Abstract
State-of-the-art high-throughput microscopes are now capable of recording image data at a phenomenal rate, imaging entire microscope slides in minutes. In this paper we investigate how a large image set can be used to perform automated cell classification and denoising. To this end, we acquire an image library consisting of over one quarter-million white blood cell (WBC) nuclei together with CD15/CD16 protein expression for each cell. We show that the WBC nucleus images alone can be used to replicate CD expression-based gating, even in the presence of significant imaging noise. We also demonstrate that accurate estimates of white blood cell images can be recovered from extremely noisy images by comparing with a reference dictionary. This has implications for dose-limited imaging when samples belong to a highly restricted class such as a well-studied cell type. Furthermore, large image libraries may endow microscopes with capabilities beyond their hardware specifications in terms of sensitivity and resolution. We call for researchers to crowd source large image libraries of common cell lines to explore this possibility.
Highlights
State-of-the-art high-throughput microscopes are capable of recording image data at a phenomenal rate, imaging entire microscope slides in minutes
Using CD15 and CD16 expression levels in each cell image, we show that the white blood cell (WBC) population is divisible into 4 distinct populations, each with distinct nuclear morphologies
Each WBC nucleus image identified by this process is entered into an array that makes up the library
Summary
State-of-the-art high-throughput microscopes are capable of recording image data at a phenomenal rate, imaging entire microscope slides in minutes. Using CD15 and CD16 expression levels in each cell image, we show that the WBC population is divisible into 4 distinct populations, each with distinct nuclear morphologies These populations are gated to produce large dictionaries of nuclear morphology, which can in turn be explored. This dictionary-based approach performs surprisingly well even in the presence of significant simulated imaging noise This observation suggests that classification or quantification of cells in fluorescence microscopy can be done at low light levels given a library of example images that captures the full range of variability in cellular structure. We show that nuclear morphology can be accurately recovered from noisy images – even when the signal falls below the noise floor We discuss extensions of this idea, where crowd sourced high-resolution, multidimensionsal (3D, spectral, etc.) image dictionaries are used to enhance the capabilities of more rudimentary, cheaper microscopes
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
