arXiv subjects

Yuta Tanoue

Publications and source records attributed to Yuta Tanoue.

4 recordsLinked to original sources

arXiv2026

PHASE: A Physiology-Guided Hierarchical Foundation Model for Intracranial EEG

Clinicians and neuroscientists have long analyzed intracranial electroencephalography (iEEG) through directly measurable physiological characteristics, which carry much of the information that downstream tasks depend on. Recent iEEG foundation models learn by reconstructing or predicting their inputs, which leaves the retention of these characteristics implicit. They are also evaluated mainly on cognitive decoding and a narrow clinical task, i.e., seizure detection. On a broad, clinically relevant benchmark such as Omni-iEEG, they remain below task-specific models when used frozen. We introduce PHASE, a physiology-guided foundation model that makes these characteristics explicit learning targets, pairing them with masked latent prediction in a temporal stage (PHASE-T) within each channel and a spatiotemporal stage (PHASE-ST) across synchronized channels. PHASE is pretrained on heterogeneous recordings from 222 participants at nine clinical sites. On all five Omni-iEEG clinical tasks, frozen PHASE-T outperforms every evaluated foundation model by up to 31\%, and fine-tuned PHASE-T surpasses the task-specific models, setting a new state of the art. PHASE-T benefits from physiological supervision, outperforming variants trained with latent prediction alone or auxiliary waveform reconstruction on every task in matched ablations. PHASE-T generalizes to unseen institutions, outperforming the compared models with few or no local labels. PHASE-ST further improves seizure-onset-zone identification over PHASE-T and, when frozen, decodes sound volume and pitch on BrainTreebank better than published models. Beyond task performance, PHASE learns to encapsulate the physiological characteristics clinicians recognize, from seizure onset and its propagation to anatomical region identity, even though its pretraining contains no ictal recordings or anatomical labels.

cs.LG↗

arXiv2026

Omni-iEEG Planner: an open-source Python platform integrating multimodal neuroimaging and intracranial EEG data for epilepsy surgery research

Multimodal intracranial EEG (iEEG) research for epilepsy surgery combines anatomical and functional imaging, implanted electrode locations, interictal biomarkers, and functional mapping--outputs produced by different applications and reconciled by hand before they can be viewed on the same anatomy. Omni-iEEG Planner is an open-source Python platform that brings these inputs into one patient coordinate frame for research data analysis. The workflow starts from the preoperative T1-weighted MRI, from which FreeSurfer provides the cortical surface and anatomical labels; CT, PET and diffusion MRI are then co-registered to that reference, electrode contacts are detected automatically on the postimplantation CT and reviewed by the analyst, and tractography is reconstructed within the application. Channel-indexed results computed outside the platform, such as high-frequency oscillation counts from pyHFO or time-resolved gamma responses, are projected onto the contacts and the cortical surface with their source units preserved, and interictal and functional evidence remain separate layers. We describe the design and demonstrate representative workflows on de-identified patient data. The platform is not proposed as a method for every laboratory; it is a worked example of how one research group combined multimodal integration with an AI-assisted iEEG analysis tool, pyHFO, in a single open environment that others can adapt to their own pipelines. The design will accommodate further evidence types--model-derived contact scores, virtual implantation and hypothetical resection studies, group-level analyses--as they are implemented. The software is released under the MIT license for research and educational use, not clinical decision-making.

physics.med-ph↗

arXiv2025

New Insight of Spatial Scan Statistics via Regression Model

The spatial scan statistic is widely used to detect disease clusters in epidemiological surveillance. Since the seminal work by~\cite{kulldorff1997}, numerous extensions have emerged, including methods for defining scan regions, detecting multiple clusters, and expanding statistical models. Notably,~\cite{jung2009} and~\cite{ZHANG20092851} introduced a regression-based approach accounting for covariates, encompassing classical methods such as those of~\cite{kulldorff1997}. Another key extension is the expectation-based approach~\citep{neill2005anomalous,neillphdthesis}, which differs from the population-based approach represented by~\cite{kulldorff1997} in terms of hypothesis testing. In this paper, we bridge the regression-based approach with both expectation-based and population-based approaches. We reveal that the two approaches are separated by a simple difference: the presence or absence of an intercept term in the regression model. Exploiting the above simple difference, we propose new spatial scan statistics under the Gaussian and Bernoulli models. We further extend the regression-based approach by incorporating the well-known sparse L0 penalty and show that the derivation of spatial scan statistics can be expressed as an equivalent optimization problem. Our extended framework accommodates extensions such as space-time scan statistics and detecting multiple clusters while naturally connecting with existing spatial regression-based cluster detection. Considering the relation to case-specific models~\citep{she2011,10.1214/11-STS377}, clusters detected by spatial scan statistics can be viewed as outliers in terms of robust statistics. Numerical experiments with real data illustrate the behavior of our proposed statistics under specified settings.

stat.ME↗

arXiv2017

Oracle inequalities for sign constrained generalized linear models

High-dimensional data have recently been analyzed because of data collection technology evolution. Although many methods have been developed to gain sparse recovery in the past two decades, most of these methods require selection of tuning parameters. As a consequence of this feature, results obtained with these methods heavily depend on the tuning. In this paper we study the theoretical properties of sign-constrained generalized linear models with convex loss function, which is one of the sparse regression methods without tuning parameters. Recent studies on this topic have shown that, in the case of linear regression, sign-constrains alone could be as efficient as the oracle method if the design matrix enjoys a suitable assumption in addition to a traditional compatibility condition. We generalize this kind of result to a much more general model which encompasses the logistic and quantile regressions. We also perform some numerical experiments to confirm theoretical findings obtained in this paper.

math.ST↗