Biology subjects

Davatzikos, C.

Publications and source records attributed to Davatzikos, C..

At least 19 recordsLinked to original sources

bioRxiv2026

Imputation-Based Harmonization Mitigates Site Effects Without Data Leakage in Machine Learning Studies

Neuroimaging studies that pool data across clinical sites often suffer from site effects --- variability in imaging measures that arises from technical heterogeneity across sites as opposed to true biological signal. While numerous harmonization methods have been proposed to remove site effects from imaging features, less attention has been placed on how to incorporate harmonization models into common machine-learning pipelines. We demonstrate that current approaches for integration either suffer from data leakage, fail to fully remove site effects from the target data, or attenuate true biological associations during the harmonization process. To address these issues, we propose Multiple Imputation for Removing Technical Heterogeneity (MIRTH), which uses imputed outcomes to harmonize the test data. We benchmark MIRTH's performance using both simulated and real-world volumetric data from the Alzheimer's Disease Neuroimaging Initiative and the Baltimore Longitudinal Study of Aging, demonstrating that MIRTH can achieve high predictive accuracy while avoiding inflated performance when the outcome is imbalanced across clinical sites.

neuroscience↗

bioRxiv2026

Neuroanatomical Subtypes of Callous-Unemotional Traits in a Community Sample of Youth

ImportanceCallous Unemotional (CU) traits are associated with significant clinical and neurophysiological heterogeneity that may affect treatment effectiveness. ObjectiveTo uncover neuroanatomical subtypes of CU traits using weakly-supervised machine learning and assess whether emerging subtypes differ on relevant clinical, temperamental, and environmental constructs. Design, Setting, and ParticipantsImaging data was from the longitudinal Adolescent, Brain, Cognitive Development (ABCD) Study. Participants were 9-10 years old at baseline (M=9.925, 69.9% male) and included 222 children with CU traits and 234 typically developing controls matched on age, sex and income. Main Outcomes and MeasuresThe weakly-supervised heterogeneity through discriminative analysis (HYDRA) model was trained on grey matter (GM) volumes from 84 regions of interest (ROIs) and tested for reproducibility using cross-validation and permutation testing. Derived subtypes were compared cross-sectionally and prospectively on relevant clinical, temperamental, and environmental measures and subsequent GM volume at 2-year follow up. ResultsHYDRA revealed an optimal 2-subtype solution within children with CU traits. Subtypes showed comparable levels of aggression that were significantly higher than typically developing controls. At the same time, subtype 1 had larger GM volume, fewer internalizing symptoms, and less adversity exposure, while subtype 2 was characterized by smaller GM volume, more internalizing symptoms, and more adversity exposure. Conclusions and RelevanceThis study provides evidence of neuroanatomically distinct subtypes of CU traits characterized by different clinical and etiological profiles, with implications for diagnosis and treatment.

neuroscience↗

bioRxiv2026

Batch Effect Correction for Neuroimaging Data with Heterogeneous Spatial Correlations

Magnetic resonance imaging scans are effective tools for unveiling brain structures and understanding pathology for complex neurodevelopmental and aging processes. The spatial correlations among various brain regions reveal critical information and insights into the mechanisms of brain functions and their associations with cognitive abilities. Large-scale neuroimaging studies that acquire or aggregate imaging scans from multiple sites have become increasingly popular. Doing so enhances the diversity of study samples and robustness of study findings, and increases the statistical power of any analysis conducted for the biological hypotheses of interest. However, collecting images across different sites introduces non-biological variability attributed to differences in imaging protocol and configurations, known as batch effects. While there are methods to perform this batch effect correction, there are limited methods that directly account for the spatial patterns found in images of the brain. We develop Covariance-Aware Multivariate (CAM) ComBat that accounts for such spatial correlation across high-dimensional features, which could be heterogeneous across batches. We also propose a computationally efficient alternative of CAM-ComBat, Spatially-Informed Iterative Block (SIB) ComBat, that is scalable for very high dimension of features. We show that these methods outperform existing batch effect correction methods through simulation studies and an application to real neuroimaging data.

neuroscience↗

bioRxiv2026

Predicting Autopsy-Confirmed Neuropathology across Clinical, Neuroimaging, and CSF Biomarkers using Machine Learning

Accurate in vivo prediction of neuropathology is critical for advancing diagnosis and treatment of Alzheimers disease and related dementias (ADRDs). As many individuals with ADRDs have mixed pathologies ({beta}-amyloid, pathologic tau, cerebrovascular disease, vascular brain injury, pathologic TDP-43, hippocampal sclerosis, Lewy bodies), there is interest in determining how accurately we can infer these pathologic changes from clinical data, biofluid assays (e.g., CSF), and neuroimaging. Here we evaluated automated machine learning models trained on data curated by the AD Sequencing Project Phenotype Harmonization Consortium (N=7,894 individuals), to predict 26 autopsy-confirmed neuropathological outcomes. Predictors included in vivo clinical and cognitive composite scores, brain measures from 3D structural MRI and diffusion tensor imaging, image-derived measures of white matter hyperintensities (WMH), and CSF biomarkers. Predictive models were trained using ensemble learning with stratified cross-validation. We assessed performance using Spearmans rank correlation and Matthews correlation coefficient, to accommodate co-occurring pathologic changes. The added value of neuroimaging and CSF versus clinical features alone was quantified. Braak stage was among the most consistently predicted outcomes. CSF biomarkers best predicted {beta}-amyloid and tau pathology, but diffusion MRI metrics best captured vascular brain injury and white matter injury, and outperformed clinical and cognitive measures and anatomical MRI in predicting Lewy body disease. Anatomical measures from structural MRI outperformed standard clinical assessments in assessing neurodegeneration and hippocampal sclerosis, and WMH complemented cognitive measures in predicting TDP-43 pathology. These results establish a baseline for comparing modalities for inferring neuropathology.

neuroscience↗

bioRxiv2026

Gene-Modulated Network Diffusion for Improved Modeling of Amyloid-β Spread in Alzheimer's Disease

Understanding the pathogenesis of amyloid-{beta} pathology in Alzheimers Disease (AD) proves to be a challenge. In this work, we expand upon the application of network diffusion models (NDM) to study pathophysiological spread of amyloid-{beta} throughout white matter structural brain networks. We found that the NDM successfully recaptures subpopulation-level spatial patterns (Pearsons R=0.45-0.48, PFDR < 0.01) of amyloid-{beta} deposition in the Alzheimers Disease Neuroimaging Cohort at a regional level, but with drawbacks in mechanism interpretability. We then moved to an extended NDM framework (eNDM), including a protein synthesis term to better reflect the role of amyloid-{beta} metabolism, as well as including regional vulnerability using spatial transcriptomics from the Allen Human Brain Atlas to modulate the region-level rate parameters of the synthesis term. The novel gene eNDMs exhibited significant performance increases in Pearsons correlation (Steigers Z, PFDR < 0.10) over baseline NDM performance in mild cognitive impairment and AD groups using APOE, SORL1, and FGL2 for gene modulation. The results were robust and replicable when testing on an external cohort of the Alzheimers Disease Sequencing Project. The study thus demonstrates the importance of regional genetic vulnerability, in conjunction with network diffusion mechanisms, in improving the modelling and prediction of amyloid-{beta} pathophysiological spread.

bioinformatics↗

bioRxiv2026

Highly replicable multisite patterns of adolescent white matter maturation

The Adolescent Brain Cognitive Development (ABCD) Study is the largest U.S.-based neuroimaging initiative of adolescent brain maturation. Diffusion MRI (dMRI) provides unique insights into white matter organization, yet applying advanced processing pipelines and managing technical variability across scanning environments remains challenging at scale. To address these issues, we present ABCD-BIDS Community Collection (ABCC) release 3.1.0, including a curated resource of more than 24,000 fully processed ABCD dMRI datasets. ABCC provides fully processed images, nuanced image quality metrics, advanced microstructural measures, and person-specific bundle tractography. Evaluating these rich data revealed that measures of diffusion restriction and non-Gaussianity--in particular the intracellular volume fraction from NODDI and return-to-origin probability from MAP-MRI--were highly sensitive to neurodevelopment and robust to variation in image quality. Additionally, harmonization of microstructural features markedly improved the cross-vendor generalizability of developmental effects. Together, ABCC accelerates reproducible, rigorous research on adolescent white matter development.

neuroscience↗

bioRxiv2025

Precision Neuromodulation with Real-Time Brain Decoding for Working Memory Enhancement

Transcranial magnetic stimulation (TMS) has transformed non-invasive brain therapies but faces challenges due to variability in outcomes, likely stemming from inter-individual differences in brain function. This study aimed to address this challenge by integrating personalized functional networks (PFNs) derived from functional magnetic resonance imaging (fMRI) with a neural network-based decoder to optimize stimulation in real time during a working memory (WM) task. After identification of individualized stimulation targets, participants completed a TMS/fMRI session, performing a WM task while receiving rTMS at randomized frequencies. Decoder outputs and behavioral data during this session guided selection of optimal and suboptimal stimulation frequencies. Participants then underwent six stimulation sessions (three optimal, three suboptimal) in a randomized crossover design, performing WM and control tasks. The optimal stimulation improved WM performance by the final session, with no improvement observed in the control task. Additionally, the decoder output predicted behavioral performance on the WM task, both during the TMS/fMRI and neuromodulation sessions. These findings show that neural network-guided closed-loop neuromodulation can improve TMS effectiveness, marking a step forward in personalized brain stimulation. HIGHLIGHTSO_LIClosed-loop TMS guided by real-time brain decoding enhances post-stimulation behavioral effects. C_LIO_LIIndividualized functional connectivity networks enable targeted neuromodulation C_LIO_LIOptimal stimulation boosted working memory performance over sub-optimal C_LIO_LIBrain decoder readouts predicted behavioral performance C_LI

neuroscience↗

bioRxiv2025

Advancing Fair and Explainable Machine Learning for Neuroimaging Dementia Pattern Classification in Multi-Ethnic Populations

Dementia, a degenerative disease affecting millions globally, is projected to triple by 2050. Early and precise diagnosis is essential for effective treatment and improved quality of life. However, current diagnostic approaches frequently demonstrate inconsistent precision and impartiality, particularly among diverse cultural groups. This study investigates performance discrepancies in dementia classification among White American, African American, and Hispanic populations. We reveal significant cross-group bias, particularly when models trained on one group are tested on another. To address this, we introduce a novel combination of few-shot learning and domain alignment to improve model adaptability across underrepresented populations. Our results show that these techniques substantially reduce inter-group performance gaps, especially between White American and Hispanic cohorts. This finding highlights the crucial need for fairness-aware strategies and the inclusion of diverse populations in training data to ensure accurate and equitable dementia diagnoses.

neuroscience↗

bioRxiv2025

Mapping individualized multi-scale hierarchical brain functional networks from fMRI by self-supervised deep learning

The brains multi-scale hierarchical organization supports functional segregation and integration. Characterizing the hierarchy of individualized multi-scale functional networks (FNs) is crucial for understanding these fundamental brain processes. It provides promising opportunities for both basic neuroscience and translational research in neuropsychiatric illness. However, current methods typically compute individualized FNs at a single scale and are not equipped to quantify any possible hierarchical organization. To address this limitation, we present a self-supervised deep learning (DL) framework that simultaneously computes multi-scale FNs and characterizes their across-scale hierarchical structure at the individual level. Our method learns intrinsic representations of fMRI data in a low-dimensional latent space to effectively encode multi-scale FNs and their hierarchical structure by optimizing functional homogeneity of FNs across scales jointly in an end-to-end learning manner. A DL model trained on fMRI scans from the Human Connectome Project successfully identified individualized multi-scale hierarchical FNs for unseen individuals and generalized to two external cohorts. Furthermore, the individualized hierarchical structure of FNs was significantly associated with biological phenotypes, including sex, brain development, and brain health. Our framework provides an effective method to compute multi-scale FNs and to characterize the inter-scale hierarchy of FNs for individuals, facilitating a comprehensive understanding of brain functional organization and its inter-individual variation.

neuroscience↗

bioRxiv2025

Two Axes of White Matter Development

Despite decades of neuroimaging research, how white matter develops along the length of major tracts in humans remains unknown. Here, we identify fundamental patterns of white matter maturation by examining developmental variation along major, long-range cortico-cortical tracts in youth ages 5-23 years using diffusion MRI from three large-scale, cross-sectional datasets (total N = 2,716). Across datasets, we delineate two replicable axes of human white matter development. First, we find a deep-to-superficial axis, in which superficial tract regions near the cortical surface exhibit greater age-related change than deep tract regions. Second, we demonstrate that the development of superficial tract regions aligns with the cortical hierarchy defined by the sensorimotor-association axis, with tract ends adjacent to sensorimotor cortices maturing earlier than those adjacent to association cortices. These results reveal developmental variation along tracts that conventional tract-average analyses have previously obscured, challenging the implicit assumption that white matter tracts mature uniformly along their length. Such developmental variation along tracts may have functional implications, including mitigating ephaptic coupling in densely packed deep tract regions and tuning neural synchrony through hierarchical development in superficial tract regions - ultimately refining neural transmission in youth.

neuroscience↗

bioRxiv2025

Uncovering functional connectivity patterns predictive of cognition in youth using interpretable predictive modeling

Functional MRI studies have identified functional connectivity (FC) patterns associated with behavioral traits using whole-brain or region-wise predictive models. However, whole-brain approaches often suffer from limited generalizability and interpretability due to the high-dimensionality of FC data. Conversely, region-wise models inherently isolate predictions, ineffective for characterizing contributions of the whole brain FC patterns in predicting a target trait. In this study, we propose an interpretable predictive model that learns fine-grained FC patterns predictive of behavioral traits, jointly at the regional and participant levels, to characterize the overall association of FC patterns with a target trait. Our model learns both a relevance score and a dedicated prediction model for each brain region, then integrates the regional predictions to generate a participant-level prediction, capturing the collective association of FC patterns with the trait. We validated our method using FC data from 6798 participants in the Adolescent Brain and Cognitive Development (ABCD) study for predicting cognition. Our interpretable predictive model identified the cingulo-parietal, retrosplenial-temporal, dorsal attention, salience, and cingulo-opercular networks as collectively predictive of cognitive traits. The interpretable model significantly improved prediction accuracy and facilitated the characterization of fine-grained differences in FC patterns across cognitive domains. Furthermore, the learned relevance scores enhanced region-wise predictions of longitudinal cognitive measures in the ABCD cohort and cognitive traits in an external Human Connectome Project Development (HCP-D) cohort. These findings suggest that our method effectively characterizes generalizable and fine-grained FC patterns linked to cognition in youth.

neuroscience↗

bioRxiv2025

Reproducible Brain Charts: An open data resource for mapping brain development and its associations with mental health

Major mental disorders are increasingly understood as disorders of brain development. Large and heterogeneous samples are required to define generalizable links between brain development and psychopathology. To this end, we introduce the Reproducible Brain Charts (RBC), an open data resource that integrates data from 5 large studies of brain development in youth from three continents (N=6,346; 45% Female). Confirmatory bifactor models were used to create harmonized psychiatric phenotypes that capture major dimensions of psychopathology. Following rigorous quality assurance, neuroimaging data were carefully curated and processed using consistent pipelines in a reproducible manner with DataLad, the Configurable Pipeline for the Analysis of Connectomes (C-PAC), and FreeSurfer. Initial analyses of RBC data emphasize the benefit of careful quality assurance and data harmonization in delineating developmental effects and associations with psychopathology. Critically, all RBC data - including harmonized psychiatric phenotypes, unprocessed images, and fully processed imaging derivatives - are openly shared without a data use agreement via the International Neuroimaging Data-sharing Initiative. Together, RBC facilitates large-scale, reproducible, and generalizable research in developmental and psychiatric neuroscience.

neuroscience↗

bioRxiv2025

Spatial Heterogeneity and Subtypes of Functional Connectivity Development in Youth

The brain functional connectome development is fundamental to neurocognitive growth in youth. While brain age prediction has been widely used to assess connectome development at the individual level, traditional approaches providing a global index overlook the spatial variability and inter-individual heterogeneity of functional connectivity (FC) development across the cortex. In this study, we introduced a regional brain development index to assess spatially fine-grained FC development. We examined the spatial variability of FC development and stratified individuals into subtypes with distinct patterns of spatial heterogeneity in region-wise FC development across the cortex through clustering. An evaluation conducted on a sample of youths aged 8-23 years using fMRI data from the Philadelphia Neurodevelopmental Cohort (PNC) revealed three distinct FC development subtypes. Individuals with advanced FC development aligned with the hierarchical brain organization along the sensorimotor-association (S-A) axis demonstrated superior cognitive performance compared to those with other patterns. These patterns were replicated in the Human Connectome Project Development (HCP-D) cohort, confirming their robustness. Further analysis revealed associations between FC development and gene expression, with enriched genes linked to neural differentiation, synaptogenesis, and myelination. These findings suggest that spatial heterogeneity in FC development reflects underlying cortical microstructure and hierarchical cortical organization, underscoring its critical role in understanding neurocognitive maturation and individual variability during youth.

neuroscience↗

bioRxiv2024

Reproducible Sex Differences in Personalized Functional Network Topography in Youth

BackgroundA key step towards understanding psychiatric disorders that disproportionately impact female mental health is delineating the emergence of sex-specific patterns of brain organization at the critical transition from childhood to adolescence. Prior work suggests that individual differences in the spatial organization of functional brain networks across the cortex are associated with psychopathology and differ systematically by sex. AimsWe aimed to evaluate the impact of sex on the spatial organization of person-specific functional brain networks. MethodWe leveraged person-specific atlases of functional brain networks defined using non-negative matrix factorization in a sample of n = 6437 youths from the Adolescent Brain Cognitive Development Study. Across independent discovery and replication samples, we used generalized additive models to uncover associations between sex and the spatial layout ("topography") of personalized functional networks (PFNs). Next, we trained support vector machines to classify participants sex from multivariate patterns of PFN topography. Finally, we leveraged transcriptomic data from the Allen Human Brain Atlas to evaluate spatial correlations between sex differences in PFN topography and gene expression. ResultsSex differences in PFN topography were greatest in association networks including the fronto-parietal, ventral attention, and default mode networks. Machine learning models trained on participants PFNs were able to classify participant sex with high accuracy. Brain regions with the greatest sex differences in PFN topography were enriched in expression of X-linked genes as well as genes expressed in astrocytes and excitatory neurons. ConclusionsSex differences in PFN topography are robust, replicate across large-scale samples of youth, and are associated with expression patterns of X-linked genes. These results suggest a potential contributor to the female-biased risk in depressive and anxiety disorders that emerge at the transition from childhood to adolescence.

neuroscience↗

bioRxiv2024

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

Structured AbstractO_ST_ABSINTRODUCTIONC_ST_ABSThe effects of sex, race, and Apolipoprotein E (APOE) - Alzheimers disease (AD) risk factors - on white matter integrity are not well characterized. METHODSDiffusion MRI data from nine well-established longitudinal cohorts of aging were free-water (FW)-corrected and harmonized. This dataset included 4,702 participants (age=73.06 {+/-} 9.75) with 9,671 imaging sessions over time. FW and FW-corrected fractional anisotropy (FAFWcorr) were used to assess differences in white matter microstructure by sex, race, and APOE-{varepsilon}4 carrier status. RESULTSSex differences in FAFWcorr in association and projection tracts, racial differences in FAFWcorr in projection tracts, and APOE-{varepsilon}4 differences in FW limbic and occipital transcallosal tracts were most pronounced. DISCUSSIONThere are prominent differences in white matter microstructure by sex, race, and APOE- {varepsilon}4 carrier status. This work adds to our understanding of disparities in AD. Additional work to understand the etiology of these differences is warranted. HighlightsO_LISex, race, and APOE-{varepsilon}4 carrier status relate to white matter microstructural integrity C_LIO_LIFemales generally have lower FAFWcorr compared to males C_LIO_LINon-Hispanic Black adults generally have lower FAFWcorr than non-Hispanic White adults C_LIO_LIAPOE-{varepsilon}4 carriers tended to have higher FW than non-carriers C_LI Research in Context Systematic ReviewThe authors used PubMed and Google Scholar to review literature that used conventional and free-water (FW)-corrected microstructural metrics to evaluate sex, race, and APOE-{varepsilon}4 differences in white matter microstructure. While studies have previously explored differences by sex and APOE-{varepsilon}4 status, less is known about racial differences and no large-scale FW-corrected analysis has been performed. InterpretationSex and race were more associated with FAFWcorr while APOE-{varepsilon}4 status was associated with FW metrics. Association, projection, limbic, and occipital transcallosal tracts showed the greatest differences. Future DirectionFuture studies to determine the biological and social pathways that lead to sex, racial, and APOE-{varepsilon}4 differences are warranted. Consent StatementAll participants provided informed consent in their respective cohort studies.

neuroscience↗

bioRxiv2024

pNet: A toolbox for personalized functional networks modeling

Personalized functional networks (FNs) derived from functional magnetic resonance imaging (fMRI) data are useful for characterizing individual variations in the brain functional topography associated with the brain development, aging, and disorders. To facilitate applications of the personalized FNs with enhanced reliability and reproducibility, we develop an open-source toolbox that is user-friendly, extendable, and includes rigorous quality control (QC), featuring multiple user interfaces (graphics, command line, and a step-by-step guideline) and job-scheduling for high performance computing (HPC) clusters. Particularly, the toolbox, named personalized functional network modeling (pNet), takes fMRI inputs in either volumetric or surface type, ensuring compatibility with multiple fMRI data formats, and computes personalized FNs using two distinct modeling methods: one method optimizes the functional coherence of FNs, while the other enhances their independence. Additionally, the toolbox provides HTML-based reports for QC and visualization of personalized FNs. The toolbox is developed in both MATLAB and Python platforms with a modular design to facilitate extension and modification by users familiar with either programming language. We have evaluated the toolbox on two fMRI datasets and demonstrated its effectiveness and user-friendliness with interactive and scripting examples. pNet is publicly available at https://github.com/MLDataAnalytics/pNet.

neuroscience↗

bioRxiv2023

Development of White Matter Fiber Covariance Networks Supports Executive Function in Youth

The white matter architecture of the human brain undergoes substantial development throughout childhood and adolescence, allowing for more efficient signaling between brain regions that support executive function. Increasingly, the field understands grey matter development as a spatially and temporally coordinated mechanism that follows hierarchically organized gradients of change. While white matter development also appears asynchronous, previous studies have largely relied on anatomical atlases to characterize white matter tracts, precluding a direct assessment of how white matter structure is spatially and temporally coordinated. Here, we leveraged advances in diffusion modeling and unsupervised machine learning to delineate white matter fiber covariance networks comprised of structurally similar areas of white matter in a cross-sectional sample of 939 youth aged 8-22 years. We then evaluated associations between fiber covariance network structural properties with both age and executive function using generalized additive models. The identified fiber covariance networks aligned with the known architecture of white matter while simultaneously capturing novel spatial patterns of coordinated maturation. Fiber covariance networks showed heterochronous increases in fiber density and cross section that generally followed hierarchically organized temporal patterns of cortical development, with the greatest increases in unimodal sensorimotor networks and the most prolonged increases in superior and anterior transmodal networks. Notably, we found that executive function was associated with structural features of limbic and association networks. Taken together, this study delineates data-driven patterns of white matter network development that support cognition and align with major axes of brain maturation.

neuroscience↗

bioRxiv2022

The Radiogenomic and Spatiogenomic Landscapes of Glioblastoma, and Their Relationship to Oncogenic Drivers

Glioblastoma (GBM) is well-known for its molecular and spatial heterogeneity, which poses a challenge for precision therapies and clinical trial stratification. Here, in a comprehensive radiogenomics study of 358 GBMs, we investigated the associations between the imaging and spatial characteristics of the tumors with their cancer gene mutation status, as well as with the cross-sectionally inferred likely order of mutational events. We show that cross-validated machine learning analysis of multi-parametric MRI scans results in distinctive in vivo imaging signatures of several mutations, which are relatively more distinctive in homogeneous tumors which harbor only one of these mutations. These imaging signatures offer mechanistic insights into how various mutations influence the phenotype of the tumor and its surrounding infiltrated brain tissue via neovascularization and vascular leakage, increased cell density, invasion and migration, and other characteristics captured by respective imaging features. Furthermore, we found that spatial location and tumor distribution vary, depending on the GBMs molecular characteristics. Finally, distinct imaging and spatial characteristics were associated with cross-sectionally estimated evolutionary trajectories of the tumors. Collectively, our study establishes a panel of in vivo and clinically accessible imaging-AI biomarkers of GBM that reflect their molecular composition and oncogenic drivers.

bioengineering↗