Related Experiment Video
Updated: Jun 18, 2026
11:23
Lensless Fluorescent Microscopy on a Chip
Published on: August 17, 2011
17.7K
Deep learning at the edge enables real-time streaming ptychographic imaging.
Anakha V Babu1,2, Tao Zhou1, Saugat Kandel1
1Argonne National Laboratory, 9700 S Cass Ave, Lemont, IL, USA.
Nature Communications
|November 4, 2023
Summary
This study introduces an AI-powered workflow for real-time X-ray ptychography (XRP) imaging. This approach significantly reduces data requirements and enables low-dose nanoscale materials characterization.
Area of Science:
- Materials Science
- Imaging Techniques
- Artificial Intelligence
Background:
- Coherent imaging offers multi-scale material insights.
- Advancements in sources and detectors drive techniques like ptychography for nanoscale characterization.
- High data and compute demands hinder real-time capabilities.
Purpose of the Study:
- To develop a real-time inversion workflow for X-ray ptychography (XRP) data.
- To overcome limitations of conventional methods in data processing and imaging speed.
- To enable low-dose imaging with reduced data requirements.
Main Methods:
- Leveraging artificial intelligence (AI) at the edge for data processing.
- Utilizing high-performance computing for accelerated analysis.
- Streaming X-ray ptychography data directly from detectors at high rates (up to 2 kHz).
Main Results:
- Demonstrated a real-time AI-enabled workflow for XRP data inversion.
- Achieved real-time processing at rates up to 2 kHz.
- Eliminated oversampling constraints, enabling low-dose imaging with significantly less data.
Conclusions:
- The AI-enabled workflow revolutionizes nanoscale materials characterization.
- Real-time XRP imaging is now feasible, facilitating advanced feedback and decision-making.
- This approach significantly reduces data and computational burdens for coherent imaging.
Related Concept Videos
01:15Depth Perception and Spatial Vision
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
01:20Parallel Processing
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...