Building Multivariate Molecular Imaging Brain Atlases Using the NeuroMark PET Independent Component Analysis Framework.

Molecular imaging analyses using positron emission tomography (PET) data often rely on macro-anatomical regions of interest (ROI), which may not align with chemo-architectural boundaries and obscure functional distinctions. While methods such as independent component analysis (ICA) have been useful to address this limitation, the fully data-driven nature can make it challenging to compare results across studies. Here, we introduce the NeuroMark PET approach, utilizing spatially constrained independent component analysis to define overlapping regions that may reflect the brain's molecular architecture. We first generate an ICA template for the PET radiotracer florbetapir (FBP), targeting amyloid-β (Aβ) accumulation in the brain, using blind ICA on large datasets to identify replicable independent components. Only components that targeted Aβ were included in this study, defined as Aβ networks (AβNs), by omitting components targeting myelin or other non-Aβ targets. Next, we use the AβNs as priors for spatially constrained ICA, resulting in a fully automated ICA pipeline called NeuroMark PET. This NeuroMark pipeline, including its AβNs, was validated against a standard neuroanatomical PET atlas, using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). The study included 296 cognitively normal participants with FBP PET scans and 173 with florbetaben (FBB) PET scans, an analogue radiotracer also targeting Aβ accumulation. Our results show that NeuroMark PET captures biologically meaningful, participant-specific features, such as subject specific loading values, consistent across individuals, and also shows higher sensitivity and power for detecting age-related changes compared to traditional atlas-based ROIs. Using this framework, we also highlight some of the advantages of using ICA analysis for PET data. In this study, an AβN consists of weighted voxels and forms a pattern throughout the entire brain. For example, components may have weighted values at every voxel and can overlap with one another, enabling the separation of artifacts which may coincide with the AβNs of interest. In addition, this approach allows for the differentiation, separating white matter components, which may overlap in complex ways with the AβNs, mainly residing in the neighboring gray matter. Results also showed that the most age associated AβN (representing the cognitive control network, CC1) exhibited a stronger association with age compared with macro-anatomical regions of interest. This may suggest that each NeuroMark FBP AβN represents a spatial network following chemo-architectural uptake with greater biological relevance compared with anatomical ROIs. In summary, the proposed NeuroMark PET approach offers a fully automated framework, providing accurate and reproducible brain AβNs. This approach enhances our ability to investigate the molecular underpinnings of brain function and pathology, offering an alternative to traditional ROI-based analyses.