High-throughput, high-resolution registration-free generated adversarial network microscopy
This work addresses the need for efficient, high-throughput super-resolution imaging in microscopy for applications like pathology and neuroscience, though it is incremental as it builds on existing GAN-based approaches.
The paper tackles the problem of achieving super-resolution microscopy over a large field of view without complex image registration, resulting in a method that recovers high-resolution images (~1.7 μm) from single low-resolution measurements at high speed (within 1 second) and over a large area (~95 mm²).
We combine generative adversarial network (GAN) with light microscopy to achieve deep learning super-resolution under a large field of view (FOV). By appropriately adopting prior microscopy data in an adversarial training, the neural network can recover a high-resolution, accurate image of new specimen from its single low-resolution measurement. Its capacity has been broadly demonstrated via imaging various types of samples, such as USAF resolution target, human pathological slides, fluorescence-labelled fibroblast cells, and deep tissues in transgenic mouse brain, by both wide-field and light-sheet microscopes. The gigapixel, multi-color reconstruction of these samples verifies a successful GAN-based single image super-resolution procedure. We also propose an image degrading model to generate low resolution images for training, making our approach free from the complex image registration during training dataset preparation. After a welltrained network being created, this deep learning-based imaging approach is capable of recovering a large FOV (~95 mm2), high-resolution (~1.7 μm) image at high speed (within 1 second), while not necessarily introducing any changes to the setup of existing microscopes.