High Performance Computer Research Center, Institute of Computing Technology Chinese Academy of Sciences, Beijing 100190, China.
University of Chinese Academy of Sciences, Beijing 100049, China.
Bioinformatics. 2022 Mar 28;38(7):2022-2029. doi: 10.1093/bioinformatics/btac052.
Cryo-electron microscopy (cryo-EM) is a widely used technology for ultrastructure determination, which constructs the 3D structures of protein and macromolecular complex from a set of 2D micrographs. However, limited by the electron beam dose, the micrographs in cryo-EM generally suffer from the extremely low signal-to-noise ratio (SNR), which hampers the efficiency and effectiveness of downstream analysis. Especially, the noise in cryo-EM is not simple additive or multiplicative noise whose statistical characteristics are quite different from the ones in natural image, extremely shackling the performance of conventional denoising methods.
Here, we introduce the Noise-Transfer2Clean (NT2C), a denoising deep neural network (DNN) for cryo-EM to enhance image contrast and restore specimen signal, whose main idea is to improve the denoising performance by correctly learning the noise distribution of cryo-EM images and transferring the statistical nature of noise into the denoiser. Especially, to cope with the complex noise model in cryo-EM, we design a contrast-guided noise and signal re-weighted algorithm to achieve clean-noisy data synthesis and data augmentation, making our method authentically achieve signal restoration based on noise's true properties. Our work verifies the feasibility of denoising based on mining the complex cryo-EM noise patterns directly from the noise patches. Comprehensive experimental results on simulated datasets and real datasets show that NT2C achieved a notable improvement in image denoising, especially in background noise removal, compared with the commonly used methods. Moreover, a case study on the real dataset demonstrates that NT2C can greatly alleviate the obstacles caused by the SNR to particle picking and simplify the identifying of particles.
The code is available at https://github.com/Lihongjia-ict/NoiseTransfer2Clean/.
Supplementary data are available at Bioinformatics online.
低温电子显微镜（cryo-EM）是一种广泛用于超微结构测定的技术，它从一组二维显微照片中构建蛋白质和大分子复合物的 3D 结构。然而，由于电子束剂量的限制，cryo-EM 中的显微照片通常受到极低的信噪比（SNR）的影响，这阻碍了下游分析的效率和效果。特别是，cryo-EM 中的噪声不是简单的加性或乘性噪声，其统计特性与自然图像有很大的不同，极大地限制了传统去噪方法的性能。
在这里，我们引入了 Noise-Transfer2Clean（NT2C），这是一种用于 cryo-EM 的去噪深度神经网络（DNN），用于增强图像对比度和恢复标本信号，其主要思想是通过正确学习 cryo-EM 图像的噪声分布，并将噪声的统计特性转移到去噪器中，来提高去噪性能。特别是，为了应对 cryo-EM 中复杂的噪声模型，我们设计了一种对比度引导的噪声和信号重新加权算法，以实现干净-噪声数据合成和数据增强，使我们的方法真正能够根据噪声的真实特性实现信号恢复。我们的工作验证了直接从噪声补丁中挖掘复杂 cryo-EM 噪声模式进行去噪的可行性。在模拟数据集和真实数据集上的综合实验结果表明，与常用方法相比，NT2C 在图像去噪方面取得了显著的改进，特别是在背景噪声去除方面。此外，对真实数据集的案例研究表明，NT2C 可以大大减轻 SNR 对粒子选择造成的障碍，并简化粒子的识别。
代码可在 https://github.com/Lihongjia-ict/NoiseTransfer2Clean/ 获得。
补充数据可在 Bioinformatics 在线获得。
Zotero 插件
