Deep learning at the edge enables real-time streaming ptychographic imaging
This addresses a bottleneck in nanoscale materials characterization for scientific and technological fields by enabling real-time imaging, though it is incremental as it builds on existing AI and computing techniques.
The paper tackles the challenge of real-time image recovery in high-speed X-ray ptychography by developing an AI-enabled workflow that processes data at up to 2 kHz, enabling low-dose imaging with orders of magnitude less data than traditional methods.
Coherent microscopy techniques provide an unparalleled multi-scale view of materials across scientific and technological fields, from structural materials to quantum devices, from integrated circuits to biological cells. Driven by the construction of brighter sources and high-rate detectors, coherent X-ray microscopy methods like ptychography are poised to revolutionize nanoscale materials characterization. However, associated significant increases in data and compute needs mean that conventional approaches no longer suffice for recovering sample images in real-time from high-speed coherent imaging experiments. Here, we demonstrate a workflow that leverages artificial intelligence at the edge and high-performance computing to enable real-time inversion on X-ray ptychography data streamed directly from a detector at up to 2 kHz. The proposed AI-enabled workflow eliminates the sampling constraints imposed by traditional ptychography, allowing low dose imaging using orders of magnitude less data than required by traditional methods.