Generalising from conventional pipelines using deep learning in high‑throughput screening workfows

Garcia Santa Cruz, Beatriz; Sölter, Jan; Gomez Giro, Gemma; Saraiva, Claudia; Sabaté Soler, Sonia; Modamio Chamarro, Jenifer; Barmpa, Kyriaki; Schwamborn, Jens Christian; Hertel, Frank; Jarazo, Javier; Husch, Andreas

doi:10.1038/s41598-022-15623-7

Reference : Generalising from conventional pipelines using deep learning in high‑throughput scree...


	Document type :	Scientific journals : Article
	Discipline(s) :	Life sciences : Multidisciplinary, general & others Engineering, computing & technology : Multidisciplinary, general & others
	Focus Areas :	Systems Biomedicine
	To cite this reference:	http://hdl.handle.net/10993/48972

Title :	Generalising from conventional pipelines using deep learning in high‑throughput screening workfows
Language :	English
Author, co-author :	Garcia Santa Cruz, Beatriz [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
	Sölter, Jan []
	Gomez Giro, Gemma [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Developmental and Cellular Biology >]
	Saraiva, Claudia [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Developmental and Cellular Biology >]
	Sabaté Soler, Sonia [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Life Sciences and Medicine (DLSM) >]
	Modamio Chamarro, Jenifer []
	Barmpa, Kyriaki [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Developmental and Cellular Biology >]
	Schwamborn, Jens Christian [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Developmental and Cellular Biology >]
	Hertel, Frank [University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > >]
	Jarazo, Javier [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
	Husch, Andreas [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > Interventional Neuroscience >]
Publication date :	6-Jul-2022
Journal title :	Scientific Reports
Publisher :	Nature Publishing Group
Peer reviewed :	Yes
Audience :	International
e-ISSN :	2045-2322
City :	London
Country :	United Kingdom
Keywords :	[en] complex disease ; high-throughput screening ; image analysis ; deep learning approaches ; microscopy-image analysis
Abstract :	[en] The study of complex diseases relies on large amounts of data to build models toward precision medicine. Such data acquisition is feasible in the context of high-throughput screening, in which the quality of the results relies on the accuracy of the image analysis. Although state-of-the-art solutions for image segmentation employ deep learning approaches, the high cost of manually generating ground truth labels for model training hampers the day-to-day application in experimental laboratories. Alternatively, traditional computer vision-based solutions do not need expensive labels for their implementation. Our work combines both approaches by training a deep learning network using weak training labels automatically generated with conventional computer vision methods. Our network surpasses the conventional segmentation quality by generalising beyond noisy labels, providing a 25% increase of mean intersection over union, and simultaneously reducing the development and inference times. Our solution was embedded into an easy-to-use graphical user interface that allows researchers to assess the predictions and correct potential inaccuracies with minimal human input. To demonstrate the feasibility of training a deep learning solution on a large dataset of noisy labels automatically generated by a conventional pipeline, we compared our solution against the common approach of training a model from a small manually curated dataset by several experts. Our work suggests that humans perform better in context interpretation, such as error assessment, while computers outperform in pixel-by-pixel fne segmentation. Such pipelines are illustrated with a case study on image segmentation for autophagy events. This work aims for better translation of new technologies to real-world settings in microscopy-image analysis.
Target :	Researchers ; Professionals ; General public
Permalink :	http://hdl.handle.net/10993/48972
DOI :	10.1038/s41598-022-15623-7
Other URL :	https://www.nature.com/articles/s41598-022-15623-7

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	Generalising_sr_publish.pdf		Publisher postprint	4.48 MB	View/Open

All documents in ORBi^lu are protected by a user license.

University of Luxembourg Library | Feedback | Legal notices