Wang Brice, Ma Tianle, Chen Theresa, Nguyen Trinh, Crouse Ethan, Fleming Stephen J, Walker Alison S, Valakh Vera, Nehme Ralda, Miller Evan W, Farhi Samouil L, Babadi Mehrtash
Data Sciences Platform (DSP), Broad Institute of MIT and Harvard, Cambridge, MA USA.
Department of Computer Science and Engineering, Oakland University, Rochester, MI USA.
Npj Imaging. 2024;2(1):51. doi: 10.1038/s44303-024-00055-x. Epub 2024 Dec 4.
Voltage imaging is a powerful technique for studying neuronal activity, but its effectiveness is often constrained by low signal-to-noise ratios (SNR). Traditional denoising methods, such as matrix factorization, impose rigid assumptions about noise and signal structures, while existing deep learning approaches fail to fully capture the rapid dynamics and complex dependencies inherent in voltage imaging data. Here, we introduce CellMincer, a novel self-supervised deep learning method specifically developed for denoising voltage imaging datasets. CellMincer operates by masking and predicting sparse pixel sets across short temporal windows and conditions the denoiser on precomputed spatiotemporal auto-correlations to effectively model long-range dependencies without large temporal contexts. We developed and utilized a physics-based simulation framework to generate realistic synthetic datasets, enabling rigorous hyperparameter optimization and ablation studies. This approach highlighted the critical role of conditioning on spatiotemporal auto-correlations, resulting in an additional 3-fold SNR gain. Comprehensive benchmarking on both simulated and real datasets, including those validated with patch-clamp electrophysiology (EP), demonstrates CellMincer's state-of-the-art performance, with substantial noise reduction across the frequency spectrum, enhanced subthreshold event detection, and high-fidelity recovery of EP signals. CellMincer consistently outperforms existing methods in SNR gain (0.5-2.9 dB) and reduces SNR variability by 17-55%. Incorporating CellMincer into standard workflows significantly improves neuronal segmentation, peak detection, and functional phenotype identification, consistently surpassing current methods in both SNR gain and consistency.
电压成像技术是研究神经元活动的有力手段，但其有效性常受低信噪比（SNR）的限制。传统的去噪方法，如矩阵分解，对噪声和信号结构有严格假设，而现有的深度学习方法未能充分捕捉电压成像数据中固有的快速动态变化和复杂依赖性。在此，我们介绍CellMincer，这是一种专门为去噪电压成像数据集而开发的新型自监督深度学习方法。CellMincer通过在短时间窗口内对稀疏像素集进行掩蔽和预测来运行，并基于预先计算的时空自相关对去噪器进行调节，以有效建模长程依赖性，而无需大的时间上下文。我们开发并利用了一个基于物理的模拟框架来生成逼真的合成数据集，从而能够进行严格的超参数优化和消融研究。这种方法突出了基于时空自相关调节的关键作用，使信噪比额外提高了3倍。在模拟和真实数据集上进行的全面基准测试，包括那些通过膜片钳电生理学（EP）验证的数据集，证明了CellMincer的领先性能，在整个频谱上有显著的降噪效果，增强了阈下事件检测，以及对EP信号的高保真恢复。CellMincer在信噪比增益（0.5 - 2.9 dB）方面始终优于现有方法，并将信噪比变异性降低了17 - 55%。将CellMincer纳入标准工作流程可显著改善神经元分割、峰值检测和功能表型识别，在信噪比增益和一致性方面均持续超过现有方法。
