降噪
计算机科学
功能磁共振成像
人工智能
人为噪声
插值(计算机图形学)
噪音(视频)
模式识别(心理学)
基本事实
信号(编程语言)
通信噪声
信噪比(成像)
神经科学
频道(广播)
图像(数学)
生物
电信
哲学
发射机
语言学
程序设计语言
计算机网络
作者
Jérôme Lecoq,Michael Oliver,Joshua H. Siegle,N. S. Orlova,Peter Ledochowitsch,Christof Koch
出处
期刊:Nature Methods
[Nature Portfolio]
日期:2021-10-14
卷期号:18 (11): 1401-1408
被引量:160
标识
DOI:10.1038/s41592-021-01285-2
摘要
Progress in many scientific disciplines is hindered by the presence of independent noise. Technologies for measuring neural activity (calcium imaging, extracellular electrophysiology and functional magnetic resonance imaging (fMRI)) operate in domains in which independent noise (shot noise and/or thermal noise) can overwhelm physiological signals. Here, we introduce DeepInterpolation, a general-purpose denoising algorithm that trains a spatiotemporal nonlinear interpolation model using only raw noisy samples. Applying DeepInterpolation to two-photon calcium imaging data yielded up to six times more neuronal segments than those computed from raw data with a 15-fold increase in the single-pixel signal-to-noise ratio (SNR), uncovering single-trial network dynamics that were previously obscured by noise. Extracellular electrophysiology recordings processed with DeepInterpolation yielded 25% more high-quality spiking units than those computed from raw data, while DeepInterpolation produced a 1.6-fold increase in the SNR of individual voxels in fMRI datasets. Denoising was attained without sacrificing spatial or temporal resolution and without access to ground truth training data. We anticipate that DeepInterpolation will provide similar benefits in other domains in which independent noise contaminates spatiotemporally structured datasets. DeepInterpolation is a self-supervised deep learning-based denoising approach for calcium imaging, electrophysiology and fMRI data. The approach increases the signal-to-noise ratio and allows extraction of more information from the processed data than from the raw data.
科研通智能强力驱动
Strongly Powered by AbleSci AI