Point-scanning imaging systems are among the most widely used tools for high-resolution cellular and tissue imaging, benefiting from arbitrarily defined pixel sizes. The resolution, speed, sample preservation, and signal-to-noise ratio (SNR) of these systems are difficult to optimize simultaneously.
Researchers show these limitations can be mitigated via the use of deep learning-based supersampling of undersampled images acquired on a point-scanning system, which they term point-scanning super-resolution (PSSR) imaging.
The researchers designed a ‘crappifier’ that computationally degrades high SNR, high-pixel resolution ground truth images to simulate low SNR, low-resolution counterparts for training PSSR models that can restore real-world undersampled images. For high spatiotemporal resolution fluorescence time-lapse data, they developed a ‘multi-frame’ PSSR approach that uses information in adjacent frames to improve model predictions. PSSR facilitates point-scanning image acquisition with an otherwise unattainable resolution, speed, and sensitivity.
Deep learning is a branch of machine learning that uses multiple layers of nonlinear transformations to learn complex patterns from data. By applying deep learning to point-scanning imaging, it is possible to reconstruct high-resolution images from low-resolution inputs, reduce noise and artifacts, and increase the contrast and dynamic range of the images. Point-scanning imaging with deep learning has potential applications in various fields, such as biology, medicine, materials science, and nanotechnology.