Deep learning at the edge enables real-time streaming ptychographic imaging.
Anakha V BabuTao ZhouSaugat KandelTekin BicerZhengchun LiuWilliam JudgeDaniel J ChingYi JiangSinisa VeseliSteven HenkeRyan ChardYudong YaoEkaterina SirazitdinovaGeetika GuptaMartin V HoltIan T FosterAntonino MiceliMathew J CherukaraPublished in: Nature communications (2023)
Coherent imaging 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 imaging methods like ptychography are poised to revolutionize nanoscale materials characterization. However, these advancements are accompanied by significant increase in data and compute needs, which precludes real-time imaging, feedback and decision-making capabilities with conventional approaches. 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 oversampling constraints, allowing low-dose imaging using orders of magnitude less data than required by traditional methods.
Keyphrases
- high resolution
- artificial intelligence
- deep learning
- big data
- low dose
- electronic health record
- machine learning
- decision making
- mass spectrometry
- computed tomography
- high dose
- induced apoptosis
- drinking water
- molecular dynamics
- magnetic resonance
- atomic force microscopy
- endoplasmic reticulum stress
- energy transfer