Luo Si-Heng, Pan Si-Qi, Chen Gan-Yu, Xie Yi, Ren Bin, Liu Guo-Kun, Tian Zhong-Qun
State Key Laboratory for Physical Chemistry of Solid Surfaces, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen 361005, China.
State Key Laboratory of Marine Environmental Science, Fujian Provincial Key Laboratory for Coastal Ecology and Environmental Studies, Center for Marine Environmental Chemistry & Toxicology, College of the Environment and Ecology, Xiamen University, Xiamen 361102, China.
Anal Chem. 2024 Mar 12;96(10):4086-4092. doi: 10.1021/acs.analchem.3c04608. Epub 2024 Feb 27.
Denoising is a necessary step in image analysis to extract weak signals, especially those hardly identified by the naked eye. Unlike the data-driven deep-learning denoising algorithms relying on a clean image as the reference, Noise2Noise (N2N) was able to denoise the noise image, providing sufficiently noise images with the same subject but randomly distributed noise. Further, by introducing data augmentation to create a big data set and regularization to prevent model overfitting, zero-shot N2N-based denoising was proposed in which only a single noisy image was needed. Although various N2N-based denoising algorithms have been developed with high performance, their complicated black box operation prevented the lightweight. Therefore, to reveal the working function of the zero-shot N2N-based algorithm, we proposed a lightweight Peak2Peak algorithm (P2P) and qualitatively and quantitatively analyzed its denoising behavior on the 1D spectrum and 2D image. We found that the high-performance denoising originates from the trade-off balance between the loss function and regularization in the denoising module, where regularization is the switch of denoising. Meanwhile, the signal extraction is mainly from the self-supervised characteristic learning in the data augmentation module. Further, the lightweight P2P improved the denoising speed by at least ten times but with little performance loss, compared with that of the current N2N-based algorithms. In general, the visualization of P2P provides a reference for revealing the working function of zero-shot N2N-based algorithms, which would pave the way for the application of these algorithms toward real-time (in situ, in vivo, and operando) research improving both temporal and spatial resolutions. The P2P is open-source at https://github.com/3331822w/Peak2Peakand will be accessible online access at https://ramancloud.xmu.edu.cn/tutorial.
去噪是图像分析中提取微弱信号的必要步骤，尤其是那些肉眼难以识别的信号。与依赖干净图像作为参考的数据驱动深度学习去噪算法不同，噪声到噪声（N2N）能够对噪声图像进行去噪，提供具有相同主题但噪声随机分布的足够噪声图像。此外，通过引入数据增强来创建大数据集和正则化来防止模型过拟合，提出了基于零样本N2N的去噪方法，该方法只需要一张噪声图像。尽管已经开发出了各种高性能的基于N2N的去噪算法，但其复杂的黑箱操作阻碍了轻量化。因此，为了揭示基于零样本N2N算法的工作原理，我们提出了一种轻量化的峰峰值算法（P2P），并对其在一维光谱和二维图像上的去噪行为进行了定性和定量分析。我们发现，高性能去噪源于去噪模块中损失函数和正则化之间的权衡平衡，其中正则化是去噪的开关。同时，信号提取主要来自数据增强模块中的自监督特征学习。此外，与当前基于N2N的算法相比，轻量化的P2P将去噪速度提高了至少十倍，但性能损失很小。总体而言，P2P的可视化可为揭示基于零样本N2N算法的工作原理提供参考，这将为这些算法在提高时间和空间分辨率的实时（原位、体内和操作中）研究中的应用铺平道路。P2P在https://github.com/3331822w/Peak2Peak上开源，并将在https://ramancloud.xmu.edu.cn/tutorial上在线访问。
