SpeckleNN: A unified embedding for real-time speckle pattern classification in X-ray single-particle imaging with limited labeled examples
This provides a solution for real-time high-throughput SPI experiments at facilities like European XFEL and LCLS-II-HE, reducing the need for manual labeling and handling missing detector areas, though it is incremental as it builds on twin neural networks for a specific domain.
The paper tackles the challenge of classifying X-ray single-particle imaging speckle patterns for real-time vetoing and 3D reconstruction in high-data-rate facilities, introducing SpeckleNN, a unified embedding model that achieves robust few-shot classification with only tens of labels per category and scales linearly with dataset size.
With X-ray free-electron lasers (XFELs), it is possible to determine the three-dimensional structure of noncrystalline nanoscale particles using X-ray single-particle imaging (SPI) techniques at room temperature. Classifying SPI scattering patterns, or "speckles", to extract single hits that are needed for real-time vetoing and three-dimensional reconstruction poses a challenge for high data rate facilities like European XFEL and LCLS-II-HE. Here, we introduce SpeckleNN, a unified embedding model for real-time speckle pattern classification with limited labeled examples that can scale linearly with dataset size. Trained with twin neural networks, SpeckleNN maps speckle patterns to a unified embedding vector space, where similarity is measured by Euclidean distance. We highlight its few-shot classification capability on new never-seen samples and its robust performance despite only tens of labels per classification category even in the presence of substantial missing detector areas. Without the need for excessive manual labeling or even a full detector image, our classification method offers a great solution for real-time high-throughput SPI experiments.