arXiv subjects

Robert C. Welsh

Publications and source records attributed to Robert C. Welsh.

4 recordsLinked to original sources

arXiv2026

A Pipeline for ADNI Resting-State Functional MRI Processing and Quality Control

The Alzheimer's Disease Neuroimaging Initiative (ADNI) provides a comprehensive multimodal neuroimaging resource for studying aging and Alzheimer's disease (AD). Since its second wave, ADNI has increasingly collected resting-state functional MRI (rs-fMRI), a valuable resource for discovering brain connectivity changes predictive of cognitive decline and AD. A major barrier to its use is the considerable variability in acquisition protocols and data quality, compounded by missing imaging sessions and inconsistencies in how functional scans temporally align with clinical assessments. As a result, many studies only utilize a small subset of the total rs-fMRI data, limiting statistical power, reproducibility, and the ability to study longitudinal functional brain changes at scale. Here, we describe a pipeline for ADNI rs-fMRI data that encompasses the download of necessary imaging and clinical data, temporally aligning the clinical and imaging data, preprocessing, and quality control. We integrate data curation and preprocessing across all ADNI sites and scanner types using a combination of open-source software (Clinica, fMRIPrep, and MRIQC) and bespoke tools. Quality metrics and reports are generated for each subject and session to facilitate rigorous data screening. All scripts and configuration files are available to enable reproducibility. The pipeline, which currently supports ADNI-GO, ADNI-2, and ADNI-3 data releases, outputs high-quality rs-fMRI time series data adhering to the BIDS-derivatives specification. This protocol provides a transparent and scalable framework for curating and utilizing ADNI fMRI data, empowering large-scale functional biomarker discovery and integrative multimodal analyses in Alzheimer's disease research.

cs.DB↗

arXiv2023

SF2Former: Amyotrophic Lateral Sclerosis Identification From Multi-center MRI Data Using Spatial and Frequency Fusion Transformer

Amyotrophic Lateral Sclerosis (ALS) is a complex neurodegenerative disorder involving motor neuron degeneration. Significant research has begun to establish brain magnetic resonance imaging (MRI) as a potential biomarker to diagnose and monitor the state of the disease. Deep learning has turned into a prominent class of machine learning programs in computer vision and has been successfully employed to solve diverse medical image analysis tasks. However, deep learning-based methods applied to neuroimaging have not achieved superior performance in ALS patients classification from healthy controls due to having insignificant structural changes correlated with pathological features. Therefore, the critical challenge in deep models is to determine useful discriminative features with limited training data. By exploiting the long-range relationship of image features, this study introduces a framework named SF2Former that leverages vision transformer architecture's power to distinguish the ALS subjects from the control group. To further improve the network's performance, spatial and frequency domain information are combined because MRI scans are captured in the frequency domain before being converted to the spatial domain. The proposed framework is trained with a set of consecutive coronal 2D slices, which uses the pre-trained weights on ImageNet by leveraging transfer learning. Finally, a majority voting scheme has been employed to those coronal slices of a particular subject to produce the final classification decision. Our proposed architecture has been thoroughly assessed with multi-modal neuroimaging data using two well-organized versions of the Canadian ALS Neuroimaging Consortium (CALSNIC) multi-center datasets. The experimental results demonstrate the superiority of our proposed strategy in terms of classification accuracy compared with several popular deep learning-based techniques.

eess.IV↗

arXiv2022

Sources of residual autocorrelation in multiband task fMRI and strategies for effective mitigation

In task fMRI analysis, OLS is typically used to estimate task-induced activation in the brain. Since task fMRI residuals often exhibit temporal autocorrelation, it is common practice to perform prewhitening prior to OLS to satisfy the assumption of residual independence, equivalent to GLS. While theoretically straightforward, a major challenge in prewhitening in fMRI is accurately estimating the residual autocorrelation at each location of the brain. Assuming a global autocorrelation model, as in several fMRI software programs, may under- or over-whiten particular regions and fail to achieve nominal false positive control across the brain. Faster multiband acquisitions require more sophisticated models to capture autocorrelation, making prewhitening more difficult. These issues are becoming more critical now because of a trend towards subject-level analysis, where prewhitening has a greater impact than in group-average analyses. In this article, we first thoroughly examine the sources of residual autocorrelation in multiband task fMRI. We find that residual autocorrelation varies spatially throughout the cortex and is affected by the task, the acquisition method, modeling choices, and individual differences. Second, we evaluate the ability of different AR-based prewhitening strategies to effectively mitigate autocorrelation and control false positives. We find that allowing the prewhitening filter to vary spatially is the most important factor for successful prewhitening, even more so than increasing AR model order. To overcome the computational challenge associated with spatially variable prewhitening, we developed a computationally efficient R implementation based on parallelization and fast C++ backend code. This implementation is included in the open source R package BayesfMRI.

stat.ME↗

arXiv2021

Longitudinal surface-based spatial Bayesian GLM reveals complex trajectories of motor neurodegeneration in ALS

Longitudinal fMRI datasets hold great promise for the study of neurodegenerative diseases, but realizing their potential depends on extracting accurate fMRI-based brain measures in individuals over time. This is especially true for rare, heterogeneous and/or rapidly progressing diseases, which often involve small samples whose functional features may vary dramatically across subjects and over time, making traditional group-difference analyses of limited utility. One such disease is ALS, which results in extreme motor function loss and eventual death. Here, we analyze a rich longitudinal dataset containing 190 motor task fMRI scans from 16 ALS patients and 22 age-matched HCs. We propose a novel longitudinal extension to our cortical surface-based spatial Bayesian GLM, which has high power and precision to detect activations in individuals. Using a series of longitudinal mixed-effects models to subsequently study the relationship between activation and disease progression, we observe an inverted U-shaped trajectory: at relatively mild disability we observe enlarging activations, while at higher disability we observe severely diminished activation, reflecting progression toward complete motor function loss. We observe distinct trajectories depending on clinical progression rate, with faster progressors exhibiting more extreme hyper-activation and subsequent hypo-activation. These differential trajectories suggest that initial hyper-activation is likely attributable to loss of inhibitory neurons. By contrast, earlier studies employing more limited sampling designs and using traditional group-difference analysis approaches were only able to observe the initial hyper-activation, which was assumed to be due to a compensatory process. This study provides a first example of how surface-based spatial Bayesian modeling furthers scientific understanding of neurodegenerative disease.

stat.AP↗