Joint Denoising of Cryo-EM Projection Images using Polar Transformers
This addresses the challenge of improving reconstruction quality in cryo-EM imaging for structural biology, representing an incremental advance by applying a novel neural network method to a specific bottleneck.
The paper tackles the problem of denoising cryo-EM projection images with low signal-to-noise ratios by introducing a polar transformer architecture that integrates information from multiple images while preserving rotational symmetry, achieving up to a 2× reduction in mean squared error at an SNR of 0.02 on simulated datasets.
Many imaging modalities involve reconstruction of unknown objects from collections of noisy projections related by random rotations. In one of these modalities, cryogenic electron microscopy (cryo-EM), the extremely low signal-to-noise ratio (SNR) makes integration of information from multiple images crucial. Existing approaches to cryo-EM processing, however, either rely on handcrafted priors or apply deep learning only on select portions of the pipeline, such as particle picking, micrograph denoising, or refinement. A fully end-to-end reconstruction approach requires a neural network architecture that integrates information from multiple images while respecting the rotational symmetry of the measurement process. In this work, we introduce the polar transformer, a new neural network architecture that combines polar representations and transformers along with a convolutional attention mechanism that preserves the rotational symmetry of the problem. We apply it to the particle-level denoising problem, where it is able to learn discriminative features in the images, enabling optimal clustering, alignment, and denoising. On simulated datasets, this achieves up to a $2\times$ reduction in mean squared error (MSE) at a signal-to-noise ratio (SNR) of $0.02$, suggesting new opportunities for data-driven approaches to reconstruction in cryo-EM and related tomographic modalities.