This paper demonstrates a workflow using artificial intelligence (AI) 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 AI-enabled workflow eliminates oversampling constraints, allowing low-dose imaging with significantly less data than traditional methods. X-ray ptychography, a high-resolution imaging technique, is enhanced by this approach to achieve real-time imaging capabilities.

Anakha V. Babu, Tao Zhou, Saugat Kandel, Tekin Bicer, Zhengchun Liu, William Judge, Daniel J. Ching, Yi Jiang, Sinisa Veseli, Steven Henke, Ryan Chard, Yudong Yao, Ekaterina Sirazitdinova, Geetika Gupta, Martin V. Holt, Ian T. Foster, Antonino Miceli, Mathew J. Cherukara