AI-driven lensless microscopy for diatom imaging
AI-driven lensless microscopy for diatom imaging
We present a novel approach for imaging diatoms using lensless imaging and deep learning. We use a laser to scatter off samples of diatomaceous earth (diatoms) and then record and transform the scattered light into microscope images of the diatoms using artificial intelligence. The predicted microscope images gave a high average SSIM and low average RMSE as compared to the experimental data. We also demonstrate the capability of determining the velocity and angle of movement of the diatoms from their scattering patterns as they are translated through the laser beam. This work shows the potential for imaging and identifying the movement of diatoms, and other micro-sized organisms, in-situ within the marine environment. Implementing such a method for real-time image acquisition and analysis could enhance environmental management, including improving the early detection of harmful algal blooms.
Mills, Ben
05f1886e-96ef-420f-b856-4115f4ab36d0
Zervas, Michalis
1840a474-dd50-4a55-ab74-6f086aa3f701
Grant-Jacob, James A.
c5d144d8-3c43-4195-8e80-edd96bfda91b
Mills, Ben
05f1886e-96ef-420f-b856-4115f4ab36d0
Zervas, Michalis
1840a474-dd50-4a55-ab74-6f086aa3f701
Grant-Jacob, James A.
c5d144d8-3c43-4195-8e80-edd96bfda91b
Mills, Ben, Zervas, Michalis and Grant-Jacob, James A.
(2025)
AI-driven lensless microscopy for diatom imaging.
Southampton Imaging Conference | Light on Life, Avenue Campus, Southampton, United Kingdom.
(Submitted)
Record type:
Conference or Workshop Item
(Other)
Abstract
We present a novel approach for imaging diatoms using lensless imaging and deep learning. We use a laser to scatter off samples of diatomaceous earth (diatoms) and then record and transform the scattered light into microscope images of the diatoms using artificial intelligence. The predicted microscope images gave a high average SSIM and low average RMSE as compared to the experimental data. We also demonstrate the capability of determining the velocity and angle of movement of the diatoms from their scattering patterns as they are translated through the laser beam. This work shows the potential for imaging and identifying the movement of diatoms, and other micro-sized organisms, in-situ within the marine environment. Implementing such a method for real-time image acquisition and analysis could enhance environmental management, including improving the early detection of harmful algal blooms.
This record has no associated files available for download.
More information
Submitted date: 20 March 2025
Venue - Dates:
Southampton Imaging Conference | Light on Life, Avenue Campus, Southampton, United Kingdom, 2025-06-18
Identifiers
Local EPrints ID: 502265
URI: http://eprints.soton.ac.uk/id/eprint/502265
PURE UUID: f946a7f2-3fdc-4b47-8a2d-53c2df76715e
Catalogue record
Date deposited: 19 Jun 2025 16:56
Last modified: 20 Jun 2025 01:44
Export record
Contributors
Author:
Ben Mills
Author:
Michalis Zervas
Author:
James A. Grant-Jacob
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics