Augmented Equivariant Attention Networks for Microscopy Image Reconstruction

TL;DR

This paper introduces AEANets, a novel deep learning model that enhances microscopy image reconstruction by capturing inter-image dependencies while maintaining equivariance, leading to improved quality over existing methods.

Contribution

The paper proposes augmented equivariant attention networks (AEANets) that effectively capture shared features and inter-image dependencies in microscopy image reconstruction, preserving equivariance.

Findings

AEANets outperform baseline methods in quantitative metrics.

AEANets produce superior visual quality in reconstructed images.

Theoretical proof confirms the equivariance property of the model.

Abstract

It is time-consuming and expensive to take high-quality or high-resolution electron microscopy (EM) and fluorescence microscopy (FM) images. Taking these images could be even invasive to samples and may damage certain subtleties in the samples after long or intense exposures, often necessary for achieving high-quality or high resolution in the first place. Advances in deep learning enable us to perform image-to-image transformation tasks for various types of microscopy image reconstruction, computationally producing high-quality images from the physically acquired low-quality ones. When training image-to-image transformation models on pairs of experimentally acquired microscopy images, prior models suffer from performance loss due to their inability to capture inter-image dependencies and common features shared among images. Existing methods that take advantage of shared features in image classification tasks cannot be properly applied to image reconstruction tasks because they fail to preserve the equivariance property under spatial permutations, something essential in image-to-image transformation. To address these limitations, we propose the augmented equivariant attention networks (AEANets) with better capability to capture inter-image dependencies, while preserving the equivariance property. The proposed AEANets captures inter-image dependencies and shared features via two augmentations on the attention mechanism, which are the shared references and the batch-aware attention during training. We theoretically derive the equivariance property of the proposed augmented attention model and experimentally demonstrate its consistent superiority in both quantitative and visual results over the baseline methods.