Finding the semantic similarity in single-particle diffraction images using self-supervised contrastive projection learning


Loading...

Date

2023-02-16

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Single-shot coherent diffraction imaging of isolated nanosized particles has seen remarkable success in recent years, yielding in-situ measurements with ultra-high spatial and temporal resolution. The progress of high-repetition-rate sources for intense X-ray pulses has further enabled recording datasets containing millions of diffraction images, which are needed for the structure determination of specimens with greater structural variety and dynamic experiments. The size of the datasets, however, represents a monumental problem for their analysis. Here, we present an automatized approach for finding semantic similarities in coherent diffraction images without relying on human expert labeling. By introducing the concept of projection learning, we extend self-supervised contrastive learning to the context of coherent diffraction imaging and achieve a dimensionality reduction producing semantically meaningful embeddings that align with physical intuition. The method yields substantial improvements compared to previous approaches, paving the way toward real-time and large-scale analysis of coherent diffraction experiments at X-ray free-electron lasers.

Publication status

published

Editor

Book title

Volume

9 (1)

Pages / Article No.

24

Publisher

Nature

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Characterization and analytical techniques; Design, synthesis and processing; Nanoparticles

Organisational unit

09668 - Rupp, Daniela / Rupp, Daniela check_circle

Notes

Funding

193642 - Ionization dynamics of helium clusters and droplets in intense short-wavelength light pulses (SNF)

Related publications and datasets