Cross-Subject Modeling for Widefield Calcium Imaging via Atlas-Aligned Spatiotemporal Tokenization

2026-07-04

AI Summary

Widefield calcium imaging data exhibit high dimensionality, complex spatiotemporal dynamics, and substantial task-irrelevant neural activity, which hinder the cross-subject generalization of existing models. To address this challenge, this work proposes WiCAT, the first foundation model tailored for multi-subject widefield imaging. WiCAT employs a brain atlas-aligned spatiotemporal tokenization strategy to eliminate session-specific variability and leverages self-supervised pretraining to learn globally shared neural representations. Evaluated across multiple datasets, WiCAT significantly outperforms single-session baselines, enabling efficient cross-subject transfer, zero-shot decoding of continuous behaviors, and accurate functional reconstruction of brain regions in unseen subjects.

Abstract

Large-scale, multi-subject widefield calcium imaging provides unprecedented access to brain-wide cortical dynamics. However, the high dimensionality, complex spatiotemporal structure, and substantial task-irrelevant activity in widefield recordings have largely restricted modeling efforts to single-session analyses, limiting scalability and generalization. While multi-subject pretrained models have been explored for some neural modalities, multi-subject models for widefield calcium imaging have not yet been demonstrated; further, subject-invariant zero-shot behavior decoding remains elusive for multi-subject models across neural modalities more broadly. As a first step toward foundation modeling of widefield data, we introduce WiCAT, a multi-subject model that leverages self-supervised pretraining to both outperform single-session models and enable zero-shot behavior decoding on unseen subjects. WiCAT introduces an atlas-grounded tokenization scheme without session-specific components and learns globally shared spatiotemporal representations. Across multiple widefield datasets, the pretrained model supports lightweight downstream decoding, transfers across subjects, tasks, and datasets, and outperforms baseline models. Notably, the model also achieves robust zero-shot continuous behavior decoding and left-out brain region reconstruction on unseen subjects.

Problem

• widefield calcium imaging
• cross-subject modeling
• zero-shot decoding
• spatiotemporal representation
• multi-subject generalization

Innovation

• widefield calcium imaging
• cross-subject modeling
• atlas-aligned tokenization
• self-supervised pretraining
• zero-shot decoding