perfusion MRI in brain age prediction

Abstract

Current structural MRI‐based brain age estimates and their difference from chronological age—the brain age gap (BAG)—are limited to late‐stage pathological brain‐tissue changes. The addition of physiological MRI features may detect early‐stage pathological brain alterations and improve brain age prediction. This study investigated the optimal combination of structural and physiological arterial spin labelling (ASL) image features and algorithms. Healthy participants (n = 341, age 59.7 ± 14.8 years) were scanned at baseline and after 1.7 ± 0.5 years follow‐up (n = 248, mean age 62.4 ± 13.3 years). From 3 T MRI, structural (T1w and FLAIR) volumetric ROI and physiological (ASL) cerebral blood flow (CBF) and spatial coefficient of variation ROI features were constructed. Multiple combinations of features and machine learning algorithms were evaluated using the Mean Absolute Error (MAE). From the best model, longitudinal BAG repeatability and feature importance were assessed. The ElasticNetCV algorithm using T1w + FLAIR+ASL performed best (MAE = 5.0 ± 0.3 years), and better compared with using T1w + FLAIR (MAE = 6.0 ± 0.4 years, p < .01). The three most important features were, in descending order, GM CBF, GM/ICV, and WM CBF. Average baseline and follow‐up BAGs were similar (−1.5 ± 6.3 and − 1.1 ± 6.4 years respectively, ICC = 0.85, 95% CI: 0.8–0.9, p = .16). The addition of ASL features to structural brain age, combined with the ElasticNetCV algorithm, improved brain age prediction the most, and performed best in a cross‐sectional and repeatability comparison. These findings encourage future studies to explore the value of ASL in brain age in various pathologies.

Determinants of cerebral blood flow and arterial transit time in healthy older adults

“…Age-related CBF decline is well documented 4,18,19 but was not replicated in the present data (although a trend was observed). This is likely due to the limited age range (60–81 yrs), with 56% of participants aged ≤65 and only 17% aged ≥70.…”

“…8,9 Higher CBF has been linked with superior cognitive function in healthy older adults, [10][11][12][13][14] although not all studies converge. 12,[15][16][17] It is well established that CBF declines with age 4,18,19 and previous research in older adults has already identified some modifiable determinants of CBF. For example, CBF is reported to be greater in older adults who are physically active, [20][21][22] engage with social or leisure activities, 23 have a lower BMI, [24][25][26] have lower blood pressure, 19,26 or have more elastic arteries.…”

Developing blood-brain barrier arterial spin labelling as a non-invasive early biomarker of Alzheimer’s disease (DEBBIE-AD): a prospective observational multicohort study protocol

“…The normal variability of the BBB-ASL values ( RQ1C ) over age and sex will be investigated in 150 healthy participants from the Centre for Lifespan Changes in Brain and Cognition (LCBC) cohort to create an atlas of a healthy BBB across age groups and to investigate the ability of Tex to predict age above and beyond CBF and ATT 90. Previous studies examining the age and sex-related variability of CBF in healthy adults achieved significant and reliable results when including between 50 and 100 participants 91 92…”

Aging and Sex Differences in Brain Volume and Cerebral Blood Flow

“…The brain volume [1][2][3][4], and its association with the cerebral blood flow (CBF) [5][6][7][8][9][10][11][12][13][14], are gradually decreased with normal aging. Furthermore, patients with dementia have not only decreased pathological regional brain volume [15][16][17], but also abnormally decreased regional has been highlighted as the most important predictor of clinical outcome in patients with acute cerebral infarction due to the main cerebral artery occlusion [21,22].…”

“…Nuclear medicine examinations, such as 15 O-labeled water or gasinhalation positron emission tomography [10,23], and 123 I-iodoamphetamine single-photon emission computed tomography [24,25], were thought to be gold-standard imaging modalities used to estimate CBFs and collateral circulations; however, their resolution is lower than that of MRI sequences. Recently, the phase-contrast (PC) MRI and arterial spin labeling (ASL) MRI sequences have become widely used because it is a minimally invasive and simple method that quantifies CBF [5][6][7][8][9][12][13][14]. Moreover, 3D PC MRI, namely 4D flow MRI [11,19], has made it possible to measure 3D flow velocities of intracranial cerebral arteries with complex bends, twists, and branches.…”