Global Voxel Transformer Networks for Augmented Microscopy

TL;DR

This paper introduces global voxel transformer networks (GVTNets) that leverage global information aggregation to improve augmented microscopy, outperforming traditional U-Net based models across multiple datasets and tasks.

Contribution

The paper presents GVTNets, a novel deep learning architecture using global voxel transformer operators to enhance augmented microscopy beyond U-Net limitations.

Findings

GVTNets outperform U-Net models in microscopy tasks

Global voxel transformers effectively aggregate global information

Significant performance improvements across datasets and settings

Abstract

Advances in deep learning have led to remarkable success in augmented microscopy, enabling us to obtain high-quality microscope images without using expensive microscopy hardware and sample preparation techniques. However, current deep learning models for augmented microscopy are mostly U-Net based neural networks, thus sharing certain drawbacks that limit the performance. In this work, we introduce global voxel transformer networks (GVTNets), an advanced deep learning tool for augmented microscopy that overcomes intrinsic limitations of the current U-Net based models and achieves improved performance. GVTNets are built on global voxel transformer operators (GVTOs), which are able to aggregate global information, as opposed to local operators like convolutions. We apply the proposed methods on existing datasets for three different augmented microscopy tasks under various settings. The performance is significantly and consistently better than previous U-Net based approaches.