Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Bacterial community characterization by deep learning aided image analysis in soil chips

Zou, Hanbang LU ; Sopasakis, Alexandros LU orcid ; Maillard, François LU ; Karlsson, Erik LU orcid ; Duljas, Julia ; Silwer, Simon LU ; Ohlsson, Pelle LU orcid and Hammer, Edith C. LU orcid (2024) In Ecological Informatics 81.
Abstract

Soil microbes play an important role in governing global processes such as carbon cycling, but it is challenging to study them embedded in their natural environment and at the single cell level due to the opaque nature of the soil. Nonetheless, progress has been achieved in recent years towards visualizing microbial activities and organo-mineral interaction at the pore scale, especially thanks to the development of microfluidic ‘soil chips’ creating transparent soil model habitats. Image-based analyses come with new challenges as manual counting of bacteria in thousands of digital images taken from the soil chips is excessively time-consuming, while simple thresholding cannot be applied due to the background of soil minerals and debris.... (More)

Soil microbes play an important role in governing global processes such as carbon cycling, but it is challenging to study them embedded in their natural environment and at the single cell level due to the opaque nature of the soil. Nonetheless, progress has been achieved in recent years towards visualizing microbial activities and organo-mineral interaction at the pore scale, especially thanks to the development of microfluidic ‘soil chips’ creating transparent soil model habitats. Image-based analyses come with new challenges as manual counting of bacteria in thousands of digital images taken from the soil chips is excessively time-consuming, while simple thresholding cannot be applied due to the background of soil minerals and debris. Here, we adopt the well-developed deep learning algorithm Mask-RCNN to quantitatively analyze the bacterial communities in soil samples from different locations in the world. This work demonstrates analysis of bacterial abundance from three contrasting locations (Greenland, Sweden and Kenya) using deep learning in microfluidic soil chips in order to characterize population and community dynamics. We additionally quantified cell- and colony morphology including cell size, shape and the cell aggregation level via calculation of the distance to the nearest neighbor. This approach allows for the first time an automated visual investigation of soil bacterial communities, and a crude biodiversity measure based on phenotypic cell morphology, which could become a valuable complement to molecular studies.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Bacterial traits, Microbial image recognition, Microfluidics, Morphological biodiversity, Segmentation, Soil bacterial cell counting
in
Ecological Informatics
volume
81
article number
102562
publisher
Elsevier
external identifiers
  • scopus:85188716851
ISSN
1574-9541
DOI
10.1016/j.ecoinf.2024.102562
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2024
id
d3ab3e55-acba-40fc-85b6-eadbd7ec8c9a
date added to LUP
2024-04-07 16:39:06
date last changed
2025-04-04 14:05:48
@article{d3ab3e55-acba-40fc-85b6-eadbd7ec8c9a,
  abstract     = {{<p>Soil microbes play an important role in governing global processes such as carbon cycling, but it is challenging to study them embedded in their natural environment and at the single cell level due to the opaque nature of the soil. Nonetheless, progress has been achieved in recent years towards visualizing microbial activities and organo-mineral interaction at the pore scale, especially thanks to the development of microfluidic ‘soil chips’ creating transparent soil model habitats. Image-based analyses come with new challenges as manual counting of bacteria in thousands of digital images taken from the soil chips is excessively time-consuming, while simple thresholding cannot be applied due to the background of soil minerals and debris. Here, we adopt the well-developed deep learning algorithm Mask-RCNN to quantitatively analyze the bacterial communities in soil samples from different locations in the world. This work demonstrates analysis of bacterial abundance from three contrasting locations (Greenland, Sweden and Kenya) using deep learning in microfluidic soil chips in order to characterize population and community dynamics. We additionally quantified cell- and colony morphology including cell size, shape and the cell aggregation level via calculation of the distance to the nearest neighbor. This approach allows for the first time an automated visual investigation of soil bacterial communities, and a crude biodiversity measure based on phenotypic cell morphology, which could become a valuable complement to molecular studies.</p>}},
  author       = {{Zou, Hanbang and Sopasakis, Alexandros and Maillard, François and Karlsson, Erik and Duljas, Julia and Silwer, Simon and Ohlsson, Pelle and Hammer, Edith C.}},
  issn         = {{1574-9541}},
  keywords     = {{Bacterial traits; Microbial image recognition; Microfluidics; Morphological biodiversity; Segmentation; Soil bacterial cell counting}},
  language     = {{eng}},
  publisher    = {{Elsevier}},
  series       = {{Ecological Informatics}},
  title        = {{Bacterial community characterization by deep learning aided image analysis in soil chips}},
  url          = {{http://dx.doi.org/10.1016/j.ecoinf.2024.102562}},
  doi          = {{10.1016/j.ecoinf.2024.102562}},
  volume       = {{81}},
  year         = {{2024}},
}