The Advanced Normalizations Tools ecosystem, known as ANTsX, consists of multiple open- source software libraries which house top-performing algorithms used worldwide by scientific and research communities for processing and analyzing biological and medical imaging data. The base software library, ANTs, is built upon, and contributes to, the NIH-sponsored Insight Toolkit. Founded in 2008 with the highly regarded Symmetric Normalization image registration framework, the ANTs library has since grown to include additional functionality. Recent enhancements include statistical, visualization, and deep learning capabilities through interfacing with both the R statistical project (ANTsR) and Python (ANTsPy). Additionally, the corresponding deep learning extensions ANTsRNet and ANTsPyNet (built on the popular TensorFlow/Keras libraries) contain several popular network architectures and trained models for specific applications. One such comprehensive application is a deep learning analog for generating cortical thickness data from structural T1-weighted brain MRI. Not only does this significantly improve computational efficiency and provide comparable-to-superior accuracy over the existing ANTs pipeline but it also illustrates the importance of the comprehensive ANTsX approach as a framework for medical image analysis.

Plasma biomarkers of amyloid, tau, and neurodegeneration (ATN) need to be characterized in cognitively unimpaired (CU) elderly indviduals. We therefore tested if plasma measurements of amyloid-β (Aβ)42/40, phospho-tau217 (P-tau217), and neurofilament light (NfL) together predict clinical deterioration in 435 CU individuals followed for an average of 4.8 ±1.7 years in the BioFINDER study. A combination of all three plasma biomarkers and basic demographics best predicted change in the cognition (Pre-Alzheimer’s Clinical Composite; R2=0.14, 95% CI [0.12-0.17]; P<0.0001) and subsequent AD dementia (AUC=0.82, 95% CI [0.77-0.91], P<0.0001). In a simulated clinical trial, a screening algorithm combining all three plasma biomarkers would reduce the required sample size by 70% (95% CI [54-81]; P<0.001) with cognition as trial endpoint, and by 63% (95% CI [53-70], P<0.001) with subsequent AD dementia as trial endpoint. Plasma ATN biomarkers show usefulness in cognitively unimpaired populations and could make large clinical trials more feasible and cost-effective.

Objective: Shorter Aβ species might modulate disease progression in Alzheimer's disease (AD). Here we studied whether Aβ38 levels in cerebrospinal fluid (CSF) are associated with risk of developing AD dementia and cognitive decline. Methods: CSF Aβ38 levels were measured in 656 individuals across two clinical cohorts - the Swedish BioFINDER study and the Alzheimer's Disease Neuroimaging Initiative (ADNI). Cox regression models were used to evaluate the association between baseline Aβ38 levels and risk of AD dementia in AD-biomarker positive individuals (AD+; determined by CSF P-tau/Aβ42 ratio) with subjective cognitive decline (SCD) or mild cognitive impairment (MCI). Linear mixed effects models were used to evaluate the association between baseline Aβ38 levels and cognitive decline as measured by MMSE in AD+ participants with SCD, MCI or AD dementia. Results: In the BioFINDER cohort, high Aβ38 levels were associated with slower decline in MMSE (β = 0.30 points / sd., P = 0.001) and with lower risk of conversion. To AD dementia (HR = 0.83 per sd., P = 0.03). In the ADNI cohort, higher Aβ38 levels were associated with less decline in MMSE (β = 0.27, P = 0.01), but not risk of conversion to AD dementia (P = 0.66). Aβ38 levels in both cohorts remained significantly associated with both outcomes when adjusted for CSF P-tau levels and remained associated with cognition when adjusted for CSF Aβ42 levels. Conclusions: Higher CSF Aβ38 levels are associated with lower risk of AD-related changes in two independent clinical cohorts. These findings may have implications for γ-secretase modulators as potential disease-altering therapy.