Research map / Learning theory and algorithms / Prediction and decision losses
OnACID: Online Analysis of Calcium Imaging Data in Real Time
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Online streaming pipeline (OnACID) instead of offline CNMF | in vivo 2p hippocampal dataset · 50-min hippocampal dataset vs manual annotations | F1 vs manual annotation: 0.79/0.78 vs 0.71 | Helped |
| Online streaming pipeline (OnACID) instead of offline CNMF | in vivo 2p parietal cortex dataset · 64-min parietal cortex dataset vs manual annotations | F1 vs manual annotation: 0.76/0.79 vs 0.65/0.66 | Helped |
| Online processing with per-frame processing rather than offline batch analysis | 50-min hippocampal dataset · runtime | total processing time: ~27 min vs ~1.5 hours offline | Helped |
| Adding the residual-buffer-based new component detection and online updates | simulated data · simulated 2000-frame dataset | detection of active sources: all active sources detected, plus one false positive | Helped |
| Longer spike-assignment lag in online deconvolution (2-5 frames vs unrestricted) (ablation) | OASIS online deconvolution on simulated data · simulated data spike train correlation | Pearson correlation with ground truth: lags of 2-5 yield already similar results as unrestricted lag | Helped |
| Motion correction by aligning each frame to previous denoised background (simple online scheme) | parietal cortex dataset · motion displacement vs offline template-based method | displacement difference: std 0.11 and 0.12 pixel; difference <1 pixel for all frames | No clear effect |
| Stricter space correlation threshold (0.9) for accepting components (ablation) | both in vivo datasets · precision vs recall | precision/recall balance: high precision, lower recall; relaxing threshold reduces discrepancy with marginal F1 change | Mixed |
Closest papers by meaning
- realSEUDO for real-time calcium imaging analysis (NeurIPS 2024 · similarity 0.88)
- ActSort: An active-learning accelerated cell sorting algorithm for large-scale calcium imaging datasets (NeurIPS 2024 · similarity 0.87)
- SpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers (NeurIPS 2026 · similarity 0.86)
- Dynamical Modeling of Behaviorally Relevant Spatiotemporal Patterns in Neural Imaging Data (ICML 2025 · similarity 0.83)
- Active learning of neural population dynamics using two-photon holographic optogenetics (NeurIPS 2024 · similarity 0.83)
- SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution (NeurIPS 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.