Noise-Transfer2Clean: Denoising cryo-EM images based on noise modeling and transfer

MotivationCryo-electron microscopy (cryo-EM) is a widely-used technology for ultrastructure determination, which constructs the three-dimensional (3D) structures of protein and macromolecular complex from a set of two-dimensional (2D) micrographs. However, limited by the electron beam dose, the micrographs in cryo-EM generally suffer from 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. ResultsHere, 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 discovering the noise model 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 noises true properties. To our knowledge, NT2C is the first denoising method that resolves the complex noise model in cryo-EM images. Comprehensive experimental results on simulated datasets and real datasets show that NT2C achieved a notable improvement in image denoising and specimen signal restoration, comparing with the state-of-art methods. A real-world case study shows that NT2C can improve the recognition rate on hard-to-identify particles by 19% in the particle picking task.