Skip to main navigation Skip to search Skip to main content

Generalizable deep learning approach for 3D particle imaging using holographic microscopy (HM)

Research output: Contribution to journalArticlepeer-review

Abstract

Despite its potential for label-free particle diagnostics, holographic microscopy is limited by specialized processing methods that struggle to generalize across diverse settings. We introduce a deep learning architecture leveraging human perception of longitudinal variation of diffracted patterns of particles, which enables highly generalizable analysis of 3D particle information with orders of magnitude improvement in processing speed. Trained with minimal synthetic and real holograms of simple particles, our method demonstrates exceptional performance across various challenging cases, including high particle concentrations, significant noise, and a wide range of particle sizes, complex shapes, and optical properties, exceeding the diversity of training datasets.

Original languageEnglish (US)
Pages (from-to)48159-48173
Number of pages15
JournalOptics Express
Volume32
Issue number27
DOIs
StatePublished - Dec 30 2024

Bibliographical note

Publisher Copyright:
© 2024 Optica Publishing Group.

PubMed: MeSH publication types

  • Journal Article

Fingerprint

Dive into the research topics of 'Generalizable deep learning approach for 3D particle imaging using holographic microscopy (HM)'. Together they form a unique fingerprint.

Cite this