Cargando…

Age prediction by deep learning applied to Greenland halibut (Reinhardtius hippoglossoides) otolith images

Otoliths (ear-stones) in the inner ears of vertebrates containing visible year zones are used extensively to determine fish age. Analysis of otoliths is a time-consuming and difficult task that requires the education of human experts. Human age estimates are inconsistent, as several readings by the...

Descripción completa

Detalles Bibliográficos
Autores principales: Martinsen, Iver, Harbitz, Alf, Bianchi, Filippo Maria
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9635702/
https://www.ncbi.nlm.nih.gov/pubmed/36331956
http://dx.doi.org/10.1371/journal.pone.0277244
_version_ 1784824765275439104
author Martinsen, Iver
Harbitz, Alf
Bianchi, Filippo Maria
author_facet Martinsen, Iver
Harbitz, Alf
Bianchi, Filippo Maria
author_sort Martinsen, Iver
collection PubMed
description Otoliths (ear-stones) in the inner ears of vertebrates containing visible year zones are used extensively to determine fish age. Analysis of otoliths is a time-consuming and difficult task that requires the education of human experts. Human age estimates are inconsistent, as several readings by the same human expert might result in different ages assigned to the same otolith, in addition to an inherent bias between readers. To improve efficiency and resolve inconsistent results in the age reading from otolith images by human experts, an automated procedure based on convolutional neural networks (CNNs), a class of deep learning models suitable for image processing, is investigated. We applied CNNs that perform image regression to estimate the age of Greenland halibut (Reinhardtius hippoglossoides) with good results for individual ages as well as the overall age distribution, with an average CV of about 10% relative to the read ages by experts. In addition, the density distribution of predicted ages resembles the density distribution of the ground truth. By using k*l-fold cross-validation, we test all available samples, and we show that the results are rather sensitive to the choice of test set. Finally, we apply explanation techniques to analyze the decision process of deep learning models. In particular, we produce heatmaps indicating which input features that are the most important in the computation of predicted age.
format Online
Article
Text
id pubmed-9635702
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-96357022022-11-05 Age prediction by deep learning applied to Greenland halibut (Reinhardtius hippoglossoides) otolith images Martinsen, Iver Harbitz, Alf Bianchi, Filippo Maria PLoS One Research Article Otoliths (ear-stones) in the inner ears of vertebrates containing visible year zones are used extensively to determine fish age. Analysis of otoliths is a time-consuming and difficult task that requires the education of human experts. Human age estimates are inconsistent, as several readings by the same human expert might result in different ages assigned to the same otolith, in addition to an inherent bias between readers. To improve efficiency and resolve inconsistent results in the age reading from otolith images by human experts, an automated procedure based on convolutional neural networks (CNNs), a class of deep learning models suitable for image processing, is investigated. We applied CNNs that perform image regression to estimate the age of Greenland halibut (Reinhardtius hippoglossoides) with good results for individual ages as well as the overall age distribution, with an average CV of about 10% relative to the read ages by experts. In addition, the density distribution of predicted ages resembles the density distribution of the ground truth. By using k*l-fold cross-validation, we test all available samples, and we show that the results are rather sensitive to the choice of test set. Finally, we apply explanation techniques to analyze the decision process of deep learning models. In particular, we produce heatmaps indicating which input features that are the most important in the computation of predicted age. Public Library of Science 2022-11-04 /pmc/articles/PMC9635702/ /pubmed/36331956 http://dx.doi.org/10.1371/journal.pone.0277244 Text en © 2022 Martinsen et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Martinsen, Iver
Harbitz, Alf
Bianchi, Filippo Maria
Age prediction by deep learning applied to Greenland halibut (Reinhardtius hippoglossoides) otolith images
title Age prediction by deep learning applied to Greenland halibut (Reinhardtius hippoglossoides) otolith images
title_full Age prediction by deep learning applied to Greenland halibut (Reinhardtius hippoglossoides) otolith images
title_fullStr Age prediction by deep learning applied to Greenland halibut (Reinhardtius hippoglossoides) otolith images
title_full_unstemmed Age prediction by deep learning applied to Greenland halibut (Reinhardtius hippoglossoides) otolith images
title_short Age prediction by deep learning applied to Greenland halibut (Reinhardtius hippoglossoides) otolith images
title_sort age prediction by deep learning applied to greenland halibut (reinhardtius hippoglossoides) otolith images
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9635702/
https://www.ncbi.nlm.nih.gov/pubmed/36331956
http://dx.doi.org/10.1371/journal.pone.0277244
work_keys_str_mv AT martinseniver agepredictionbydeeplearningappliedtogreenlandhalibutreinhardtiushippoglossoidesotolithimages
AT harbitzalf agepredictionbydeeplearningappliedtogreenlandhalibutreinhardtiushippoglossoidesotolithimages
AT bianchifilippomaria agepredictionbydeeplearningappliedtogreenlandhalibutreinhardtiushippoglossoidesotolithimages