arXiv subjects

Neda Jahanshad

Publications and source records attributed to Neda Jahanshad.

At least 19 recordsLinked to original sources

arXiv2025

FedDAPL: Toward Client-Private Generalization in Federated Learning

Federated Learning (FL) trains models locally at each research center or clinic and aggregates only model updates, making it a natural fit for medical imaging, where strict privacy laws forbid raw data sharing. A major obstacle is scanner-induced domain shift: non-biological variations in hardware or acquisition protocols can cause models to fail on external sites. Most harmonization methods correct this shift by directly comparing data across sites, conflicting with FL's privacy constraints. Domain Generalization (DG) offers a privacy-friendly alternative - learning site-invariant representations without sharing raw data - but standard DG pipelines still assume centralized access to multi-site data, again violating FL's guarantees. This paper meets these difficulties with a straightforward integration of a Domain-Adversarial Neural Network (DANN) within the FL process. After demonstrating that a naive federated DANN fails to converge, we propose a proximal regularization method that stabilizes adversarial training among clients. Experiments on T1-weighted 3-D brain MRIs from the OpenBHB dataset, performing brain-age prediction on participants aged 6-64 y (mean 22+/-6 y; 45 percent male) in training and 6-79 y (mean 19+/-13 y; 55 percent male) in validation, show that training on 15 sites and testing on 19 unseen sites yields superior cross-site generalization over FedAvg and ERM while preserving data privacy.

cs.LG↗

arXiv2025

Classification of Major Depressive Disorder Using Vertex-Wise Brain Sulcal Depth, Curvature, and Thickness with a Deep and a Shallow Learning Model

Major depressive disorder (MDD) is a complex psychiatric disorder that affects the lives of hundreds of millions of individuals around the globe. Even today, researchers debate if morphological alterations in the brain are linked to MDD, likely due to the heterogeneity of this disorder. The application of deep learning tools to neuroimaging data, capable of capturing complex non-linear patterns, has the potential to provide diagnostic and predictive biomarkers for MDD. However, previous attempts to demarcate MDD patients and healthy controls (HC) based on segmented cortical features via linear machine learning approaches have reported low accuracies. Here, we used globally representative data from the ENIGMA-MDD working group containing 7,012 participants from 30 sites (N=2,772 MDD and N=4,240 HC), which allows a comprehensive analysis with generalizable results. Based on the hypothesis that integration of vertex-wise cortical features can improve classification performance, we evaluated the classification of a DenseNet and a Support Vector Machine (SVM), with the expectation that the former would outperform the latter. We found that both classifiers exhibited close to chance performance (balanced accuracy DenseNet: 51%; SVM: 53%), when estimated on unseen sites. Slightly higher classification performance (balanced accuracy DenseNet: 58%; SVM: 55%) was found when the cross-validation folds contained subjects from all sites, indicating site effect. In conclusion, the integration of vertex-wise morphometric features and the use of the non-linear classifier did not lead to the differentiability between MDD and HC. Our results support the notion that MDD classification on this combination of such features and classifiers is unfeasible. Perhaps more sophisticated integration of multimodal information may lead to a higher performance in this diagnostic task.

q-bio.QM↗

arXiv2024

MICCAI-CDMRI 2023 QuantConn Challenge Findings on Achieving Robust Quantitative Connectivity through Harmonized Preprocessing of Diffusion MRI

White matter alterations are increasingly implicated in neurological diseases and their progression. International-scale studies use diffusion-weighted magnetic resonance imaging (DW-MRI) to qualitatively identify changes in white matter microstructure and connectivity. Yet, quantitative analysis of DW-MRI data is hindered by inconsistencies stemming from varying acquisition protocols. There is a pressing need to harmonize the preprocessing of DW-MRI datasets to ensure the derivation of robust quantitative diffusion metrics across acquisitions. In the MICCAI-CDMRI 2023 QuantConn challenge, participants were provided raw data from the same individuals collected on the same scanner but with two different acquisitions and tasked with preprocessing the DW-MRI to minimize acquisition differences while retaining biological variation. Submissions are evaluated on the reproducibility and comparability of cross-acquisition bundle-wise microstructure measures, bundle shape features, and connectomics. The key innovations of the QuantConn challenge are that (1) we assess bundles and tractography in the context of harmonization for the first time, (2) we assess connectomics in the context of harmonization for the first time, and (3) we have 10x additional subjects over prior harmonization challenge, MUSHAC and 100x over SuperMUDI. We find that bundle surface area, fractional anisotropy, connectome assortativity, betweenness centrality, edge count, modularity, nodal strength, and participation coefficient measures are most biased by acquisition and that machine learning voxel-wise correction, RISH mapping, and NeSH methods effectively reduce these biases. In addition, microstructure measures AD, MD, RD, bundle length, connectome density, efficiency, and path length are least biased by these acquisition differences.

physics.med-ph↗

arXiv2024

Synthesizing study-specific controls using generative models on open access datasets for harmonized multi-study analyses

Neuroimaging consortia can enhance reliability and generalizability of findings by pooling data across studies to achieve larger sample sizes. To adjust for site and MRI protocol effects, imaging datasets are often harmonized based on healthy controls. When data from a control group were not collected, statistical harmonization options are limited as patient characteristics and acquisition-related variables may be confounded. Here, in a multi-study neuroimaging analysis of Alzheimer's patients and controls, we tested whether it is possible to generate synthetic control MRIs. For one case-control study, we used a generative adversarial model for style-based harmonization to generate site-specific controls. Downstream feature extraction, statistical harmonization and group-level multi-study case-control and case-only analyses were performed twice, using either true or synthetic controls. All effect sizes using synthetic controls overlapped with those based on true study controls. This line of work may facilitate wider inclusion of case-only studies in multi-study consortia.

q-bio.QM↗

arXiv2023

Tackling the dimensions in imaging genetics with CLUB-PLS

A major challenge in imaging genetics and similar fields is to link high-dimensional data in one domain, e.g., genetic data, to high dimensional data in a second domain, e.g., brain imaging data. The standard approach in the area are mass univariate analyses across genetic factors and imaging phenotypes. That entails executing one genome-wide association study (GWAS) for each pre-defined imaging measure. Although this approach has been tremendously successful, one shortcoming is that phenotypes must be pre-defined. Consequently, effects that are not confined to pre-selected regions of interest or that reflect larger brain-wide patterns can easily be missed. In this work we introduce a Partial Least Squares (PLS)-based framework, which we term Cluster-Bootstrap PLS (CLUB-PLS), that can work with large input dimensions in both domains as well as with large sample sizes. One key factor of the framework is to use cluster bootstrap to provide robust statistics for single input features in both domains. We applied CLUB-PLS to investigating the genetic basis of surface area and cortical thickness in a sample of 33,000 subjects from the UK Biobank. We found 107 genome-wide significant locus-phenotype pairs that are linked to 386 different genes. We found that a vast majority of these loci could be technically validated at a high rate: using classic GWAS or Genome-Wide Inferred Statistics (GWIS) we found that 85 locus-phenotype pairs exceeded the genome-wide suggestive (P<1e-05) threshold.

q-bio.GN↗

arXiv2023

Linking Symptom Inventories using Semantic Textual Similarity

An extensive library of symptom inventories has been developed over time to measure clinical symptoms, but this variety has led to several long standing issues. Most notably, results drawn from different settings and studies are not comparable, which limits reproducibility. Here, we present an artificial intelligence (AI) approach using semantic textual similarity (STS) to link symptoms and scores across previously incongruous symptom inventories. We tested the ability of four pre-trained STS models to screen thousands of symptom description pairs for related content - a challenging task typically requiring expert panels. Models were tasked to predict symptom severity across four different inventories for 6,607 participants drawn from 16 international data sources. The STS approach achieved 74.8% accuracy across five tasks, outperforming other models tested. This work suggests that incorporating contextual, semantic information can assist expert decision-making processes, yielding gains for both general and disease-specific clinical assessment.

cs.CL↗

arXiv2023

Partial Identification of Dose Responses with Hidden Confounders

Inferring causal effects of continuous-valued treatments from observational data is a crucial task promising to better inform policy- and decision-makers. A critical assumption needed to identify these effects is that all confounding variables -- causal parents of both the treatment and the outcome -- are included as covariates. Unfortunately, given observational data alone, we cannot know with certainty that this criterion is satisfied. Sensitivity analyses provide principled ways to give bounds on causal estimates when confounding variables are hidden. While much attention is focused on sensitivity analyses for discrete-valued treatments, much less is paid to continuous-valued treatments. We present novel methodology to bound both average and conditional average continuous-valued treatment-effect estimates when they cannot be point identified due to hidden confounding. A semi-synthetic benchmark on multiple datasets shows our method giving tighter coverage of the true dose-response curve than a recently proposed continuous sensitivity model and baselines. Finally, we apply our method to a real-world observational case study to demonstrate the value of identifying dose-dependent causal effects.

stat.ME↗

arXiv2023

A Comprehensive Corpus Callosum Segmentation Tool for Detecting Callosal Abnormalities and Genetic Associations from Multi Contrast MRIs

Structural alterations of the midsagittal corpus callosum (midCC) have been associated with a wide range of brain disorders. The midCC is visible on most MRI contrasts and in many acquisitions with a limited field-of-view. Here, we present an automated tool for segmenting and assessing the shape of the midCC from T1w, T2w, and FLAIR images. We train a UNet on images from multiple public datasets to obtain midCC segmentations. A quality control algorithm is also built-in, trained on the midCC shape features. We calculate intraclass correlations (ICC) and average Dice scores in a test-retest dataset to assess segmentation reliability. We test our segmentation on poor quality and partial brain scans. We highlight the biological significance of our extracted features using data from over 40,000 individuals from the UK Biobank; we classify clinically defined shape abnormalities and perform genetic analyses.

q-bio.QM↗

arXiv2022

Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures

Machine learning (ML) techniques have gained popularity in the neuroimaging field due to their potential for classifying neuropsychiatric disorders. However, the diagnostic predictive power of the existing algorithms has been limited by small sample sizes, lack of representativeness, data leakage, and/or overfitting. Here, we overcome these limitations with the largest multi-site sample size to date (n=5,356) to provide a generalizable ML classification benchmark of major depressive disorder (MDD). Using brain measures from standardized ENIGMA analysis pipelines in FreeSurfer, we were able to classify MDD vs healthy controls (HC) with around 62% balanced accuracy, but when harmonizing the data using ComBat balanced accuracy dropped to approximately 52%. Similar results were observed in stratified groups according to age of onset, antidepressant use, number of episodes and sex. Future studies incorporating higher dimensional brain imaging/phenotype features, and/or using more advanced machine and deep learning methods may achieve more encouraging prospects.

q-bio.QM↗

arXiv2020

3D Grid-Attention Networks for Interpretable Age and Alzheimer's Disease Prediction from Structural MRI

We propose an interpretable 3D Grid-Attention deep neural network that can accurately predict a person's age and whether they have Alzheimer's disease (AD) from a structural brain MRI scan. Building on a 3D convolutional neural network, we added two attention modules at different layers of abstraction, so that features learned are spatially related to the global features for the task. The attention layers allow the network to focus on brain regions relevant to the task, while masking out irrelevant or noisy regions. In evaluations based on 4,561 3-Tesla T1-weighted MRI scans from 4 phases of the Alzheimer's Disease Neuroimaging Initiative (ADNI), salience maps for age and AD prediction partially overlapped, but lower-level features overlapped more than higher-level features. The brain age prediction network also distinguished AD and healthy control groups better than another state-of-the-art method. The resulting visual analyses can distinguish interpretable feature patterns that are important for predicting clinical diagnosis. Future work is needed to test performance across scanners and populations.

q-bio.TO↗

arXiv2019

A Fast, Accurate Two-Step Linear Mixed Model for Genetic Analysis Applied to Repeat MRI Measurements

Large-scale biobanks are being collected around the world in efforts to better understand human health and risk factors for disease. They often survey hundreds of thousands of individuals, combining questionnaires with clinical, genetic, demographic, and imaging assessments; some of this data may be collected longitudinally. Genetic associations analysis of such datasets requires methods to properly handle relatedness, population structure and other types of biases introduced by confounders. Most popular and accurate approaches rely on linear mixed model (LMM) algorithms, which are iterative and computational complexity of each iteration scales by the square of the sample size, slowing the pace of discoveries (up to several days for single trait analysis), and, furthermore, limiting the use of repeat phenotypic measurements. Here, we describe our new, non-iterative, much faster and accurate Two-Step Linear Mixed Model (Two-Step LMM) approach, that has a computational complexity that scales linearly with sample size. We show that the first step retains accurate estimates of the heritability (the proportion of the trait variance explained by additive genetic factors), even when increasingly complex genetic relationships between individuals are modeled. Second step provides a faster framework to obtain the effect sizes of covariates in regression model. We applied Two-Step LMM to real data from the UK Biobank, which recently released genotyping information and processed MRI data from 9,725 individuals. We used the left and right hippocampus volume (HV) as repeated measures, and observed increased and more accurate heritability estimation, consistent with simulations.

q-bio.QM↗

arXiv2018

A Continuous Model of Cortical Connectivity

We present a continuous model for structural brain connectivity based on the Poisson point process. The model treats each streamline curve in a tractography as an observed event in connectome space, here a product space of cortical white matter boundaries. We approximate the model parameter via kernel density estimation. To deal with the heavy computational burden, we develop a fast parameter estimation method by pre-computing associated Legendre products of the data, leveraging properties of the spherical heat kernel. We show how our approach can be used to assess the quality of cortical parcellations with respect to connectivty. We further present empirical results that suggest the discrete connectomes derived from our model have substantially higher test-retest reliability compared to standard methods.

q-bio.NC↗

arXiv2017

Simultaneous Matrix Diagonalization for Structural Brain Networks Classification

This paper considers the problem of brain disease classification based on connectome data. A connectome is a network representation of a human brain. The typical connectome classification problem is very challenging because of the small sample size and high dimensionality of the data. We propose to use simultaneous approximate diagonalization of adjacency matrices in order to compute their eigenstructures in more stable way. The obtained approximate eigenvalues are further used as features for classification. The proposed approach is demonstrated to be efficient for detection of Alzheimer's disease, outperforming simple baselines and competing with state-of-the-art approaches to brain disease classification.

stat.ML↗

arXiv2017

Heritability estimates on resting state fMRI data using the ENIGMA analysis pipeline

Big data initiatives such as the Enhancing NeuroImaging Genetics through Meta-Analysis consortium (ENIGMA), combine data collected by independent studies worldwide to achieve more accurate estimates of effect sizes and more reliable and reproducible outcomes. Such efforts require harmonized analyses protocols to consistently extract phenotypes. Even so, challenges include wide variability of fMRI protocols and scanner platforms; this leads to site-to-site variance in quality, resolution and temporal signal-to-noise ratio (tSNR). An effective harmonization should provide optimal measures for data of different qualities. We developed a multi-site rsfMRI analysis pipeline to allow research groups around the world to process rsfMRI scans in a harmonized way, to extract consistent and quantitative measurements of connectivity and to perform coordinated statistical tests. We used the single-modality ENIGMA rsfMRI pipeline based on model-free Marchenko-Pastor PCA based denoising to verify and replicate findings of significant heritability of measures from resting state networks. We analyzed two independent cohorts, GOBS (Genetics of Brain Structure) and HCP (the Human Connectome Project), which collected data using conventional and connectomics oriented fMRI protocols. We used seed-based connectivity and dual-regression approaches to show that rsfMRI signal is consistently heritable across twenty major functional network measures. Heritability values of 20-40% were observed across both cohorts.

q-bio.NC↗

arXiv2017

Evaluating 35 Methods to Generate Structural Connectomes Using Pairwise Classification

There is no consensus on how to construct structural brain networks from diffusion MRI. How variations in pre-processing steps affect network reliability and its ability to distinguish subjects remains opaque. In this work, we address this issue by comparing 35 structural connectome-building pipelines. We vary diffusion reconstruction models, tractography algorithms and parcellations. Next, we classify structural connectome pairs as either belonging to the same individual or not. Connectome weights and eight topological derivative measures form our feature set. For experiments, we use three test-retest datasets from the Consortium for Reliability and Reproducibility (CoRR) comprised of a total of 105 individuals. We also compare pairwise classification results to a commonly used parametric test-retest measure, Intraclass Correlation Coefficient (ICC).

q-bio.NC↗

arXiv2017

Classification of Major Depressive Disorder via Multi-Site Weighted LASSO Model

Large-scale collaborative analysis of brain imaging data, in psychiatry and neu-rology, offers a new source of statistical power to discover features that boost ac-curacy in disease classification, differential diagnosis, and outcome prediction. However, due to data privacy regulations or limited accessibility to large datasets across the world, it is challenging to efficiently integrate distributed information. Here we propose a novel classification framework through multi-site weighted LASSO: each site performs an iterative weighted LASSO for feature selection separately. Within each iteration, the classification result and the selected features are collected to update the weighting parameters for each feature. This new weight is used to guide the LASSO process at the next iteration. Only the fea-tures that help to improve the classification accuracy are preserved. In tests on da-ta from five sites (299 patients with major depressive disorder (MDD) and 258 normal controls), our method boosted classification accuracy for MDD by 4.9% on average. This result shows the potential of the proposed new strategy as an ef-fective and practical collaborative platform for machine learning on large scale distributed imaging and biobank data.

cs.LG↗

arXiv2017

Large-scale Feature Selection of Risk Genetic Factors for Alzheimer's Disease via Distributed Group Lasso Regression

Genome-wide association studies (GWAS) have achieved great success in the genetic study of Alzheimer's disease (AD). Collaborative imaging genetics studies across different research institutions show the effectiveness of detecting genetic risk factors. However, the high dimensionality of GWAS data poses significant challenges in detecting risk SNPs for AD. Selecting relevant features is crucial in predicting the response variable. In this study, we propose a novel Distributed Feature Selection Framework (DFSF) to conduct the large-scale imaging genetics studies across multiple institutions. To speed up the learning process, we propose a family of distributed group Lasso screening rules to identify irrelevant features and remove them from the optimization. Then we select the relevant group features by performing the group Lasso feature selection process in a sequence of parameters. Finally, we employ the stability selection to rank the top risk SNPs that might help detect the early stage of AD. To the best of our knowledge, this is the first distributed feature selection model integrated with group Lasso feature selection as well as detecting the risk genetic factors across multiple research institutions system. Empirical studies are conducted on 809 subjects with 5.9 million SNPs which are distributed across several individual institutions, demonstrating the efficiency and effectiveness of the proposed method.

cs.LG↗

arXiv2017

A Restaurant Process Mixture Model for Connectivity Based Parcellation of the Cortex

One of the primary objectives of human brain mapping is the division of the cortical surface into functionally distinct regions, i.e. parcellation. While it is generally agreed that at macro-scale different regions of the cortex have different functions, the exact number and configuration of these regions is not known. Methods for the discovery of these regions are thus important, particularly as the volume of available information grows. Towards this end, we present a parcellation method based on a Bayesian non-parametric mixture model of cortical connectivity.

q-bio.NC↗