phenopype : A phenotyping pipeline for Python
(2022) In Methods in Ecology and Evolution 13(3). p.569-576- Abstract
Digital images are an intuitive way to capture, store and analyse organismal phenotypes. Many biologists are taking images to collect high-dimensional phenotypic information from specimens to investigate complex ecological, evolutionary and developmental phenomena, such as relationships between trait diversity and ecosystem function, multivariate natural selection or developmental plasticity. As a consequence, images are being collected at ever-increasing rates, but extraction of the contained phenotypic information poses a veritable analytical bottleneck. phenopype is a high-throughput phenotyping pipeline for the programming language Python that aims at alleviating this bottleneck. The package facilitates immediate extraction of... (More)
Digital images are an intuitive way to capture, store and analyse organismal phenotypes. Many biologists are taking images to collect high-dimensional phenotypic information from specimens to investigate complex ecological, evolutionary and developmental phenomena, such as relationships between trait diversity and ecosystem function, multivariate natural selection or developmental plasticity. As a consequence, images are being collected at ever-increasing rates, but extraction of the contained phenotypic information poses a veritable analytical bottleneck. phenopype is a high-throughput phenotyping pipeline for the programming language Python that aims at alleviating this bottleneck. The package facilitates immediate extraction of high-dimensional phenotypic data from digital images with low levels of background noise and complexity. At the core, phenopype provides functions for rapid signal processing-based image preprocessing and segmentation, data extraction, as well as visualization and data export. This functionality is provided by wrapping low-level computer vision libraries (such as OpenCV) into accessible functions to facilitate scientific image analysis. In addition, phenopype provides a project management ecosystem to streamline data collection and to increase reproducibility. phenopype offers two different workflows that support users during different stages of scientific image analysis. The low-throughput workflow uses regular Python syntax and has greater flexibility at the cost of reproducibility, which is suitable for prototyping during the initial stages of a research project. The high-throughput workflow allows users to specify and store image-specific settings for analysis in human-readable YAML format, and then execute all functions in one step by means of an interactive parser. This approach facilitates rapid program-user interactions during batch processing, and greatly increases scientific reproducibility. Overall, phenopype intends to make the features of powerful but technically involved low-level CV libraries available to biologists with little or no Python coding experience. Therefore, phenopype is aiming to augment, rather than replace the utility of existing Python CV libraries, allowing biologists to focus on rapid and reproducible data collection. Furthermore, image annotations produced by phenopype can be used as training data, thus presenting a stepping stone towards the application of deep learning architectures.
(Less)
- author
- Lürig, Moritz D. LU
- organization
- publishing date
- 2022
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- automation, computer vision, image analysis, image segmentation, phenomics, phenotype, toolbox, trait measurement
- in
- Methods in Ecology and Evolution
- volume
- 13
- issue
- 3
- pages
- 569 - 576
- publisher
- John Wiley & Sons Inc.
- external identifiers
-
- scopus:85120485237
- ISSN
- 2041-210X
- DOI
- 10.1111/2041-210X.13771
- language
- English
- LU publication?
- yes
- additional info
- Funding Information: I conceived in its current form during a laboratory retreat in Vna (Graubünden, Switzerland) that was organized and funded by Jukka Jokela. Its implementation was made possible by Blake Matthews and the Eawag directorate (Discretionary Funding Grant No. 5221.00492.013.11). Additional funding came from the Swiss National Science Foundation through an Early Postdoc. Mobility Fellowship (Grant No. P2EZP3_191804) and from the European Union's Horizon 2020 research and innovation programme through a Marie Skłodowska‐Curie IF (Grant No. 898932). I thank Kim Kaltenbach for being a patient alpha tester, and Cam Hudson, Ryan Greenway, Andres Grolimund, Nare Ngoepe, Anja Merz and Irene Gallego for being helpful beta testers. I would also express my sincere gratitude to Arthur Porto and Seth Donoughe whose comprehensive review for the consortium greatly improved the presentation and documentation of the package. Two anonymous reviewers provided very constructive feedback during review of the manuscript. The stickleback image for 's logo was taken by Angelina Arquint. Finally, this package may not have come into existence without Matt McGee, who encouraged me to learn Python and use it for computer vision. phenopype pyOpenSci phenopype Publisher Copyright: © 2021 The Authors. Methods in Ecology and Evolution published by John Wiley & Sons Ltd on behalf of British Ecological Society
- id
- 520a2f25-cbe9-4686-8d25-c29cd90dbaaa
- date added to LUP
- 2021-12-30 10:28:03
- date last changed
- 2024-05-05 18:28:16
@article{520a2f25-cbe9-4686-8d25-c29cd90dbaaa,
abstract = {{<p>Digital images are an intuitive way to capture, store and analyse organismal phenotypes. Many biologists are taking images to collect high-dimensional phenotypic information from specimens to investigate complex ecological, evolutionary and developmental phenomena, such as relationships between trait diversity and ecosystem function, multivariate natural selection or developmental plasticity. As a consequence, images are being collected at ever-increasing rates, but extraction of the contained phenotypic information poses a veritable analytical bottleneck. phenopype is a high-throughput phenotyping pipeline for the programming language Python that aims at alleviating this bottleneck. The package facilitates immediate extraction of high-dimensional phenotypic data from digital images with low levels of background noise and complexity. At the core, phenopype provides functions for rapid signal processing-based image preprocessing and segmentation, data extraction, as well as visualization and data export. This functionality is provided by wrapping low-level computer vision libraries (such as OpenCV) into accessible functions to facilitate scientific image analysis. In addition, phenopype provides a project management ecosystem to streamline data collection and to increase reproducibility. phenopype offers two different workflows that support users during different stages of scientific image analysis. The low-throughput workflow uses regular Python syntax and has greater flexibility at the cost of reproducibility, which is suitable for prototyping during the initial stages of a research project. The high-throughput workflow allows users to specify and store image-specific settings for analysis in human-readable YAML format, and then execute all functions in one step by means of an interactive parser. This approach facilitates rapid program-user interactions during batch processing, and greatly increases scientific reproducibility. Overall, phenopype intends to make the features of powerful but technically involved low-level CV libraries available to biologists with little or no Python coding experience. Therefore, phenopype is aiming to augment, rather than replace the utility of existing Python CV libraries, allowing biologists to focus on rapid and reproducible data collection. Furthermore, image annotations produced by phenopype can be used as training data, thus presenting a stepping stone towards the application of deep learning architectures.</p>}},
author = {{Lürig, Moritz D.}},
issn = {{2041-210X}},
keywords = {{automation; computer vision; image analysis; image segmentation; phenomics; phenotype; toolbox; trait measurement}},
language = {{eng}},
number = {{3}},
pages = {{569--576}},
publisher = {{John Wiley & Sons Inc.}},
series = {{Methods in Ecology and Evolution}},
title = {{phenopype : A phenotyping pipeline for Python}},
url = {{http://dx.doi.org/10.1111/2041-210X.13771}},
doi = {{10.1111/2041-210X.13771}},
volume = {{13}},
year = {{2022}},
}