arXiv subjects

Richard Leahy

Publications and source records attributed to Richard Leahy.

12 recordsLinked to original sources

arXiv2026

Exploring Brain Networks Using Noninvasive Electrophysiological Measurements: Methods and Applications

Electroencephalography (EEG) and magnetoencephalography (MEG) provide noninvasive measurements of brain activity with millisecond temporal resolution, enabling the investigation of functional and effective interactions within large-scale brain networks. This chapter presents a comprehensive overview of the methodological foundations and practical workflows for EEG/MEG-based brain network analysis. We first review the physical principles underlying EEG and MEG, emphasizing their complementary strengths and limitations. We then describe the forward and inverse problems, including subject-specific head modeling, source reconstruction techniques, and the importance of accurate anatomical modeling for reliable source localization. Strategies for mitigating volume conduction and signal leakage are discussed, together with best practices for source-space connectivity analysis. The chapter reviews widely used functional and effective connectivity measures, including coherence, phase synchronization metrics, amplitude envelope correlation, Granger causality, dynamic causal modeling, and transfer entropy, highlighting their assumptions, advantages, and limitations. Modern end-to-end analysis pipelines are presented, with particular emphasis on Brainstorm and complementary open-source software for reproducible EEG/MEG research. Finally, we discuss emerging approaches, including time-varying connectivity, cross-frequency interactions, and network-based analyses, illustrating how noninvasive electrophysiology contributes to understanding brain organization in health and disease. The chapter provides both conceptual foundations and practical guidance for researchers and advanced students seeking to map and interpret human brain networks using EEG and MEG.

q-bio.NC↗

arXiv2026

Aperiodic and Low-Frequency Spectral Bias in Reconstruction based EEG Foundation Models

EEG foundation models, pre-trained on large-scale unlabelled EEG data, have emerged as a promising direction towards learning generalizable EEG representations. Despite showing positive results in data-rich regimes, they often fail to outperform significantly smaller supervised models in low-resource settings compared to fully supervised models. We provide a mechanistic account of this shortcoming, attributing it to a fundamental mismatch between reconstruction-based pretext tasks and the idiosyncratic spectral structure of EEG signals, which decompose into distinct high-power aperiodic and low-power oscillatory components. Using controlled, synthetically-generated EEG inputs, we demonstrate that EEG foundation model embeddings are biased to capture the aperiodic components of the EEG signal while under-representing oscillatory components, particularly at higher frequencies. Additionally, linear probe evaluations on real-world BCI datasets further reveal that embeddings encode subject identity more strongly than task-relevant information, thereby reinforcing the low-frequency and aperiodic component bias in foundation model embeddings trained primarily on reconstruction based objectives. Together, these findings elucidate a failure mode in reconstruction based EEG foundation models and motivate future work to incorporate auxiliary losses explicitly targeting high-frequency oscillatory structure as a path toward more capable and generalizable EEG representations.

cs.LG↗

arXiv2026

Learning Cross-Joint Attention for Generalizable Video-Based Seizure Detection

Automated seizure detection from long-term clinical videos can substantially reduce manual review time and enable real-time monitoring. However, existing video-based methods often struggle to generalize to unseen subjects due to background bias and reliance on subject-specific appearance cues. We propose a joint-centric attention model that focuses exclusively on body dynamics to improve cross-subject generalization. For each video segment, body joints are detected and joint-centered clips are extracted, suppressing background context. These joint-centered clips are tokenized using a Video Vision Transformer (ViViT), and cross-joint attention is learned to model spatial and temporal interactions between body parts, capturing coordinated movement patterns characteristic of seizure semiology. Extensive cross-subject experiments show that the proposed method consistently outperforms state-of-the-art CNN-, graph-, and transformer-based approaches on unseen subjects.

cs.CV↗

arXiv2025

Informed Bootstrap Augmentation Improves EEG Decoding

Electroencephalography (EEG) offers detailed access to neural dynamics but remains constrained by noise and trial-by-trial variability, limiting decoding performance in data-restricted or complex paradigms. Data augmentation is often employed to enhance feature representations, yet conventional uniform averaging overlooks differences in trial informativeness and can degrade representational quality. We introduce a weighted bootstrapping approach that prioritizes more reliable trials to generate higher-quality augmented samples. In a Sentence Evaluation paradigm, weights were computed from relative ERP differences and applied during probabilistic sampling and averaging. Across conditions, weighted bootstrapping improved decoding accuracy relative to unweighted (from 68.35% to 71.25% at best), demonstrating that emphasizing reliable trials strengthens representational quality. The results demonstrate that reliability-based augmentation yields more robust and discriminative EEG representations. The code is publicly available at https://github.com/lyricists/NeuroBootstrap.

eess.SP↗

arXiv2025

High-Resolution Directional Depth Electrodes: Open-Source FEM Lead-Field Modeling, Characterization, and Validation

Depth electrodes used in stereoelectroencephalography (sEEG) and deep-brain stimulation (DBS) are essential tools for neural recording and stimulation. Traditional designs have limited spatial resolution, typically 8 to 16 cylindrical contacts (0.8 to 1.0 mm diameter) along a 5 to 10 cm shaft, restricting recordings from small or localized populations. Recent high-density, directional electrodes (HDsEEG) enable finer localization of local field potentials (LFPs) and spike timing. Yet, characterizing their directional sensitivity and validating modeling tools for lead field (LF) analysis remain critical. We compare finite element method (FEM) LF modeling of a novel HD-sEEG electrode using two tools: a commercial solver (ANSYS) and an open-source pipeline (Brainstorm-DUNEuro). Goals: (i) validate against analytical solutions, (ii) assess solver differences, and (iii) characterize HDsEEG directional sensitivity. LFs were modeled in simple and bio-relevant scenarios. Using Helmholtz reciprocity, we computed LFs by (a) electrode-based stimulation with ANSYS and (b) source-based recording with Brainstorm-DUNEuro. First, a multi-sphere head model with known solutions tested the solver's accuracy. Next, an HDsEEG electrode in a homogeneous conductor was simulated. Directional effects were assessed by comparing sensitivity with vs. without the insulating substrate. Source localization performance was also compared between HDsEEG and standard electrodes. Both solvers closely matched analytic solutions. In realistic settings, LF distributions were highly similar. Modeling showed clear directional sensitivity: contacts facing a source had higher sensitivity than those shadowed, reflecting a substrate shielding effect that vanished when the substrate was conductive. Crucially, HDsEEG improved source localization, as voltage differences across contacts provided robust directional LF information.

physics.med-ph↗

arXiv2025

Modeling and Reversing Brain Lesions Using Diffusion Models

Brain lesions are abnormalities or injuries in brain tissue that are often detectable using magnetic resonance imaging (MRI), which reveals structural changes in the affected areas. This broad definition of brain lesions includes areas of the brain that are irreversibly damaged, as well as areas of brain tissue that are deformed as a result of lesion growth or swelling. Despite the importance of differentiating between damaged and deformed tissue, existing lesion segmentation methods overlook this distinction, labeling both of them as a single anomaly. In this work, we introduce a diffusion model-based framework for analyzing and reversing the brain lesion process. Our pipeline first segments abnormal regions in the brain, then estimates and reverses tissue deformations by restoring displaced tissue to its original position, isolating the core lesion area representing the initial damage. Finally, we inpaint the core lesion area to arrive at an estimation of the pre-lesion healthy brain. This proposed framework reverses a forward lesion growth process model that is well-established in biomechanical studies that model brain lesions. Our results demonstrate improved accuracy in lesion segmentation, characterization, and brain labeling compared to traditional methods, offering a robust tool for clinical and research applications in brain lesion analysis. Since pre-lesion healthy versions of abnormal brains are not available in any public dataset for validation of the reverse process, we simulate a forward model to synthesize multiple lesioned brain images.

cs.CV↗

arXiv2024

Knowledge-guided EEG Representation Learning

Self-supervised learning has produced impressive results in multimedia domains of audio, vision and speech. This paradigm is equally, if not more, relevant for the domain of biosignals, owing to the scarcity of labelled data in such scenarios. The ability to leverage large-scale unlabelled data to learn robust representations could help improve the performance of numerous inference tasks on biosignals. Given the inherent domain differences between multimedia modalities and biosignals, the established objectives for self-supervised learning may not translate well to this domain. Hence, there is an unmet need to adapt these methods to biosignal analysis. In this work we propose a self-supervised model for EEG, which provides robust performance and remarkable parameter efficiency by using state space-based deep learning architecture. We also propose a novel knowledge-guided pre-training objective that accounts for the idiosyncrasies of the EEG signal. The results indicate improved embedding representation learning and downstream performance compared to prior works on exemplary tasks. Also, the proposed objective significantly reduces the amount of pre-training data required to obtain performance equivalent to prior works.

cs.LG↗

arXiv2023

Learning A Disentangling Representation For PU Learning

In this paper, we address the problem of learning a binary (positive vs. negative) classifier given Positive and Unlabeled data commonly referred to as PU learning. Although rudimentary techniques like clustering, out-of-distribution detection, or positive density estimation can be used to solve the problem in low-dimensional settings, their efficacy progressively deteriorates with higher dimensions due to the increasing complexities in the data distribution. In this paper we propose to learn a neural network-based data representation using a loss function that can be used to project the unlabeled data into two (positive and negative) clusters that can be easily identified using simple clustering techniques, effectively emulating the phenomenon observed in low-dimensional settings. We adopt a vector quantization technique for the learned representations to amplify the separation between the learned unlabeled data clusters. We conduct experiments on simulated PU data that demonstrate the improved performance of our proposed method compared to the current state-of-the-art approaches. We also provide some theoretical justification for our two cluster-based approach and our algorithmic choices.

cs.LG↗

arXiv2023

Beta quantile regression for robust estimation of uncertainty in the presence of outliers

Quantile Regression (QR) can be used to estimate aleatoric uncertainty in deep neural networks and can generate prediction intervals. Quantifying uncertainty is particularly important in critical applications such as clinical diagnosis, where a realistic assessment of uncertainty is essential in determining disease status and planning the appropriate treatment. The most common application of quantile regression models is in cases where the parametric likelihood cannot be specified. Although quantile regression is quite robust to outlier response observations, it can be sensitive to outlier covariate observations (features). Outlier features can compromise the performance of deep learning regression problems such as style translation, image reconstruction, and deep anomaly detection, potentially leading to misleading conclusions. To address this problem, we propose a robust solution for quantile regression that incorporates concepts from robust divergence. We compare the performance of our proposed method with (i) least trimmed quantile regression and (ii) robust regression based on the regularization of case-specific parameters in a simple real dataset in the presence of outlier. These methods have not been applied in a deep learning framework. We also demonstrate the applicability of the proposed method by applying it to a medical imaging translation task using diffusion models.

cs.LG↗

arXiv2022

Learning From Positive and Unlabeled Data Using Observer-GAN

The problem of learning from positive and unlabeled data (A.K.A. PU learning) has been studied in a binary (i.e., positive versus negative) classification setting, where the input data consist of (1) observations from the positive class and their corresponding labels, (2) unlabeled observations from both positive and negative classes. Generative Adversarial Networks (GANs) have been used to reduce the problem to the supervised setting with the advantage that supervised learning has state-of-the-art accuracy in classification tasks. In order to generate \textit{pseudo}-negative observations, GANs are trained on positive and unlabeled observations with a modified loss. Using both positive and \textit{pseudo}-negative observations leads to a supervised learning setting. The generation of pseudo-negative observations that are realistic enough to replace missing negative class samples is a bottleneck for current GAN-based algorithms. By including an additional classifier into the GAN architecture, we provide a novel GAN-based approach. In our suggested method, the GAN discriminator instructs the generator only to produce samples that fall into the unlabeled data distribution, while a second classifier (observer) network monitors the GAN training to: (i) prevent the generated samples from falling into the positive distribution; and (ii) learn the features that are the key distinction between the positive and negative observations. Experiments on four image datasets demonstrate that our trained observer network performs better than existing techniques in discriminating between real unseen positive and negative samples.

cs.CV↗

arXiv2022

Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection

Despite impressive state-of-the-art performance on a wide variety of machine learning tasks, deep learning methods can produce over-confident predictions, particularly with limited training data. Therefore, quantifying uncertainty is particularly important in critical applications such as lesion detection and clinical diagnosis, where a realistic assessment of uncertainty is essential in determining surgical margins, disease status and appropriate treatment. In this work, we propose a novel approach that uses quantile regression for quantifying aleatoric uncertainty in both supervised and unsupervised lesion detection problems. The resulting confidence intervals can be used for lesion detection and segmentation. In the unsupervised setting, we combine quantile regression with the Variational AutoEncoder (VAE). Here we address the problem of quantifying uncertainty in the images that are reconstructed by the VAE as the basis for principled outlier or lesion detection. The VAE models the output as a conditionally independent Gaussian characterized by its mean and variance. Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance. Here we describe an alternative Quantile-Regression VAE (QR-VAE) that avoids this variance shrinkage problem by directly estimating conditional quantiles for the input image. Using the estimated quantiles, we compute the conditional mean and variance for the input image from which we then detect outliers by thresholding at a false-discovery-rate corrected p-value. In the supervised setting, we develop binary quantile regression (BQR) for the supervised lesion segmentation task. We show how BQR can be used to capture uncertainty in lesion boundaries in a manner that characterizes expert disagreement.

cs.LG↗

arXiv2020

3D Phase Retrieval at Nano-Scale via Accelerated Wirtinger Flow

Imaging 3D nano-structures at very high resolution is crucial in a variety of scientific fields. However, due to fundamental limitations of light propagation we can only measure the object indirectly via 2D intensity measurements of the 3D specimen through highly nonlinear projection mappings where a variety of information (including phase) is lost. Reconstruction therefore involves inverting highly non-linear and seemingly non-invertible mappings. In this paper, we introduce a novel technique where the 3D object is directly reconstructed from an accurate non-linear propagation model. Furthermore, we characterize the ambiguities of this model and leverage a priori knowledge to mitigate their effect and also significantly reduce the required number of measurements and hence the acquisition time. We demonstrate the performance of our algorithm via numerical experiments aimed at nano-scale reconstruction of 3D integrated circuits. Moreover, we provide rigorous theoretical guarantees for convergence to stationarity.

eess.IV↗