MRI-free amyloid PET quantification using a deep learning model and white matter reference

Regional differences in 18F-flutemetamol accumulation between amyloid-positive and -negative brains using high-resolution dedicated head PET scanner.

High-resolution dhPET revealed significantly higher SUVRs in Aβ⁺ compared with Aβ⁻ subjects in supratentorial structures, including cerebral white matter, and in cerebellar gray matter.

[18F]FDG PET outperforms MRI for detecting early tau-related neurodegeneration.

Brain Amyloid Burden Mapping Using MR Fingerprinting Aided by Deep Learning.

PURPOSE To develop and externally validate a non-invasive framework for quantifying brain amyloid-β (Aβ) deposition using magnetic resonance fingerprinting (MRF) and neural network-based decoding, with positron emission tomography (PET) as the reference standard. METHODS This prospective multi-site study included 44 participants from 2 sites who had undergone, or were scheduled to undergo, Aβ PET within 1 year. MRF was performed on a 3T MR system using a 2D fast imaging with steady-state precession sequence with B1 correction, covering the whole brain in 9.5 min. PET images were co-registered to the MRF space, and regional amyloid load was calculated using an automated template-based pipeline. An inverse mapping function was implemented to convert MRF signals into amyloid burden maps. Repeatability, agreement with PET-based centiloid values, and associations with cognitive scores were evaluated. RESULTS The generated amyloid maps were visually similar to PET images. Test-retest analysis showed high repeatability, with a coefficient of variation of 1.8 ± 1.3% and an intraclass correlation coefficient of 0.84. In the external test set, MRF-based measurements correlated significantly with PET centiloid scores (Spearman's ρ = 0.589, P = 0.015) and Montreal Cognitive Assessment scores (ρ = -0.543, P = 0.020). CONCLUSION The proposed framework enables non-invasive Aβ mapping using a clinically feasible MRI protocol and may support repeated assessment for monitoring during anti-amyloid treatment.

Binary classification of 18 F-flutemetamol PET using machine learning: comparison with visual reads and structural MRI

Identification of MRI-Derived Structural Biomarkers in Female Alzheimer’s Disease Subjects Using CAT12 and Mimics: Effects of Voxel Geometry on Biomarker Estimation

Alzheimer’s disease (AD) is the leading cause of dementia and disproportionately affects women, who experience a higher lifetime risk and more rapid structural brain changes than men. Reliable imaging biomarkers are essential for detecting these changes, although their estimation may be influenced by voxel geometry, image resolution, and segmentation methodology. In this study, magnetic resonance imaging (MRI) scans from 40 female participants with AD obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database were analyzed using the Computational Anatomy Toolbox 12 (CAT12), implemented within Statistical Parametric Mapping 12 (SPM12), and Materialise Mimics to identify structural biomarkers associated with neurodegeneration. Cortical thickness, gray matter (GM), white matter (WM), cerebrospinal fluid (CSF), and total intracranial volume (TIV) were quantified, while Brain Parenchymal Volume (BPV) and Brain Parenchymal Fraction (BPF) were calculated to assess global brain tissue preservation. The analyses demonstrated characteristic AD-related changes, including cortical thinning, GM loss, ventricular enlargement, and increased CSF volume. Significant correlations among cortical thickness, tissue volumes, BPV, and BPF further supported their complementary role in characterizing disease-related structural changes. Overall, these findings suggest that MRI-derived measures of cortical thickness, tissue volumes, BPV, and BPF provide useful structural biomarkers of AD and emphasize the importance of considering voxel geometry and segmentation methodology when evaluating neuroimaging biomarkers.

Structural MRI signature predicts tau staging in Alzheimer's disease

Abstract INTRODUCTION Tau positron emission tomography (PET) probes Alzheimer's disease (AD) severity via regional tau spread but is not widely available. We tested whether multiregion structural magnetic resonance imaging (MRI) could approximate individual tau burden. METHODS We studied 378 Alzheimer's Disease Neuroimaging Initiative (ADNI) participants with mild cognitive impairment (MCI)‐AD or AD dementia with paired T1‐MRI and [18F]flortaucipir tau‐PET (≤6 months apart). Regional cortical thickness and volume were extracted with FreeSurfer. Principal component analysis and multivariable linear regression yielded MRI signatures of tau‐PET standardized uptake value ratio (SUVR) in Braak composite regions (I, III–IV, V–VI), a meta‐temporal region of interest (ROI), and a global neocortical meta‐ROI. Performance and high/low tau classification were evaluated by leave‐one‐out cross‐validation against published cut‐offs. RESULTS MRI signatures were significantly associated with tau‐PET burden across all regions (p < 0.001). High‐versus‐low tau discrimination varied: AUC ≈ 0.70 in Braak I, ≈0.89 in Braak V–VI, and ≈0.90 globally. Discussion Here we provide proof‐of‐concept evidence that multiregion T1‐MRI patterns can inform on tau‐PET burden in AD and may support approximate tau staging when tau‐PET is unavailable, especially in subjects with more advanced tau burden.