Preliminary Validation of a Structural Magnetic Resonance Imaging Metric for Differential Diagnosis of Frontotemporal Lobe Dementias.

Background: AD‐NeuroScore is a validated metric that summarizes Alzheimer’s disease (AD)‐specific atrophy and can detect AD early, benchmark disease severity, predict and monitor AD progression, and can aid in testing the efficacy of therapeutic interventions using a single number (Kress, 2023). It meets criteria for translatability by using clinically available regional brain volumes as input (Ahdidan, 2015; Cavedo, 2022) and having patient and model‐level interpretability (Pinto, 2022). Also, features can be reviewed by a neuroradiologist (Larson, 2019).

Gray Matter Alterations Associated with Aging & APOEε4 Genotype in 37,437 Participants from the UK Biobank.

Background: Carrying one or more copies of the apolipoprotein E ε4 allele represents the greatest known source of genetic risk for late‐onset Alzheimer’s disease (AD), although the mechanisms are not fully understood. Several smaller‐scale studies have analyzed APOEε4 effects on brain volume, reporting gray matter volume (GMV) alterations in medial temporal and precuneal regions in people with AD and in healthy APOEε4 carriers. Here, we analyzed brain images from a large sample of healthy elderly adults in relation to ε4 carrier status, stratifying by age to assess potential group differences.

Harmonized Tractometry Visualizes Alzheimer’s Disease Effects on the Brain’s White Matter Tract Microstructure.

Background: Diffusion MRI (dMRI) metrics of brain microstructure offer valuable insight into Alzheimer’s disease (AD) pathology; recent reports have identified dMRI metrics that (1) tightly link with CSF or PET measures of amyloid and tau burden; and (2) mediate the relationship between CSF markers of AD and delayed logical memory performance, commonly impaired in early AD [1,2]. To better localize white matter tract disruption in AD, our BUndle ANalytic (BUAN) [3] tractometry pipeline allows principled use of statistical methods to map factors affecting microstructural metrics along the 3D length of the brain’s fiber tracts. Here, we extended BUAN to pool data from multiple scanning protocols/sites ‐ using a new approach, based on ComBat [4,5], a widely‐used harmonization method modeling variations in multi‐site datasets due to site‐ and scanner‐specific effects.

A novel fMRI memory paradigm designed for brain imaging studies in early Alzheimer’s Disease.

Background: We present the results of a task‐based fMRI study in early Alzheimer’s disease (mild cognitive impairment, MCI and mild Alzheimer’s disease, AD) using a novel‐fMRI memory paradigm suitable for use in patients with significant cognitive impairment having difficulties with remembering complex instructions.

Method: The study samples comprised 65 patients with early AD(MCI n = 42; 21 males; mild AD n = 23; 16 males) and 26(14 males) elderly cognitively healthy control(eCHC) participants. The incidental encoding phase of the paradigm (7 minutes) comprised 110 trials of common objects (55 living and 55 non‐living trials which included 4 objects repeated 6 times each and 1 object repeated 5 times) while the intentional retrieval phase of the paradigm (7 minutes) comprised 55 trials of the 5 objects encoded during the previous phase(repeated 11 times each), and 55 new objects.

‘Diet’ deep canonical correlation analysis for high‐dimensional genetics study of brain imaging phenotypes in Alzheimer’s disease.

Background: Understanding the relationship between genetic variations and brain imaging phenotypes is an important issue in Alzheimer's disease (AD) research. As an alternative to GWAS univariate analyses, canonical correlation analysis (CCA) and its deep learning extension (DCCA) are widely used to identify associations between multiple genetic variants such as SNPs and multiple imaging traits such as brain ROIs from PET/MRI. However, with the recent availability of numerous genetic variants from genotyping and whole genome sequencing data for AD, these approaches often suffer from severe overfitting when dealing with ‘fat’ genetics data, e.

Interpretable Deep Clustering Survival Machines for Alzheimer's Disease Risk Groups Discovery.

Background: Alzheimer's disease (AD) is a complex neurodegenerative disorder that has impacted millions of people worldwide. Identifying different risk groups converting to AD during the mild cognitive impairment (MCI) stage and determining their genetic basis would be immensely valuable for drug discovery and subsequent clinical treatment. Previous studies typically clustered subgroups by unsupervised learning techniques, neglecting the survival information.

Large‐scale Normative Modeling of Brain Microstructure over the Human Lifespan.

Background: Normative models (NM) of brain metrics based on large, diverse populations offer novel strategies to detect individual brain abnormalities. To create an age‐dependent statistical model of brain microstructure over the human lifespan, we built the largest multi‐site NM of white matter (WM) diffusion tensor imaging (DTI) metrics based on 54,591 subjects. We used state‐of‐the‐art tools to adjust for site‐dependent effects.

Deep Learning Algorithms for Alzheimer’s Disease Detection based on Diffusion MRI: Tests in Indian and North American Cohorts.

Background: Deep learning models based on convolutional neural networks (CNNs) have been used to classify Alzheimer’s disease or infer dementia severity from T1‐weighted brain MRI. Here we tested the added value of incorporating information from 3D diffusion‐weighted MRI ‐ a technique sensitive to microstructural differences ‐ alongside traditional 3D T1‐weighted images. We evaluated our classifier’s performance on cohorts from India and North America.

Generative AI improves MRI‐based Detection of Alzheimer’s Disease by using Latent Diffusion Models and Convolutional Neural Networks.

Background: As new treatments (such as the anti‐amyloid vaccine, lecanamab) emerge for Alzheimer’s disease (AD) and other dementias, approaches are required to rapidly diagnose AD at the earliest possible stage, and to assess disease progression and prognosis. In January 2024, the FDA approved the first AI tool to predict AD progression based on magnetic resonance imaging (MRI) [1]. Here we train a generative AI approach based on latent diffusion models ‐ to encode disease effects on brain structures.

Body Mass Index and Brain Aging: Microstructural Effects Mapped with Advanced Diffusion MRI.

Background: High body mass index (BMI) is a risk factor for dementia, and prior diffusion‐weighted magnetic resonance (dMRI) work has shown that higher BMI is associated with lower white matter (WM) integrity. The tensor distribution function (TDF) is an advanced dMRI model that is sensitive to the effects of both healthy aging and Alzheimer’s disease (Nir et al., 2017; Lawrence et al.

Genetic associations with amyloid, tau, and neurodegeneration: an ADSP neuroimaging study.

Background: The amyloid‐tau‐neurodegeneration (ATN) framework provides a valuable model for comprehending the pathophysiology and progression of Alzheimer’s disease (AD). However the relationship between and genetic interaction with these three characteristics are complex and not fully understood. Here, we use neuroimaging‐derived quantitative traits to evaluate the genetic risk for amyloid accumulation, tau pathology, and neurodegeneration.

How Low Should We Go to Prevent Brain Aging Associated with Exposure to Ambient Fine Particles?

Background: Late‐life exposure to PM is a risk factor for Alzheimer’s disease (AD) and related dementias. Accelerated brain aging associated with PM exposure likely takes place at preclinical stage. In Feb.

Harmonized Tractometry Visualizes Alzheimer’s Disease Effects on the Brain’s White Matter Tract Microstructure.

Background: Diffusion MRI (dMRI) metrics of brain microstructure offer valuable insight into Alzheimer’s disease (AD) pathology; recent reports have identified dMRI metrics that (1) tightly link with CSF or PET measures of amyloid and tau burden; and (2) mediate the relationship between CSF markers of AD and delayed logical memory performance, commonly impaired in early AD [1,2]. To better localize white matter tract disruption in AD, our BUndle ANalytic (BUAN) [3] tractometry pipeline allows principled use of statistical methods to map factors affecting microstructural metrics along the 3D length of the brain’s fiber tracts. Here, we extended BUAN to pool data from multiple scanning protocols/sites ‐ using a new harmonized tractometry approach, based on ComBat [4,5], a widely‐used harmonization method modeling variations in multi‐site datasets due to site‐ and scanner‐specific effects.

A novel fMRI memory paradigm designed for brain imaging studies in early Alzheimer’s Disease.

Background: We present the results of a task‐based fMRI study in early Alzheimer’s disease(mild cognitive impairment, MCI and mild Alzheimer’s disease, AD) using a novel‐fMRI memory paradigm suitable for use in patients with significant cognitive impairment having difficulties with remembering complex instructions.

Method: The study samples comprised 65 patients with early AD(MCI n = 42; 21 males; mild AD n = 23; 16 males) and 26(14 males) elderly cognitively healthy control(eCHC) participants. The incidental encoding phase of the paradigm(7 minutes) comprised 110 trials of common objects(55 living and 55 non‐living trials which included 4 objects repeated 6 times each and 1 object repeated 5 times) while the intentional retrieval phase of the paradigm(7 minutes) comprised 55 trials of the 5 objects encoded during the previous phase(repeated 11 times each), and 55 new objects.

Large‐scale Normative Modeling of Brain Microstructure over the Human Lifespan.

Background: Normative models (NM) of brain metrics based on large, diverse populations offer novel strategies to detect individual brain abnormalities. To create an age‐dependent statistical model of brain microstructure over the human lifespan, we built the largest multi‐site NM of white matter (WM) diffusion tensor imaging (DTI) metrics based on 54,591 subjects. We used state‐of‐the‐art tools to adjust for site‐dependent effects.

Larger perivascular space volume fraction is associated with worse post-stroke sensorimotor outcomes: An ENIGMA analysis.

Background: Perivascular Spaces (PVS) are a marker of cerebral small vessel disease (CSVD) that are visible on brain imaging. Larger PVS has been associated with poor quality of life and cognitive impairment post-stroke. However, the association between PVS and post-stroke sensorimotor outcomes has not been investigated.

Predicting Antidepressant Treatment Response From Cortical Structure on MRI: A Mega-Analysis From the ENIGMA-MDD Working Group.

Accurately predicting individual antidepressant treatment response could expedite the lengthy trial-and-error process of finding an effective treatment for major depressive disorder (MDD). We tested and compared machine learning-based methods that predict individual-level pharmacotherapeutic treatment response using cortical morphometry from multisite longitudinal cohorts. We conducted an international analysis of pooled data from six sites of the ENIGMA-MDD consortium (n = 262 MDD patients; age = 36.

Microstructural mapping of neural pathways in Alzheimer's disease using macrostructure-informed normative tractometry.

Introduction: Diffusion-weighted magnetic resonance imaging (dMRI) is sensitive to the microstructural properties of brain tissues and shows great promise in detecting the effects of degenerative diseases. However, many approaches analyze single measures averaged over regions of interest without considering the underlying fiber geometry.

Methods: We propose a novel macrostructure-informed normative tractometry (MINT) framework to investigate how white matter (WM) microstructure and macrostructure are jointly altered in mild cognitive impairment (MCI) and dementia.

Negative valence in Obsessive-Compulsive Disorder: A worldwide mega-analysis of task-based functional neuroimaging data of the ENIGMA-OCD consortium.

Objective: Obsessive-compulsive disorder (OCD) is associated with altered brain function related to processing of negative emotions. To investigate neural correlates of negative valence in OCD, we pooled fMRI data of 633 individuals with OCD and 453 healthy controls from 16 studies using different negatively-valenced tasks across the ENIGMA-OCD Working-Group.

Methods: Participant data were processed uniformly using HALFpipe, to extract voxelwise participant-level statistical images of one common first-level contrast: negative vs.

Sex and APOE ε4 allele differences in longitudinal white matter microstructure in multiple cohorts of aging and Alzheimer's disease.

Introduction: The effects of sex and apolipoprotein E (APOE)-Alzheimer's disease (AD) risk factors-on white matter microstructure are not well characterized.

Methods: Diffusion magnetic resonance imaging data from nine well-established longitudinal cohorts of aging were free water (FW)-corrected and harmonized. This dataset included 4741 participants (age = 73.

Adherence to Life's Essential 8 is associated with delayed white matter aging.

Importance: The American Heart Association introduced Life's Essential 8 (LE8) as a checklist of healthy lifestyle factors to help older individuals maintain and improve cardiovascular health and live longer. How LE8 can foster healthy brain aging and interact with genetic risk factors to render the aging brain less vulnerable to dementia is not well understood.

Objective: To investigate the impact of LE8 on the white matter brain aging and the moderating effects of the allele.

Session Introduction: Translating Big Data Imaging Genomics Findings to the Individual: Prediction of Risks and Outcomes in Neuropsychiatric Illnesses.

This PSB 2025 session is focused on opportunities, challenges and solutions for translating Big Data Imaging Genomic findings toward powering decision making in personalized medicine and guiding individual clinical decisions. It combines many of the scientific directions that are of interest to PSB members including Big Data analyses, pattern recognition, machine learning and AI, electronic health records and others.

Amyloid, Tau, and APOE in Alzheimer's Disease: Impact on White Matter Tracts.

Alzheimer's disease (AD) is characterized by cognitive decline and memory loss due to the abnormal accumulation of amyloid-beta (Aβ) plaques and tau tangles in the brain; its onset and progression also depend on genetic factors such as the apolipoprotein E (APOE) genotype. Understanding how these factors affect the brain's neural pathways is important for early diagnostics and interventions. Tractometry is an advanced technique for 3D quantitative assessment of white matter tracts, localizing microstructural abnormalities in diseased populations in vivo.

BPEN: Brain Posterior Evidential Network for trustworthy brain imaging analysis.

The application of deep learning techniques to analyze brain functional magnetic resonance imaging (fMRI) data has led to significant advancements in identifying prospective biomarkers associated with various clinical phenotypes and neurological conditions. Despite these achievements, the aspect of prediction uncertainty has been relatively underexplored in brain fMRI data analysis. Accurate uncertainty estimation is essential for trustworthy learning, given the challenges associated with brain fMRI data acquisition and the potential diagnostic implications for patients.