Braden Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Braden Yang has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- Aristeidis Sotiras
University of Pennsylvania
12 shared publications - Tom Earnest
Mallinckrodt Institute of Radiology Washington University School of Medicine in St Louis Saint Louis Missouri USA
11 shared publications - Brian Andrew Gordon
Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO 63110, USA
9 shared publications - Tammie Lee Smith Benzinger
Mallinckrodt Institute of Radiology, Washington University School of Medicine, St. Louis, MO 63110, USA
9 shared publications Deydeep Kothapalli
Mallinckrodt Institute of Radiology Washington University School of Medicine in St Louis Saint Louis Missouri USA
8 shared publications- Sayantan Kumar
Division of Intramural Research, National Library of Medicine, Bethesda, MD, USA
6 shared publications
Latest Publications
- Open Access
- 8 September 2026
- Published by MIT Press in Imaging Neuroscience
- Vol. 4
Taming dimensionality in big neuroimaging data: Efficient orthonormal projective NMF via stochastic learning and data compression
Large-scale neuroimaging datasets present remarkable opportunities for advancing our understanding of human brain structure and function. Data-driven pattern analysis methods such as Orthonormal Projective Non-negative Matrix Factorization (opNMF) are particularly well suited to uncover multivariate relationships within these data, offering greater interpretability and reproducibility than more conventional approaches such as principal component analysis (PCA) and independent component analysis (ICA). Despite its utility in clinical computational neuroscience, the application of opNMF in large cohort studies has been impeded by computational challenges and scalability limitations. In this work, we address these issues by introducing a stochastic optimization strategy that processes mini-batches of the data, substantially improving scalability. We further accelerate computation through random data compression and leverage repulsive point processes to diversify mini-batches, reducing redundancy and the variance of updates. We first evaluated our method on gray matter tissue density maps from 1,000 participants in the Open Access Series of Imaging Studies (OASIS). Compared with the original approach, it achieved similar approximation accuracy and factor interpretability while greatly reducing computational cost. To demonstrate practical utility, we then applied the framework to 10,000 participants from the UK Biobank, identifying 20 patterns of structural covariance (PSCs) and examined associations between visceral adipose tissue (VAT) and PSC loadings, finding significant relationships for 13 PSCs in females and 11 PSCs in males, most of which were negative. We further show how these patterns refine in higher-rank decompositions with 40 and 60 components. This enhanced opNMF framework opens new possibilities for large-scale neuroimaging analyses, facilitating deeper insights into brain structure in both health and disease.
- 8 September 2026
- Published by MIT Press in Imaging Neuroscience
- Vol. 4
Open AccessTaming dimensionality in big neuroimaging data: Efficient orthonormal projective NMF via stochastic learning and data compression
Large-scale neuroimaging datasets present remarkable opportunities for advancing our understanding of human brain structure and function. Data-driven pattern analysis methods such as Orthonormal Projective Non-negative Matrix Factorization (opNMF) are particularly well suited to uncover multivariate relationships within these data, offering greater interpretability and reproducibility than more conventional approaches such as principal component analysis (PCA) and independent component analysis (ICA). Despite its utility in clinical computational neuroscience, the application of opNMF in large cohort studies has been impeded by computational challenges and scalability limitations. In this work, we address these issues by introducing a stochastic optimization strategy that processes mini-batches of the data, substantially improving scalability. We further accelerate computation through random data compression and leverage repulsive point processes to diversify mini-batches, reducing redundancy and the variance of updates. We first evaluated our method on gray matter tissue density maps from 1,000 participants in the Open Access Series of Imaging Studies (OASIS). Compared with the original approach, it achieved similar approximation accuracy and factor interpretability while greatly reducing computational cost. To demonstrate practical utility, we then applied the framework to 10,000 participants from the UK Biobank, identifying 20 patterns of structural covariance (PSCs) and examined associations between visceral adipose tissue (VAT) and PSC loadings, finding significant relationships for 13 PSCs in females and 11 PSCs in males, most of which were negative. We further show how these patterns refine in higher-rank decompositions with 40 and 60 components. This enhanced opNMF framework opens new possibilities for large-scale neuroimaging analyses, facilitating deeper insights into brain structure in both health and disease.
- Open Access
- 3 August 2026
- Published by Springer Nature in Research Square
Regional Cerebrospinal Fluid Motility as a Key Determinant of Soluble Amyloid-β Levels and Kinetics
Alzheimer’s disease and cerebral amyloid angiopathy are characterized by the accumulation of amyloid-β (Aβ) species, yet the human fluid-physiological mechanisms that regulate soluble Aβ transport and clearance remain poorly understood. Aβ40, the dominant vascular Aβ species, remains relatively soluble and accumulates preferentially along vascular basement membranes, making it especially relevant to CSF-mediated clearance pathways. Here, we used non-invasive low b-value diffusion MRI to quantify regional effective CSF motility in a large multimodal cohort from the Knight Alzheimer Disease Research Center, including participants with CSF biomarkers (n = 502), plasma biomarkers (n = 459), amyloid PET imaging (n = 270), and stable isotope labeling kinetics data (n = 40). Effective CSF motility was quantified as mean pseudo-diffusivity (Mψ) and mapped using CSF pseudo-diffusion spatial statistics with a data-driven CSF Waterways atlas. Higher regional CSF motility was consistently associated with higher CSF Aβ40 concentrations, with convergent voxel-wise and region-of-interest effects across ventricular and extra-axial CSF compartments that were most prominent in peri-Sylvian CSF pathways. Across regions, CSF motility measures collectively explained approximately 18% of the variance in CSF Aβ40. A weaker, spatially restricted association was also observed with plasma Aβ40. In contrast, associations with CSF Aβ42 were smaller, anatomically limited, and further attenuated among participants with amyloid deposition on PET. In participants with stable isotope labeling kinetics, higher transventricular and cranio-cervical CSF motility was associated with earlier peak enrichment of labeled Aβ40 and Aβ42, while greater lateral ventricular motility was associated with faster fractional turnover of both peptides. Collectively, these findings identify effective CSF motility as an important physiological determinant of soluble Aβ levels in plasma and CSF, linking regional CSF dynamics to in vivo Aβ transport and turnover, with potential relevance to cerebral amyloid angiopathy and Alzheimer’s disease.
- 3 August 2026
- Published by Springer Nature in Research Square
Open AccessRegional Cerebrospinal Fluid Motility as a Key Determinant of Soluble Amyloid-β Levels and Kinetics
Alzheimer’s disease and cerebral amyloid angiopathy are characterized by the accumulation of amyloid-β (Aβ) species, yet the human fluid-physiological mechanisms that regulate soluble Aβ transport and clearance remain poorly understood. Aβ40, the dominant vascular Aβ species, remains relatively soluble and accumulates preferentially along vascular basement membranes, making it especially relevant to CSF-mediated clearance pathways. Here, we used non-invasive low b-value diffusion MRI to quantify regional effective CSF motility in a large multimodal cohort from the Knight Alzheimer Disease Research Center, including participants with CSF biomarkers (n = 502), plasma biomarkers (n = 459), amyloid PET imaging (n = 270), and stable isotope labeling kinetics data (n = 40). Effective CSF motility was quantified as mean pseudo-diffusivity (Mψ) and mapped using CSF pseudo-diffusion spatial statistics with a data-driven CSF Waterways atlas. Higher regional CSF motility was consistently associated with higher CSF Aβ40 concentrations, with convergent voxel-wise and region-of-interest effects across ventricular and extra-axial CSF compartments that were most prominent in peri-Sylvian CSF pathways. Across regions, CSF motility measures collectively explained approximately 18% of the variance in CSF Aβ40. A weaker, spatially restricted association was also observed with plasma Aβ40. In contrast, associations with CSF Aβ42 were smaller, anatomically limited, and further attenuated among participants with amyloid deposition on PET. In participants with stable isotope labeling kinetics, higher transventricular and cranio-cervical CSF motility was associated with earlier peak enrichment of labeled Aβ40 and Aβ42, while greater lateral ventricular motility was associated with faster fractional turnover of both peptides. Collectively, these findings identify effective CSF motility as an important physiological determinant of soluble Aβ levels in plasma and CSF, linking regional CSF dynamics to in vivo Aβ transport and turnover, with potential relevance to cerebral amyloid angiopathy and Alzheimer’s disease.
- Open Access
- 1 July 2026
- Published by Wiley in Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring
- Vol. 18 (3) , e70480
Comprehensive evaluation of AT(N) imaging biomarkers for predicting cognitive decline
INTRODUCTION: Few studies have investigated how different Alzheimer's disease biomarker definitions affect predictions of cognitive decline. METHODS: We predicted cognitive decline using 42 biomarker definitions spanning amyloid beta, tau, and neurodegeneration in 383 ADNI participants with baseline neuroimaging and longitudinal cognitive assessments. We identified optimal predictors for each pathology and variable type (continuous, binary, non‐binary categorical) using nested cross‐validation. Models were compared against support vector machines (SVMs) incorporating brain‐wide pathology. In a subsample, we compared imaging‐based biomarkers with biofluids (cerebrospinal fluid and plasma). RESULTS: We observed substantial variability in accuracy, even for measures of the same pathology. Tau biomarkers were most accurate, performing comparably to models incorporating all three pathologies. Binarization of biomarkers mostly preserved accuracy, while SVMs trained on brain‐wide pathology data generally did not improve performance. Imaging‐based biomarkers consistently outperformed biofluid ones. DISCUSSION: Imaging‐based biomarker definitions are not interchangeable and can influence the assessment of cognitive decline.
- 1 July 2026
- Published by Wiley in Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring
- Vol. 18 (3) , e70480
Open AccessComprehensive evaluation of AT(N) imaging biomarkers for predicting cognitive decline
INTRODUCTION: Few studies have investigated how different Alzheimer's disease biomarker definitions affect predictions of cognitive decline. METHODS: We predicted cognitive decline using 42 biomarker definitions spanning amyloid beta, tau, and neurodegeneration in 383 ADNI participants with baseline neuroimaging and longitudinal cognitive assessments. We identified optimal predictors for each pathology and variable type (continuous, binary, non‐binary categorical) using nested cross‐validation. Models were compared against support vector machines (SVMs) incorporating brain‐wide pathology. In a subsample, we compared imaging‐based biomarkers with biofluids (cerebrospinal fluid and plasma). RESULTS: We observed substantial variability in accuracy, even for measures of the same pathology. Tau biomarkers were most accurate, performing comparably to models incorporating all three pathologies. Binarization of biomarkers mostly preserved accuracy, while SVMs trained on brain‐wide pathology data generally did not improve performance. Imaging‐based biomarkers consistently outperformed biofluid ones. DISCUSSION: Imaging‐based biomarker definitions are not interchangeable and can influence the assessment of cognitive decline.
- Open Access
- 19 April 2026
- Published by Elsevier in Neurobiology of Aging
- Vol. 165, 8-23
Predicting future cognitive impairment in preclinical Alzheimer’s disease using amyloid PET and MRI: A multisite machine learning study
- 19 April 2026
- Published by Elsevier in Neurobiology of Aging
- Vol. 165, 8-23
Open AccessPredicting future cognitive impairment in preclinical Alzheimer’s disease using amyloid PET and MRI: A multisite machine learning study
- Open Access
A unified model for staging amyloid and tau pathology in Alzheimer’s disease
Biological staging models are a key tool for assessing the severity of Alzheimer’s disease (AD), supporting personalized medicine and playing a critical role in clinical trial design. Recently, researchers have leveraged positron emission tomography (PET) to inform data-driven staging models of brain pathology related to AD. However, most approaches have focused on staging either amyloid or tau progressions separately, while both pathologies constitute defining factors of AD. Here, we aimed to derive a data-driven staging model which encompasses the spatial spread of both amyloid and tau. We assembled a large sample (n=3,293) of individuals with both amyloid and tau PET imaging stemming from 8 neuroimaging studies of AD and aging. We applied unsupervised machine learning to estimate brain areas which showed coordinated pathological accumulation across our sample, and we used these regions to inform a data-driven model for staging amyloid and tau. The resulting six stage model showed two stages of amyloid progression followed by four stages of tau spread, which were associated with cross-sectional and longitudinal assessments of cognitive decline. Comparison of our biological staging model with clinical disease stages recommended by the Alzheimer’s Association showed evidence of heterogenous symptom profiles. Replication of results in holdout data demonstrated the generalizability and prognostic value of our staging model. Together, these findings establish a comprehensive and rigorously validated biological staging model that jointly characterizes amyloid and tau progression, advances beyond global or anatomically predefined summaries, and provides a scalable framework for studying disease heterogeneity and progression in AD. One Sentence Summary: Using PET imaging from a large sample of individuals (n=3,293), we derive a data-driven model for staging amyloid and tau pathology.
Open AccessA unified model for staging amyloid and tau pathology in Alzheimer’s disease
Biological staging models are a key tool for assessing the severity of Alzheimer’s disease (AD), supporting personalized medicine and playing a critical role in clinical trial design. Recently, researchers have leveraged positron emission tomography (PET) to inform data-driven staging models of brain pathology related to AD. However, most approaches have focused on staging either amyloid or tau progressions separately, while both pathologies constitute defining factors of AD. Here, we aimed to derive a data-driven staging model which encompasses the spatial spread of both amyloid and tau. We assembled a large sample (n=3,293) of individuals with both amyloid and tau PET imaging stemming from 8 neuroimaging studies of AD and aging. We applied unsupervised machine learning to estimate brain areas which showed coordinated pathological accumulation across our sample, and we used these regions to inform a data-driven model for staging amyloid and tau. The resulting six stage model showed two stages of amyloid progression followed by four stages of tau spread, which were associated with cross-sectional and longitudinal assessments of cognitive decline. Comparison of our biological staging model with clinical disease stages recommended by the Alzheimer’s Association showed evidence of heterogenous symptom profiles. Replication of results in holdout data demonstrated the generalizability and prognostic value of our staging model. Together, these findings establish a comprehensive and rigorously validated biological staging model that jointly characterizes amyloid and tau progression, advances beyond global or anatomically predefined summaries, and provides a scalable framework for studying disease heterogeneity and progression in AD. One Sentence Summary: Using PET imaging from a large sample of individuals (n=3,293), we derive a data-driven model for staging amyloid and tau pathology.
- Open Access
Predicting future cognitive impairment in preclinical Alzheimer’s disease using amyloid PET and MRI: a multisite machine learning study
Predicting the likelihood of developing Alzheimer’s disease (AD) dementia in at-risk individuals is important for the design of and optimal recruitment for clinical trials of disease-modifying therapies. Machine learning (ML) has been shown to excel in this task; however, there remains a lack of models developed specifically for the preclinical AD population, who display early signs of abnormal brain amyloidosis but remain cognitively unimpaired. Here, we trained and evaluated ML classifiers to predict whether individuals with preclinical AD will progress to mild cognitive impairment or dementia within multiple fixed time windows, ranging from one to five years. Models were trained on regional imaging features extracted from amyloid positron emission tomography and magnetic resonance imaging pooled across seven independent sites and from two amyloid radiotracers ([ 18 F]-florbetapir and [ 11 C]-Pittsburgh-compound-B). Out-of-sample generalizability was evaluated via a leave-one-site-out and leave-one-tracer-out cross-validation. Classifiers achieved an out-of-sample receiver operating characteristic area-under-the-curve of 0.66 or greater when applied to all except one hold-out sites and 0.72 or greater when applied to each hold-out radiotracer. Additionally, when applying our models in a retroactive cohort enrichment analysis on A4 clinical trial data, we observed increased statistical power of detecting differences in amyloid accumulation between placebo and treatment arms after enrichment by ML stratifications. As emerging investigations of new disease-modifying therapies for AD increasingly focus on asymptomatic, preclinical populations, our findings underscore the potential applicability of ML-based patient stratification for recruiting more homogeneous cohorts and improving statistical power for detecting treatment effects for future clinical trials. Highlights: Machine learning can predict future cognitive impairment in preclinical Alzheimer’s Models achieved high out-of-sample ROC-AUC on external sites and PET tracers Models were able to distinguish cognitively stable from decliners in the A4 cohort ML cohort enrichment enhanced secondary treatment effect detection in the A4 cohort
Open AccessPredicting future cognitive impairment in preclinical Alzheimer’s disease using amyloid PET and MRI: a multisite machine learning study
Predicting the likelihood of developing Alzheimer’s disease (AD) dementia in at-risk individuals is important for the design of and optimal recruitment for clinical trials of disease-modifying therapies. Machine learning (ML) has been shown to excel in this task; however, there remains a lack of models developed specifically for the preclinical AD population, who display early signs of abnormal brain amyloidosis but remain cognitively unimpaired. Here, we trained and evaluated ML classifiers to predict whether individuals with preclinical AD will progress to mild cognitive impairment or dementia within multiple fixed time windows, ranging from one to five years. Models were trained on regional imaging features extracted from amyloid positron emission tomography and magnetic resonance imaging pooled across seven independent sites and from two amyloid radiotracers ([ 18 F]-florbetapir and [ 11 C]-Pittsburgh-compound-B). Out-of-sample generalizability was evaluated via a leave-one-site-out and leave-one-tracer-out cross-validation. Classifiers achieved an out-of-sample receiver operating characteristic area-under-the-curve of 0.66 or greater when applied to all except one hold-out sites and 0.72 or greater when applied to each hold-out radiotracer. Additionally, when applying our models in a retroactive cohort enrichment analysis on A4 clinical trial data, we observed increased statistical power of detecting differences in amyloid accumulation between placebo and treatment arms after enrichment by ML stratifications. As emerging investigations of new disease-modifying therapies for AD increasingly focus on asymptomatic, preclinical populations, our findings underscore the potential applicability of ML-based patient stratification for recruiting more homogeneous cohorts and improving statistical power for detecting treatment effects for future clinical trials. Highlights: Machine learning can predict future cognitive impairment in preclinical Alzheimer’s Models achieved high out-of-sample ROC-AUC on external sites and PET tracers Models were able to distinguish cognitively stable from decliners in the A4 cohort ML cohort enrichment enhanced secondary treatment effect detection in the A4 cohort
- Open Access
- 15 April 2025
- Published by Wiley in Alzheimer's & Dementia
- Vol. 21 (4) , e70143
Analyzing heterogeneity in Alzheimer disease using multimodal normative modeling on imaging‐based ATN biomarkers
INTRODUCTION: Previous studies have applied normative modeling on a single neuroimaging modality to investigate Alzheimer disease (AD) heterogeneity. We employed a deep learning‐based multimodal normative framework to analyze individual‐level variation across ATN (amyloid‐tau‐neurodegeneration) imaging biomarkers. METHODS: We selected cross‐sectional discovery ( n = 665) and replication cohorts ( n = 430) with available T1‐weighted magnetic resonance imaging (MRI), amyloid, and tau positron emission tomography (PET). Normative modeling estimated individual‐level abnormal deviations in amyloid‐positive individuals compared to amyloid‐negative controls. Regional abnormality patterns were mapped at different clinical group levels to assess intra‐group heterogeneity. An individual‐level disease severity index (DSI) was calculated using both the spatial extent and magnitude of abnormal deviations across ATN. RESULTS: Greater intra‐group heterogeneity in ATN abnormality patterns was observed in more severe clinical stages of AD. Higher DSI was associated with worse cognitive function and increased risk of disease progression. DISCUSSION: Subject‐specific abnormality maps across ATN reveal the heterogeneous impact of AD on the brain. Highlights: Normative modeling examined AD heterogeneity across multimodal imaging biomarkers. Heterogeneity in spatial patterns of gray matter atrophy, amyloid, and tau burden. Higher within‐group heterogeneity for AD patients at advanced dementia stages. Patient‐specific metric summarized extent of neurodegeneration and neuropathology. Metric is a marker of poor brain health and can monitor risk of disease progression.
- 15 April 2025
- Published by Wiley in Alzheimer's & Dementia
- Vol. 21 (4) , e70143
Open AccessAnalyzing heterogeneity in Alzheimer disease using multimodal normative modeling on imaging‐based ATN biomarkers
INTRODUCTION: Previous studies have applied normative modeling on a single neuroimaging modality to investigate Alzheimer disease (AD) heterogeneity. We employed a deep learning‐based multimodal normative framework to analyze individual‐level variation across ATN (amyloid‐tau‐neurodegeneration) imaging biomarkers. METHODS: We selected cross‐sectional discovery ( n = 665) and replication cohorts ( n = 430) with available T1‐weighted magnetic resonance imaging (MRI), amyloid, and tau positron emission tomography (PET). Normative modeling estimated individual‐level abnormal deviations in amyloid‐positive individuals compared to amyloid‐negative controls. Regional abnormality patterns were mapped at different clinical group levels to assess intra‐group heterogeneity. An individual‐level disease severity index (DSI) was calculated using both the spatial extent and magnitude of abnormal deviations across ATN. RESULTS: Greater intra‐group heterogeneity in ATN abnormality patterns was observed in more severe clinical stages of AD. Higher DSI was associated with worse cognitive function and increased risk of disease progression. DISCUSSION: Subject‐specific abnormality maps across ATN reveal the heterogeneous impact of AD on the brain. Highlights: Normative modeling examined AD heterogeneity across multimodal imaging biomarkers. Heterogeneity in spatial patterns of gray matter atrophy, amyloid, and tau burden. Higher within‐group heterogeneity for AD patients at advanced dementia stages. Patient‐specific metric summarized extent of neurodegeneration and neuropathology. Metric is a marker of poor brain health and can monitor risk of disease progression.
- Open Access
- 15 April 2025
- Vol. 21 (4)
Analyzing heterogeneity in Alzheimer disease using multimodal normative modeling on imaging‐based ATN biomarkers
Previous studies have applied normative modeling on a single neuroimaging modality to investigate Alzheimer disease (AD) heterogeneity. We employed a deep learning‐based multimodal normative framework to analyze individual‐level variation across ATN (amyloid‐tau‐neurodegeneration) imaging biomarkers. We selected cross‐sectional discovery (n = 665) and replication cohorts (n = 430) with available T1‐weighted magnetic resonance imaging (MRI), amyloid, and tau positron emission tomography (PET). Normative modeling estimated individual‐level abnormal deviations in amyloid‐positive individuals compared to amyloid‐negative controls. Regional abnormality patterns were mapped at different clinical group levels to assess intra‐group heterogeneity. An individual‐level disease severity index (DSI) was calculated using both the spatial extent and magnitude of abnormal deviations across ATN. Greater intra‐group heterogeneity in ATN abnormality patterns was observed in more severe clinical stages of AD. Higher DSI was associated with worse cognitive function and increased risk of disease progression. Subject‐specific abnormality maps across ATN reveal the heterogeneous impact of AD on the brain. Normative modeling examined AD heterogeneity across multimodal imaging biomarkers. Heterogeneity in spatial patterns of gray matter atrophy, amyloid, and tau burden. Higher within‐group heterogeneity for AD patients at advanced dementia stages. Patient‐specific metric summarized extent of neurodegeneration and neuropathology. Metric is a marker of poor brain health and can monitor risk of disease progression.
- 15 April 2025
- Vol. 21 (4)
Open AccessAnalyzing heterogeneity in Alzheimer disease using multimodal normative modeling on imaging‐based ATN biomarkers
Previous studies have applied normative modeling on a single neuroimaging modality to investigate Alzheimer disease (AD) heterogeneity. We employed a deep learning‐based multimodal normative framework to analyze individual‐level variation across ATN (amyloid‐tau‐neurodegeneration) imaging biomarkers. We selected cross‐sectional discovery (n = 665) and replication cohorts (n = 430) with available T1‐weighted magnetic resonance imaging (MRI), amyloid, and tau positron emission tomography (PET). Normative modeling estimated individual‐level abnormal deviations in amyloid‐positive individuals compared to amyloid‐negative controls. Regional abnormality patterns were mapped at different clinical group levels to assess intra‐group heterogeneity. An individual‐level disease severity index (DSI) was calculated using both the spatial extent and magnitude of abnormal deviations across ATN. Greater intra‐group heterogeneity in ATN abnormality patterns was observed in more severe clinical stages of AD. Higher DSI was associated with worse cognitive function and increased risk of disease progression. Subject‐specific abnormality maps across ATN reveal the heterogeneous impact of AD on the brain. Normative modeling examined AD heterogeneity across multimodal imaging biomarkers. Heterogeneity in spatial patterns of gray matter atrophy, amyloid, and tau burden. Higher within‐group heterogeneity for AD patients at advanced dementia stages. Patient‐specific metric summarized extent of neurodegeneration and neuropathology. Metric is a marker of poor brain health and can monitor risk of disease progression.
- Open Access
Multimodal normative modeling in Alzheimer’s Disease with introspective variational autoencoders
Normative models in neuroimaging learn patterns of healthy brain distributions to identify deviations in disease subjects, such as those with Alzheimer’s Disease (AD). This study addresses two key limitations of variational autoencoder (VAE)-based normative models: (1) VAEs often struggle to accurately model healthy control distributions, resulting in high reconstruction errors and false positives, and (2) traditional multimodal aggregation methods, like Product-of-Experts (PoE) and Mixture-of-Experts (MoE), can produce uninformative latent representations. To overcome these challenges, we developed a multimodal introspective VAE that enhances normative modeling by achieving more precise representations of healthy anatomy in both the latent space and reconstructions. Additionally, we implemented a Mixture-of-Product-of-Experts (MOPOE) approach, leveraging the strengths of PoE and MoE to efficiently aggregate multimodal information and improve abnormality detection in the latent space. Using multimodal neuroimaging biomarkers from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, our proposed multimodal introspective VAE demonstrated superior reconstruction of healthy controls and outperformed baseline methods in detecting outliers. Deviations calculated in the aggregated latent space effectively integrated complementary information from multiple modalities, leading to higher likelihood ratios. The model exhibited strong performance in Out-of-Distribution (OOD) detection, achieving clear separation between control and disease cohorts. Additionally, Z-score deviations in specific latent dimensions were mapped to feature-space abnormalities, enabling interpretable identification of brain regions associated with AD pathology.
Open AccessMultimodal normative modeling in Alzheimer’s Disease with introspective variational autoencoders
Normative models in neuroimaging learn patterns of healthy brain distributions to identify deviations in disease subjects, such as those with Alzheimer’s Disease (AD). This study addresses two key limitations of variational autoencoder (VAE)-based normative models: (1) VAEs often struggle to accurately model healthy control distributions, resulting in high reconstruction errors and false positives, and (2) traditional multimodal aggregation methods, like Product-of-Experts (PoE) and Mixture-of-Experts (MoE), can produce uninformative latent representations. To overcome these challenges, we developed a multimodal introspective VAE that enhances normative modeling by achieving more precise representations of healthy anatomy in both the latent space and reconstructions. Additionally, we implemented a Mixture-of-Product-of-Experts (MOPOE) approach, leveraging the strengths of PoE and MoE to efficiently aggregate multimodal information and improve abnormality detection in the latent space. Using multimodal neuroimaging biomarkers from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, our proposed multimodal introspective VAE demonstrated superior reconstruction of healthy controls and outperformed baseline methods in detecting outliers. Deviations calculated in the aggregated latent space effectively integrated complementary information from multiple modalities, leading to higher likelihood ratios. The model exhibited strong performance in Out-of-Distribution (OOD) detection, achieving clear separation between control and disease cohorts. Additionally, Z-score deviations in specific latent dimensions were mapped to feature-space abnormalities, enabling interpretable identification of brain regions associated with AD pathology.
- Open Access
- 1 December 2024
- Published by Wiley in Alzheimer's & Dementia
- Vol. 20 (S9)
Harmonization of amyloid PET radiotracers using ComBat and its influence on detecting treatment effects in a simulated clinical trial
Background: Differences in amyloid PET radiotracer pharmacokinetics and binding properties lead to discrepancies in amyloid uptake measurements, which may adversely affect the statistical power of clinical trials that utilize multiple tracers to track brain amyloid deposition. To address this, Centiloid was developed for standardizing global amyloid SUVRs across tracers to a common scale. Alternatively, ComBat is a technique for harmonizing batch effects while preserving variations from biologically‐relevant covariates. Unlike Centiloid, ComBat is entirely data‐driven, does not require a calibration process, and can be applied to regional SUVRs. However, it has not been validated for amyloid PET. Here, we evaluate whether ComBat improves detection of treatment effects in a simulated clinical trial.Method: 365 amyloid‐positive subjects were identified from the OASIS‐3 dataset, from which 322 Pittsburgh compound B (PiB) and 260 18F‐Florbetapir (FBP) PET scans were selected. SUVRs of the global cortical region and 82 FreeSurfer regions were computed from each scan using the PET Unified Pipeline. Linear mixed effects (LME) models were fitted on each tracer separately and used to simulate longitudinal SUVRs of placebo and treatment groups in a hypothetical clinical trial (Figure 1). A negative rate‐of‐change was introduced to the treatment group to mimic a treatment effect. Additionally, tracer mixing proportions were varied within each group. Centiloid and ComBat were applied to simulated data to harmonize across tracers. A separate LME model was fitted to test for significant differences in SUVR rate‐of‐change between groups. Power was estimated as the proportion of significant findings across 1000 simulations.Result: After harmonization with either Centiloid or ComBat with no covariates, an increase in power was observed in the presence of a treatment effect, and a decrease in Type‐I error was observed for no treatment effect (Figure 2). These changes were most prominent in cases where groups exhibited differing tracer mixing proportions. Similar patterns were observed for regional SUVRs (Figure 3).Conclusion: We demonstrated that tracer harmonization is important for improving power in the presence of a treatment effect and reducing Type‐I error in its absence. ComBat performs comparably to Centiloid in harmonizing amyloid radiotracers in the context of a clinical trial.
- 1 December 2024
- Published by Wiley in Alzheimer's & Dementia
- Vol. 20 (S9)
Open AccessHarmonization of amyloid PET radiotracers using ComBat and its influence on detecting treatment effects in a simulated clinical trial
Background: Differences in amyloid PET radiotracer pharmacokinetics and binding properties lead to discrepancies in amyloid uptake measurements, which may adversely affect the statistical power of clinical trials that utilize multiple tracers to track brain amyloid deposition. To address this, Centiloid was developed for standardizing global amyloid SUVRs across tracers to a common scale. Alternatively, ComBat is a technique for harmonizing batch effects while preserving variations from biologically‐relevant covariates. Unlike Centiloid, ComBat is entirely data‐driven, does not require a calibration process, and can be applied to regional SUVRs. However, it has not been validated for amyloid PET. Here, we evaluate whether ComBat improves detection of treatment effects in a simulated clinical trial.Method: 365 amyloid‐positive subjects were identified from the OASIS‐3 dataset, from which 322 Pittsburgh compound B (PiB) and 260 18F‐Florbetapir (FBP) PET scans were selected. SUVRs of the global cortical region and 82 FreeSurfer regions were computed from each scan using the PET Unified Pipeline. Linear mixed effects (LME) models were fitted on each tracer separately and used to simulate longitudinal SUVRs of placebo and treatment groups in a hypothetical clinical trial (Figure 1). A negative rate‐of‐change was introduced to the treatment group to mimic a treatment effect. Additionally, tracer mixing proportions were varied within each group. Centiloid and ComBat were applied to simulated data to harmonize across tracers. A separate LME model was fitted to test for significant differences in SUVR rate‐of‐change between groups. Power was estimated as the proportion of significant findings across 1000 simulations.Result: After harmonization with either Centiloid or ComBat with no covariates, an increase in power was observed in the presence of a treatment effect, and a decrease in Type‐I error was observed for no treatment effect (Figure 2). These changes were most prominent in cases where groups exhibited differing tracer mixing proportions. Similar patterns were observed for regional SUVRs (Figure 3).Conclusion: We demonstrated that tracer harmonization is important for improving power in the presence of a treatment effect and reducing Type‐I error in its absence. ComBat performs comparably to Centiloid in harmonizing amyloid radiotracers in the context of a clinical trial.