Cargando…

POSEA: A novel algorithm to evaluate the performance of multi-object instance image segmentation

Many techniques and software packages have been developed to segment individual cells within microscopy images, necessitating a robust method to evaluate images segmented into a large number of unique objects. Currently, segmented images are often compared with ground-truth images at a pixel level;...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Nianchao, Hu, Linghao, Walsh, Alex J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10057750/
https://www.ncbi.nlm.nih.gov/pubmed/36989326
http://dx.doi.org/10.1371/journal.pone.0283692
_version_ 1785016448025886720
author Wang, Nianchao
Hu, Linghao
Walsh, Alex J.
author_facet Wang, Nianchao
Hu, Linghao
Walsh, Alex J.
author_sort Wang, Nianchao
collection PubMed
description Many techniques and software packages have been developed to segment individual cells within microscopy images, necessitating a robust method to evaluate images segmented into a large number of unique objects. Currently, segmented images are often compared with ground-truth images at a pixel level; however, this standard pixel-level approach fails to compute errors due to pixels incorrectly assigned to adjacent objects. Here, we define a per-object segmentation evaluation algorithm (POSEA) that calculates segmentation accuracy metrics for each segmented object relative to a ground truth segmented image. To demonstrate the performance of POSEA, precision, recall, and f-measure metrics are computed and compared with the standard pixel-level evaluation for simulated images and segmented fluorescence microscopy images of three different cell samples. POSEA yields lower accuracy metrics than the standard pixel-level evaluation due to correct accounting of misclassified pixels of adjacent objects. Therefore, POSEA provides accurate evaluation metrics for objects with pixels incorrectly assigned to adjacent objects and is robust for use across a variety of applications that require evaluation of the segmentation of unique adjacent objects.
format Online
Article
Text
id pubmed-10057750
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-100577502023-03-30 POSEA: A novel algorithm to evaluate the performance of multi-object instance image segmentation Wang, Nianchao Hu, Linghao Walsh, Alex J. PLoS One Research Article Many techniques and software packages have been developed to segment individual cells within microscopy images, necessitating a robust method to evaluate images segmented into a large number of unique objects. Currently, segmented images are often compared with ground-truth images at a pixel level; however, this standard pixel-level approach fails to compute errors due to pixels incorrectly assigned to adjacent objects. Here, we define a per-object segmentation evaluation algorithm (POSEA) that calculates segmentation accuracy metrics for each segmented object relative to a ground truth segmented image. To demonstrate the performance of POSEA, precision, recall, and f-measure metrics are computed and compared with the standard pixel-level evaluation for simulated images and segmented fluorescence microscopy images of three different cell samples. POSEA yields lower accuracy metrics than the standard pixel-level evaluation due to correct accounting of misclassified pixels of adjacent objects. Therefore, POSEA provides accurate evaluation metrics for objects with pixels incorrectly assigned to adjacent objects and is robust for use across a variety of applications that require evaluation of the segmentation of unique adjacent objects. Public Library of Science 2023-03-29 /pmc/articles/PMC10057750/ /pubmed/36989326 http://dx.doi.org/10.1371/journal.pone.0283692 Text en © 2023 Wang 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
Wang, Nianchao
Hu, Linghao
Walsh, Alex J.
POSEA: A novel algorithm to evaluate the performance of multi-object instance image segmentation
title POSEA: A novel algorithm to evaluate the performance of multi-object instance image segmentation
title_full POSEA: A novel algorithm to evaluate the performance of multi-object instance image segmentation
title_fullStr POSEA: A novel algorithm to evaluate the performance of multi-object instance image segmentation
title_full_unstemmed POSEA: A novel algorithm to evaluate the performance of multi-object instance image segmentation
title_short POSEA: A novel algorithm to evaluate the performance of multi-object instance image segmentation
title_sort posea: a novel algorithm to evaluate the performance of multi-object instance image segmentation
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10057750/
https://www.ncbi.nlm.nih.gov/pubmed/36989326
http://dx.doi.org/10.1371/journal.pone.0283692
work_keys_str_mv AT wangnianchao poseaanovelalgorithmtoevaluatetheperformanceofmultiobjectinstanceimagesegmentation
AT hulinghao poseaanovelalgorithmtoevaluatetheperformanceofmultiobjectinstanceimagesegmentation
AT walshalexj poseaanovelalgorithmtoevaluatetheperformanceofmultiobjectinstanceimagesegmentation