SpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers

2026-10-08

AI Summary

This study addresses the limited cross-domain generalization in spike inference from calcium imaging caused by diverse indicators, proposing SpikeSSL, a universal framework to overcome this challenge. Methodologically, it designs a bidirectional IIR state-space layer for dynamics matching and introduces adaptive layer normalization alongside a multimodal conditional encoder to modulate the backbone network. Furthermore, a heteroscedastic variance head and biophysically grounded synthetic data augmentation are incorporated to bridge domain gaps. Experimental evaluations across 33 datasets demonstrate that SpikeSSL achieves state-of-the-art performance in both within-domain assessments and zero-shot inference tasks, significantly enhancing the model's cross-domain generalization capability.

Abstract

Two-photon calcium imaging is a standard tool for recording large neural populations in vivo, yet inferring spikes accurately across the growing diversity of calcium indicators remains an open problem. Existing supervised methods achieve reasonable in-domain accuracy but generalize poorly to unseen indicators, because different indicators induce distinct fluorescence kinetics and signal statistics while existing architectures remain relatively simple generic temporal regressors without dynamics-matched inductive bias. We propose SpikeSSL, a universal spike inference framework whose temporal backbone is a bank of bidirectional IIR state-space layers broadly motivated by calcium dynamics. A multi-modal conditioning encoder maps indicator identity, sampling rate, and trace-level signal statistics into a global conditioning vector that modulates the backbone via Adaptive Layer Normalization, while a heteroscedastic variance head provides calibrated per-frame uncertainty. On a benchmark with five fixed evaluation splits built from 33 public ground-truth datasets, SpikeSSL achieves state-of-the-art performance in both in-domain and zero-shot leave-one-indicator-out settings. We also develop a biophysical simulation pipeline capable of generating paired fluorescence-spike traces with systematically varied kinetic parameters, spike statistics, response nonlinearities, baseline drift, and noise. Using this pipeline, we synthesize approximately 11,000 simulated traces. Augmenting training with these data effectively closes the cross-indicator domain gap and improves zero-shot generalization. Code is publicly available at https://github.com/detimage123/SpikeSSL.

Problem

• calcium imaging
• spike inference
• cross-indicator generalization
• fluorescence dynamics
• zero-shot learning

Innovation

• Spike Inference
• State-Space Layers
• Multi-modal Conditioning
• Biophysical Simulation
• Zero-shot Generalization