arXiv subjects

Suprateek Kundu

Publications and source records attributed to Suprateek Kundu.

At least 19 recordsLinked to original sources

arXiv2026

Robust Community Detection for Noisy Networks with Covariates: Application to Functional Brain Networks

Community detection is fundamental to understanding the modular organization in functional brain networks, yet noise in neuroimaging-derived networks and auxiliary node-level covariates pose critical challenges. Existing methods typically either assume networks are noise-free or ignore covariate information. We propose a Bayesian framework for recovering a shared latent community structure from multiple noisy network realizations and auxiliary covariates. The model combines a degree-corrected stochastic block model for the latent network, a block-structured noise model linking noisy observations to latent edges, and a covariate cluster model for node-level attributes. This specification allows anatomical or functional attributes of regions of interest to contribute information when network signals are weak or sparse. We develop an efficient Markov chain Monte Carlo algorithm for posterior sampling and select the number of communities using the widely applicable information criterion, avoiding prior specification of this quantity. Simulation studies demonstrate improved community recovery relative to existing methods across varying noise levels, covariate signal strengths, and numbers of noisy networks, with larger gains when network noise is moderate to high or only a small number of noisy networks is available. Applications to functional brain networks from the Alzheimer's Disease Neuroimaging Initiative and the Human Connectome Project identify biologically interpretable structures and capture disease-related reorganization and individual-level variation.

stat.ME↗

arXiv2026

Bayesian Tensor-on-Tensor Varying Coefficient Model for Forecasting Alzheimer's Disease Progression

We propose a novel tensor-on-tensor modeling framework that flexibly models nonlinear voxel-level relationships using Gaussian process (GP) priors, while incorporating the spatial structure of the output tensor through low-rank tensor-based coefficients. Spatial heterogeneity is captured through patch-to-voxel mappings, enabling each output voxel to depend on its spatial neighborhood. The proposed interpretable and flexible Bayesian tensor-on-tensor framework is able to capture nonlinearity, spatial information, and spatial heterogeneity. We develop an efficient Markov chain Monte Carlo (MCMC) algorithm that exploits parallel structure to sample voxel-specific GP atoms and update low-rank tensor coefficients. Extensive simulations reveal advantages of the proposed approach over existing methods in terms of coefficient estimation, inference, prediction, and scalability to high-dimensional images. Applied to longitudinal image prediction with T1-weighted MRIs from the Alzheimer's Disease Neuroimaging Initiative (ADNI), the proposed method can accurately forecast future cortical thickness. The predicted images also enable reliable prediction of brain aging, underscoring their biological relevance. Overall, the ADNI analysis highlights the model's ability to forecast future neurobiological changes that has important implications for early detection of AD.

stat.ME↗

arXiv2026

Spatially-informed Image Harmonization Results in Improved Scanner Effect Removal and Prediction

We propose a novel data harmonization approach known as Tensor-ComBat (TC) for structural neuroimaging data. Tensor-Combat is a novel spatially aware harmonization method that aims to estimate and remove unwanted technical variation between voxel-level images from different study sites or scanners. Tensor-ComBat uses a Bayesian tensor response regression (BTRR) model to estimate spatially distributed scanner effects via a low-rank PARAFAC decomposition on the model coefficients, and subsequently removes these scanner effects via a post-hoc ComBat harmonization step. Unlike the classical ComBat method that treats the ROIs or voxels in the image as interchangeable, the Tensor-ComBat approach incorporates the information about the spatial configurations of imaging voxels when estimating the model parameters, resulting an improved harmonization pipeline. The proposed Tensor-ComBat method is fit using a Markov chain Monte Carlo (MCMC) that is not only able to produce point estimates, but also able to quantify uncertainty associated with these estimates. Due to the fully Bayesian implementation of Tensor-ComBat, it is able to perform inference related to significant spatially distributed scanner effects and/or biological effects that is not straightforward under existing methods. The methods is applied to over 2100 T1w-MRI scans in ADNI-1 that illustrates greater scanner effect removal, improved biological prediction, and superior reproducibility compared to state-of-the-art approaches such as ComBat.

stat.ME↗

arXiv2026

Bayesian Scalar-on-Tensor Quantile Regression for Longitudinal Data on Alzheimer's Disease

As a general and robust alternative to traditional mean regression models, quantile regression avoids the assumption of normally distributed errors, making it a versatile choice when modeling outcomes such as cognitive scores that typically have skewed distributions. Motivated by an application to Alzheimer's disease data where the aim is to explore how brain-behavior associations change over time, we propose a novel Bayesian tensor quantile regression for high-dimensional longitudinal imaging data. The proposed approach distinguishes between effects that are consistent across visits and patterns unique to each visit, contributing to the overall longitudinal trajectory. A low-rank decomposition is employed on the tensor coefficients which reduces dimensionality and preserves spatial configurations of the imaging voxels. We incorporate multiway shrinkage priors to model the visit-invariant tensor coefficients and variable selection priors on the tensor margins of the visit-specific effects. For posterior inference, we develop a computationally efficient Markov chain Monte Carlo sampling algorithm. Simulation studies reveal significant improvements in parameter estimation, feature selection, and prediction performance when compared with existing approaches. In the analysis of the Alzheimer's disease data, the flexibility of our modeling approach brings new insights as it provides a fuller picture of the relationship between the imaging voxels and the quantile distributions of the cognitive scores.

stat.ME↗

arXiv2026

Risk Prediction in Cancer Imaging Using Enriched Radiomics Features

Background: We aim to develop enriched radiomics features that integrate classical structural radiomics with novel functional radiomics derived from liver MRI for diagnosis and risk stratification in liver cancer. The proposed framework leverages enhancement pattern mapping (EPM) images to provide an automated and robust radiomics representation that captures intratumoral heterogeneity through pixel-level functional information. Methods: Pixel-wise EPM data reflecting blood perfusion were extracted from T1-weighted MRI scans. Classical structural radiomics features were extracted via existing software such as PyRadiomics. In addition, empirical quantiles of EPM values over all pixels within the image, and then smoothed using suitable basis. The smoothed quantiles, along with the classical structural quantiles, are used as functional radiomics features for diagnostic classification and tumor grade stratification, using L1-penalized logistic model that automatically downweights the contribution of the irrelevant features. Further, we conducted longitudinal analyses using Bayesian tensor response regression, which enables spatial smoothing and parsimonious modeling of temporally evolving imaging patterns. Results: The enriched radiomics features illustrate higher diagnostic classification performance (AUC=0.96, sensitivity> 0.8) and superior tumor grade stratification accuracy (AUC=0.87, sensitivity=0.8) compared to alternate radiomics features. Moreover, we find that the proportion of lesion pixels with significant reduction in EPM values over time is considerably higher (median = 0.12) in aggressive lesions versus stable or mildly aggressive lesions (median = 0.025). Conclusion: The enriched novel radiomics features can potentially replace classical radiomics analysis and be used for imaging biomarkers in cross-sectional and in longitudinal cancer imaging studies.

stat.AP↗

arXiv2025

DeepJIVE: Learning Joint and Individual Variation Explained from Multimodal Data Using Deep Learning

Conventional multimodal data integration methods provide a comprehensive assessment of the shared or unique structure within each individual data type but suffer from several limitations such as the inability to handle high-dimensional data and identify nonlinear structures. In this paper, we introduce DeepJIVE, a deep-learning approach to performing Joint and Individual Variance Explained (JIVE). We perform mathematical derivation and experimental validations using both synthetic and real-world 1D, 2D, and 3D datasets. Different strategies of achieving the identity and orthogonality constraints for DeepJIVE were explored, resulting in three viable loss functions. We found that DeepJIVE can successfully uncover joint and individual variations of multimodal datasets. Our application of DeepJIVE to the Alzheimer's Disease Neuroimaging Initiative (ADNI) also identified biologically plausible covariation patterns between the amyloid positron emission tomography (PET) and magnetic resonance (MR) images. In conclusion, the proposed DeepJIVE can be a useful tool for multimodal data analysis.

cs.CV↗

arXiv2024

Flexible Bayesian Nonparametric Product Mixtures for Multi-scale Functional Clustering

There is a rich literature on clustering functional data with applications to time-series modeling, trajectory data, and even spatio-temporal applications. However, existing methods routinely perform global clustering that enforces identical atom values within the same cluster. Such grouping may be inadequate for high-dimensional functions, where the clustering patterns may change between the more dominant high-level features and the finer resolution local features. While there is some limited literature on local clustering approaches to deal with the above problems, these methods are typically not scalable to high-dimensional functions, and their theoretical properties are not well-investigated. Focusing on basis expansions for high-dimensional functions, we propose a flexible non-parametric Bayesian approach for multi-resolution clustering. The proposed method imposes independent Dirichlet process (DP) priors on different subsets of basis coefficients that ultimately results in a product of DP mixture priors inducing local clustering. We generalize the approach to incorporate spatially correlated error terms when modeling random spatial functions to provide improved model fitting. An efficient Markov chain Monte Carlo (MCMC) algorithm is developed for implementation. We show posterior consistency properties under the local clustering approach that asymptotically recovers the true density of random functions. Extensive simulations illustrate the improved clustering and function estimation under the proposed method compared to classical approaches. We apply the proposed approach to a spatial transcriptomics application where the goal is to infer clusters of genes with distinct spatial patterns of expressions. Our method makes an important contribution by expanding the limited literature on local clustering methods for high-dimensional functions with theoretical guarantees.

stat.ME↗

arXiv2024

Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend

Fréchet Inception Distance (FID) is a widely used metric for assessing synthetic image quality. It relies on an ImageNet-based feature extractor, making its applicability to medical imaging unclear. A recent trend is to adapt FID to medical imaging through feature extractors trained on medical images. Our study challenges this practice by demonstrating that ImageNet-based extractors are more consistent and aligned with human judgment than their RadImageNet counterparts. We evaluated sixteen StyleGAN2 networks across four medical imaging modalities and four data augmentation techniques with Fréchet distances (FDs) computed using eleven ImageNet or RadImageNet-trained feature extractors. Comparison with human judgment via visual Turing tests revealed that ImageNet-based extractors produced rankings consistent with human judgment, with the FD derived from the ImageNet-trained SwAV extractor significantly correlating with expert evaluations. In contrast, RadImageNet-based rankings were volatile and inconsistent with human judgment. Our findings challenge prevailing assumptions, providing novel evidence that medical image-trained feature extractors do not inherently improve FDs and can even compromise their reliability. Our code is available at https://github.com/mckellwoodland/fid-med-eval.

cs.CV↗

arXiv2024

Heterogeneous Image-based Classification Using Distributional Data Analysis

Diagnostic imaging has gained prominence as potential biomarkers for early detection and diagnosis in a diverse array of disorders including cancer. However, existing methods routinely face challenges arising from various factors such as image heterogeneity. We develop a novel imaging-based distributional data analysis (DDA) approach that incorporates the probability (quantile) distribution of the pixel-level features as covariates. The proposed approach uses a smoothed quantile distribution (via a suitable basis representation) as functional predictors in a scalar-on-functional quantile regression model. Some distinctive features of the proposed approach include the ability to: (i) account for heterogeneity within the image; (ii) incorporate granular information spanning the entire distribution; and (iii) tackle variability in image sizes for unregistered images in cancer applications. Our primary goal is risk prediction in Hepatocellular carcinoma that is achieved via predicting the change in tumor grades at post-diagnostic visits using pre-diagnostic enhancement pattern mapping (EPM) images of the liver. Along the way, the proposed DDA approach is also used for case versus control diagnosis and risk stratification objectives. Our analysis reveals that when coupled with global structural radiomics features derived from the corresponding T1-MRI scans, the proposed smoothed quantile distributions derived from EPM images showed considerable improvements in sensitivity and comparable specificity in contrast to classification based on routinely used summary measures that do not account for image heterogeneity. Given that there are limited predictive modeling approaches based on heterogeneous images in cancer, the proposed method is expected to provide considerable advantages in image-based early detection and risk prediction.

stat.AP↗

arXiv2023

Bayesian Tensor Modeling for Image-based Classification of Alzheimer's Disease

Tensor-based representations are being increasingly used to represent complex data types such as imaging data, due to their appealing properties such as dimension reduction and the preservation of spatial information. Recently, there is a growing literature on using Bayesian scalar-on-tensor regression techniques that use tensor-based representations for high-dimensional and spatially distributed covariates to predict continuous outcomes. However surprisingly, there is limited development on corresponding Bayesian classification methods relying on tensor-valued covariates. Standard approaches that vectorize the image are not desirable due to the loss of spatial structure, and alternate methods that use extracted features from the image in the predictive model may suffer from information loss. We propose a novel data augmentation-based Bayesian classification approach relying on tensor-valued covariates, with a focus on imaging predictors. We propose two data augmentation schemes, one resulting in a support vector machine (SVM) classifier, and another yielding a logistic regression classifier. While both types of classifiers have been proposed independently in literature, our contribution is to extend such existing methodology to accommodate high-dimensional tensor valued predictors that involve low rank decompositions of the coefficient matrix while preserving the spatial information in the image. An efficient Markov chain Monte Carlo (MCMC) algorithm is developed for implementing these methods. Simulation studies show significant improvements in classification accuracy and parameter estimation compared to routinely used classification methods. We further illustrate our method in a neuroimaging application using cortical thickness MRI data from Alzheimer's Disease Neuroimaging Initiative, with results displaying better classification accuracy throughout several classification tasks.

stat.ME↗

arXiv2023

A Wasserstein-type Distance for Gaussian Mixtures on Vector Bundles with Applications to Shape Analysis

This paper uses sample data to study the problem of comparing populations on finite-dimensional parallelizable Riemannian manifolds and more general trivial vector bundles. Utilizing triviality, our framework represents populations as mixtures of Gaussians on vector bundles and estimates the population parameters using a mode-based clustering algorithm. We derive a Wasserstein-type metric between Gaussian mixtures, adapted to the manifold geometry, in order to compare estimated distributions. Our contributions include an identifiability result for Gaussian mixtures on manifold domains and a convenient characterization of optimal couplings of Gaussian mixtures under the derived metric. We demonstrate these tools on some example domains, including the pre-shape space of planar closed curves, with applications to the shape space of triangles and populations of nanoparticles. In the nanoparticle application, we consider a sequence of populations of particle shapes arising from a manufacturing process, and utilize the Wasserstein-type distance to perform change-point detection.

stat.ME↗

arXiv2023

Bayesian longitudinal tensor response regression for modeling neuroplasticity

A major interest in longitudinal neuroimaging studies involves investigating voxel-level neuroplasticity due to treatment and other factors across visits. However, traditional voxel-wise methods are beset with several pitfalls, which can compromise the accuracy of these approaches. We propose a novel Bayesian tensor response regression approach for longitudinal imaging data, which pools information across spatially-distributed voxels to infer significant changes while adjusting for covariates. The proposed method, which is implemented using Markov chain Monte Carlo (MCMC) sampling, utilizes low-rank decomposition to reduce dimensionality and preserve spatial configurations of voxels when estimating coefficients. It also enables feature selection via joint credible regions which respect the shape of the posterior distributions for more accurate inference. In addition to group level inferences, the method is able to infer individual-level neuroplasticity, allowing for examination of personalized disease or recovery trajectories. The advantages of the proposed approach in terms of prediction and feature selection over voxel-wise regression are highlighted via extensive simulation studies. Subsequently, we apply the approach to a longitudinal Aphasia dataset consisting of task functional MRI images from a group of subjects who were administered either a control intervention or intention treatment at baseline and were followed up over subsequent visits. Our analysis revealed that while the control therapy showed long-term increases in brain activity, the intention treatment produced predominantly short-term changes, both of which were concentrated in distinct localized regions. In contrast, the voxel-wise regression failed to detect any significant neuroplasticity after multiplicity adjustments, which is biologically implausible and implies lack of power.

q-bio.NC↗

arXiv2022

Accounting for Temporal Variability in Functional Magnetic Resonance Imaging Improves Prediction of Intelligence

Neuroimaging-based prediction methods for intelligence and cognitive abilities have seen a rapid development in literature. Among different neuroimaging modalities, prediction based on functional connectivity (FC) has shown great promise. Most literature has focused on prediction using static FC, but there are limited investigations on the merits of such analysis compared to prediction based on dynamic FC or region level functional magnetic resonance imaging (fMRI) times series that encode temporal variability. To account for the temporal dynamics in fMRI data, we propose a deep neural network involving bi-directional long short-term memory (bi-LSTM) approach that also incorporates feature selection mechanism. The proposed pipeline is implemented via an efficient GPU computation framework and applied to predict intelligence scores based on region level fMRI time series as well as dynamic FC. We compare the prediction performance for different intelligence measures based on static FC, dynamic FC, and region level time series acquired from the Adolescent Brain Cognitive Development (ABCD) study involving close to 7000 individuals. Our detailed analysis illustrates that static FC consistently has inferior prediction performance compared to region level time series or dynamic FC for unimodal rest and task fMRI experiments, and in almost all cases using a combination of task and rest features. In addition, the proposed bi-LSTM pipeline based on region level time series identifies several shared and differential important brain regions across task and rest fMRI experiments that drive intelligence prediction. A test-retest analysis of the selected features shows strong reliability across cross-validation folds. Given the large sample size from ABCD study, our results provide strong evidence that superior prediction of intelligence can be achieved by accounting for temporal variations in fMRI.

q-bio.NC↗

arXiv2022

High-dimensional Measurement Error Models for Lipschitz Loss

Recently emerging large-scale biomedical data pose exciting opportunities for scientific discoveries. However, the ultrahigh dimensionality and non-negligible measurement errors in the data may create difficulties in estimation. There are limited methods for high-dimensional covariates with measurement error, that usually require knowledge of the noise distribution and focus on linear or generalized linear models. In this work, we develop high-dimensional measurement error models for a class of Lipschitz loss functions that encompasses logistic regression, hinge loss and quantile regression, among others. Our estimator is designed to minimize the $L_1$ norm among all estimators belonging to suitable feasible sets, without requiring any knowledge of the noise distribution. Subsequently, we generalize these estimators to a Lasso analog version that is computationally scalable to higher dimensions. We derive theoretical guarantees in terms of finite sample statistical error bounds and sign consistency, even when the dimensionality increases exponentially with the sample size. Extensive simulation studies demonstrate superior performance compared to existing methods in classification and quantile regression problems. An application to a gender classification task based on brain functional connectivity in the Human Connectome Project data illustrates improved accuracy under our approach, and the ability to reliably identify significant brain connections that drive gender differences.

stat.ME↗

arXiv2022

Evaluating the Performance of StyleGAN2-ADA on Medical Images

Although generative adversarial networks (GANs) have shown promise in medical imaging, they have four main limitations that impeded their utility: computational cost, data requirements, reliable evaluation measures, and training complexity. Our work investigates each of these obstacles in a novel application of StyleGAN2-ADA to high-resolution medical imaging datasets. Our dataset is comprised of liver-containing axial slices from non-contrast and contrast-enhanced computed tomography (CT) scans. Additionally, we utilized four public datasets composed of various imaging modalities. We trained a StyleGAN2 network with transfer learning (from the Flickr-Faces-HQ dataset) and data augmentation (horizontal flipping and adaptive discriminator augmentation). The network's generative quality was measured quantitatively with the Fréchet Inception Distance (FID) and qualitatively with a visual Turing test given to seven radiologists and radiation oncologists. The StyleGAN2-ADA network achieved a FID of 5.22 ($\pm$ 0.17) on our liver CT dataset. It also set new record FIDs of 10.78, 3.52, 21.17, and 5.39 on the publicly available SLIVER07, ChestX-ray14, ACDC, and Medical Segmentation Decathlon (brain tumors) datasets. In the visual Turing test, the clinicians rated generated images as real 42% of the time, approaching random guessing. Our computational ablation study revealed that transfer learning and data augmentation stabilize training and improve the perceptual quality of the generated images. We observed the FID to be consistent with human perceptual evaluation of medical images. Finally, our work found that StyleGAN2-ADA consistently produces high-quality results without hyperparameter searches or retraining.

eess.IV↗

arXiv2022

Flexible Bayesian Product Mixture Models for Vector Autoregressions

Bayesian non-parametric methods based on Dirichlet process mixtures have seen tremendous success in various domains and are appealing in being able to borrow information by clustering samples that share identical parameters. However, such methods can face hurdles in heterogeneous settings where objects are expected to cluster only along a subset of axes or where clusters of samples share only a subset of identical parameters. We overcome such limitations by developing a novel class of product of Dirichlet process location-scale mixtures that enable independent clustering at multiple scales, which result in varying levels of information sharing across samples. First, we develop the approach for independent multivariate data. Subsequently we generalize it to multivariate time-series data under the framework of multi-subject Vector Autoregressive (VAR) models that is our primary focus, which go beyond parametric single-subject VAR models. We establish posterior consistency and develop efficient posterior computation for implementation. Extensive numerical studies involving VAR models show distinct advantages over competing methods, in terms of estimation, clustering, and feature selection accuracy. Our resting state fMRI analysis from the Human Connectome Project reveals biologically interpretable connectivity differences between distinct intelligence groups, while another air pollution application illustrates the superior forecasting accuracy compared to alternate methods.

stat.ME↗

arXiv2022

Flexible Bayesian Support Vector Machines for Brain Network-based Classification

Objective: Brain networks have gained increasing recognition as potential biomarkers in mental health studies, but there are limited approaches that can leverage complex brain networks for accurate classification. Our goal is to develop a novel Bayesian Support Vector Machine (SVM) approach that incorporates high-dimensional networks as covariates and is able to overcome limitations of existing penalized methods. Methods: We develop a novel Dirichlet process mixture of double exponential priors on the coefficients in the Bayesian SVM model that is able to perform feature selection and uncertainty quantification, by pooling information across edges to determine differential sparsity levels in an unsupervised manner. We develop different versions of the model that incorporates static and dynamic connectivity features, as well as an integrative analysis that jointly includes features from multiple scanning sessions. We perform classification of intelligence levels using resting state fMRI data from the Human Connectome Project (HCP), and a second Attention Deficiency Hyperactivity Disorder (ADHD) classification task. Results: Our results clearly reveal the considerable greater classification accuracy under the proposed approach over state-of-the-art methods. The multi-session analysis results in the highest classification accuracy in the HCP data analysis. Conclusion: We provide concrete evidence that the novel Bayesian SVMs provides an unsupervised and automated approach for network-based classification, that results in considerable improvements over penalized methods and parametric Bayesian approaches. Significance: Our work is one of the first to conclusively demonstrate the advantages of a Bayesian SVM in network-based classification of mental health outcomes, and the importance of multi-session network analysis.

stat.ME↗

arXiv2022

Multi-task Learning with High-Dimensional Noisy Images

Recent medical imaging studies have given rise to distinct but inter-related datasets corresponding to multiple experimental tasks or longitudinal visits. Standard scalar-on-image regression models that fit each dataset separately are not equipped to leverage information across inter-related images, and existing multi-task learning approaches are compromised by the inability to account for the noise that is often observed in images. We propose a novel joint scalar-on-image regression framework involving wavelet-based image representations with grouped penalties that are designed to pool information across inter-related images for joint learning, and which explicitly accounts for noise in high-dimensional images via a projection-based approach. In the presence of non-convexity arising due to noisy images, we derive non-asymptotic error bounds under non-convex as well as convex grouped penalties, even when the number of voxels increases exponentially with sample size. A projected gradient descent algorithm is used for computation, which is shown to approximate the optimal solution via well-defined non-asymptotic optimization error bounds under noisy images. Extensive simulations and application to a motivating longitudinal Alzheimer's disease study illustrate significantly improved predictive ability and greater power to detect true signals, that are simply missed by existing methods without noise correction due to the attenuation to null phenomenon.

stat.ME↗