CUSP: Complex Spike Sorting from Multi-electrode Array Recordings with U-net Sequence-to-Sequence Prediction
Authors:
- Chenhao BaoCBChenhao Bao
- Robyn MildrenRMRobyn Mildren
- Adam S. CharlesACAdam S. Charles
- Kathleen E. CullenKCKathleen E. Cullen
Preprint
Abstract
Background: Complex spikes (CSs) in cerebellar Purkinje cells convey unique signals complementary to Simple spike (SS) action potentials, but are infrequent and variable in waveform. Their variability and low spike counts, combined with recording artifacts such as electrode drift, make automated detection challenging. New Method: We introduce CUSP (CS sorting via U-net Sequence Prediction), a fully automated deep learning framework for CS sorting in high-density multi-electrode array recordings. CUSP uses a U-Net architecture with hybrid self-attention inception blocks to integrate local field potential and action potential signals and outputs CS event probabilities in a sequence-to-sequence manner. Detected events are clustered and paired with concurrently detected SSs to reconstruct the complete Purkinje cell activity. Results: Trained on cerebellar neuropixels recordings in rhesus macaques, CUSP achieves human-expert performance (F1 = 0.83 ± 0.03) and even captures valid CS events overlooked during manual annotation. Comparison with Existing Methods: CUSP outperforms traditional and state-of-the-art CS and SS sorting algorithms on CS detection. It remains robust to waveform variability, spikelet composition, and electrode drift, enabling accurate CS tracking in long-term recordings. In contrast, existing methods often show false-positive biases or degrade under drift. Conclusions: CUSP provides a scalable, robust framework for analyzing burst-like or dynamically complex spike patterns. Its generalizability makes it valuable for large-scale cerebellar datasets and other neural systems, such as hippocampal pyramidal cells, where complex bursts are critical for computation. By combining expert-level accuracy with automation, CUSP offers a broadly applicable solution for studying information coding across circuits.Keywords
All Related Versions
- Published version: Journal of Neuroscience Methods, 426, 110631.
Funding Information
- National Institute on Deafness and Other Communication Disorders (R01-DC002390)
- National Institute on Deafness and Other Communication Disorders (R01-DC018061)
- Raynor Cerebellar Project
- Kavli Neuroscience Discovery Institute, Baltimore, MD (Distinguished Postdoctoral Fellowship)
- Natural Sciences and Engineering Research Council of Canada (Postdoctoral Fellowship)
This publication has 58 references indexed in Scilit:
- Convergence of vestibular and proprioceptive signals in the cerebellar nodulus/uvula enhances the encoding of self-motion in primatesCurrent Biology, 2025
- Voltage- and Branch-Specific Climbing Fiber Responses in Purkinje CellsCell Reports, 2018
- Complex Spike Wars: a New HopeThe Cerebellum, 2018
- Spike detection: Inter-reader agreement and a statistical Turing test on a large data setClinical Neurophysiology, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Specific vermal complex spike responses build up during the course of smooth-pursuit adaptation, paralleling the decrease of performance errorExperimental Brain Research, 2010
- Cerebellar Complex Spike Firing Is Suitable to Induce as Well as to Stabilize Motor LearningCurrent Biology, 2005
- Cerebellar outflow lesions: A comparison of movement deficits resulting from lesions at the levels of the cerebellum and thalamusAnnals of Neurology, 1995
- Neural design of the cerebellar motor control systemBrain Research, 1972
- A theory of cerebellar functionMathematical Biosciences, 1971