Application of an attention-based CNN-BiLSTM framework for in vivo two-photon calcium imaging of neuronal ensembles: decoding complex bilateral forelimb movements from unilateral M1

2025-04-23

AI Summary

Decoding how unilateral primary motor cortex (M1) neuronal populations encode complex bilateral forelimb movements remains a fundamental challenge in neural decoding. Method: We propose an end-to-end deep learning framework that, for the first time, integrates attention mechanisms into a CNN-BiLSTM hybrid architecture to jointly model multi-scale spatiotemporal dependencies in calcium imaging signals. The approach combines in vivo two-photon calcium imaging with high-precision behavioral synchronization and analysis. Results/Contribution: Our model achieves simultaneous, high-accuracy decoding of both ipsilateral and contralateral forelimb kinematics—significantly outperforming baseline methods in mean accuracy—while demonstrating strong robustness to low signal-to-noise ratios and high-dimensional neural time series, as well as cross-subject generalizability. Crucially, it reveals a distributed encoding scheme in unilateral M1 for bilateral movement control and establishes a scalable deep learning paradigm for neural decoding of complex naturalistic behaviors.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Decoding behavior, such as movement, from multiscale brain networks remains a central objective in neuroscience. Over the past decades, artificial intelligence and machine learning have played an increasingly significant role in elucidating the neural mechanisms underlying motor function. The advancement of brain-monitoring technologies, capable of capturing complex neuronal signals with high spatial and temporal resolution, necessitates the development and application of more sophisticated machine learning models for behavioral decoding. In this study, we employ a hybrid deep learning framework, an attention-based CNN-BiLSTM model, to decode skilled and complex forelimb movements using signals obtained from in vivo two-photon calcium imaging. Our findings demonstrate that the intricate movements of both ipsilateral and contralateral forelimbs can be accurately decoded from unilateral M1 neuronal ensembles. These results highlight the efficacy of advanced hybrid deep learning models in capturing the spatiotemporal dependencies of neuronal networks activity linked to complex movement execution.

Problem

• Decoding complex bilateral forelimb movements from unilateral M1 neuronal ensembles
• Developing sophisticated machine learning models for behavioral decoding
• Capturing spatiotemporal dependencies of neuronal networks linked to movement

Innovation

• Attention-based CNN-BiLSTM for neuronal decoding
• Decoding bilateral forelimb movements from unilateral M1
• Two-photon calcium imaging with deep learning