Satpathi, Siddhartha

Abstract Background Brain age models are increasingly being used as measures of brain health and neurodegeneration. These models can be deep learning (DL) based and/or classical methods and provide a brain age gap (BAG) which is the difference between chronological and predicted brain age. Our goal was to develop DL‐based scanner invariant brain age models that can be applied in aging and dementia studies even when there are scanner changes that may hinder longitudinal follow‐up. Method We identified 3374 cognitively unimpaired (CU) participants with T1 scans from the Mayo Clinic Study of Aging (MCSA). A subset of 863 CU amyloidosis negative (PiB‐PET cutoff < 25 Centiloid) and no history of diabetes and hypertension was selected (CU‐noVAβ). We built two models – Model‐A trained on CU‐noVAβ, and Model‐B trained on all CU. We included 453 MCSA MCI participants as test set for both models. We used 113 participants (74 CU, 28 MCI, 10 dementia) from MCSA and Mayo ADRC with scans from two different vendors (scanned within a week of each other) for testing cross‐vendor/scanner differences (cross‐vendor data). The two unique features of our model included histogram matching and scanner type as an input to the DenseNet model for training (Figure 1). Result In the data, the inclusion of scanner as an input decreased the prediction of mean age differences between the scanners (Model‐A=2.17 years; Model‐B=1.71 years) (Figure 2). The mean absolute error (MAE=absolute value of BAG) for Model‐A in MCI was 5.72 years and Model‐B in MCI was 4.06 years, consistent across scanners (Figure 3). Longitudinal prediction increased with age (Model‐A slope=0.53; Model‐B slope=0.63). Conclusion We found that training on all CU (Model B) rather than a subset CU‐noVAβ (Model A) allowed for the DenseNet model to backpropagate on more variable data which lowered MAE in prediction error between scanners and lowered MAE for MCIs. Histogram matching and scanner as an input to the brain age model accounted for scanner changes and resulted in scanner invariant longitudinal brain age estimation.

Abstract Background Diffusion tensor imaging along perivascular spaces index (DTI‐ALPS), which measures diffusivity increases in the perivascular spaces along the medullary veins, is being increasingly utilized as a surrogate marker of glymphatic clearance (Taoka et. al. Jpn J Radio 2017). Lower DTI‐ALPS index means higher measured diffusivity from the perivascular space, and so it is expected to decrease with age. However, correlation with aging and dementia markers have not been systematically evaluated. The goal of this work was to automatically estimate DTI‐ALPS in a large sample and evaluate the variance explained by various demographic and imaging markers. Methods We identified 2739 participants aged 30+ years (mean 69.6, 48% female, 88% CU) in the population‐based Mayo Clinic Study of Aging with diffusion MRI. We estimated DTI‐ALPS through automated placement of regions as published previously (Liu et al. AAIC 2023) and shown in Figure 1. We examined the associations of DTI‐ALPS with demographics (age, sex), vascular risk (cardiovascular and metabolic condition score), clinical data (diagnosis, global cognition) and imaging markers (white matter hyperintensity (WMH), global amyloid load from PIB‐PET, and the temporal meta‐ROI Tau‐PET SUVR) using partial Pearson correlations and ANCOVA with adjustments for age and sex. Results DTI‐ALPS was negatively correlated with age, higher in females, declined with vascular risk, and lower in MCI/dementia groups (Figure 2). Higher WMH and higher amyloid were associated with lower DTI‐ALPS whereas Tau‐PET SUVR was not associated with DTI‐ALPS. Conclusions DTI‐ALPS can be automatically computed in large samples. Vascular risk and WMH had stronger associations with the computed DTI‐ALPS compared to AD biomarkers (amyloid and tau) suggesting that the surrogate was more likely linked to vascular injury.