Cargando…

U-Net-Based Segmentation of Microscopic Images of Colorants and Simplification of Labeling in the Learning Process

Colored product textures correspond to particle size distributions. The microscopic images of colorants must be divided into regions to determine the particle size distribution. The conventional method used for this process involves manually dividing images into areas, which may be inefficient. In t...

Descripción completa

Detalles Bibliográficos
Autores principales: Hirose, Ikumi, Tsunomura, Mari, Shishikura, Masami, Ishii, Toru, Yoshimura, Yuichiro, Ogawa-Ochiai, Keiko, Tsumura, Norimichi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9318575/
https://www.ncbi.nlm.nih.gov/pubmed/35877621
http://dx.doi.org/10.3390/jimaging8070177
_version_ 1784755326642290688
author Hirose, Ikumi
Tsunomura, Mari
Shishikura, Masami
Ishii, Toru
Yoshimura, Yuichiro
Ogawa-Ochiai, Keiko
Tsumura, Norimichi
author_facet Hirose, Ikumi
Tsunomura, Mari
Shishikura, Masami
Ishii, Toru
Yoshimura, Yuichiro
Ogawa-Ochiai, Keiko
Tsumura, Norimichi
author_sort Hirose, Ikumi
collection PubMed
description Colored product textures correspond to particle size distributions. The microscopic images of colorants must be divided into regions to determine the particle size distribution. The conventional method used for this process involves manually dividing images into areas, which may be inefficient. In this paper, we have overcome this issue by developing two different modified architectures of U-Net convolution neural networks to automatically determine the particle sizes. To develop these modified architectures, a significant amount of ground truth data must be prepared to train the U-Net, which is difficult for big data as the labeling is performed manually. Therefore, we also aim to reduce this process by using incomplete labeling data. The first objective of this study is to determine the accuracy of our modified U-Net architectures for this type of image. The second objective is to reduce the difficulty of preparing the ground truth data by testing the accuracy of training on incomplete labeling data. The results indicate that efficient segmentation can be realized using our modified U-Net architectures, and the generation of ground truth data can be simplified. This paper presents a preliminary study to improve the efficiency of determining particle size distributions with incomplete labeling data.
format Online
Article
Text
id pubmed-9318575
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93185752022-07-27 U-Net-Based Segmentation of Microscopic Images of Colorants and Simplification of Labeling in the Learning Process Hirose, Ikumi Tsunomura, Mari Shishikura, Masami Ishii, Toru Yoshimura, Yuichiro Ogawa-Ochiai, Keiko Tsumura, Norimichi J Imaging Article Colored product textures correspond to particle size distributions. The microscopic images of colorants must be divided into regions to determine the particle size distribution. The conventional method used for this process involves manually dividing images into areas, which may be inefficient. In this paper, we have overcome this issue by developing two different modified architectures of U-Net convolution neural networks to automatically determine the particle sizes. To develop these modified architectures, a significant amount of ground truth data must be prepared to train the U-Net, which is difficult for big data as the labeling is performed manually. Therefore, we also aim to reduce this process by using incomplete labeling data. The first objective of this study is to determine the accuracy of our modified U-Net architectures for this type of image. The second objective is to reduce the difficulty of preparing the ground truth data by testing the accuracy of training on incomplete labeling data. The results indicate that efficient segmentation can be realized using our modified U-Net architectures, and the generation of ground truth data can be simplified. This paper presents a preliminary study to improve the efficiency of determining particle size distributions with incomplete labeling data. MDPI 2022-06-23 /pmc/articles/PMC9318575/ /pubmed/35877621 http://dx.doi.org/10.3390/jimaging8070177 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Hirose, Ikumi
Tsunomura, Mari
Shishikura, Masami
Ishii, Toru
Yoshimura, Yuichiro
Ogawa-Ochiai, Keiko
Tsumura, Norimichi
U-Net-Based Segmentation of Microscopic Images of Colorants and Simplification of Labeling in the Learning Process
title U-Net-Based Segmentation of Microscopic Images of Colorants and Simplification of Labeling in the Learning Process
title_full U-Net-Based Segmentation of Microscopic Images of Colorants and Simplification of Labeling in the Learning Process
title_fullStr U-Net-Based Segmentation of Microscopic Images of Colorants and Simplification of Labeling in the Learning Process
title_full_unstemmed U-Net-Based Segmentation of Microscopic Images of Colorants and Simplification of Labeling in the Learning Process
title_short U-Net-Based Segmentation of Microscopic Images of Colorants and Simplification of Labeling in the Learning Process
title_sort u-net-based segmentation of microscopic images of colorants and simplification of labeling in the learning process
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9318575/
https://www.ncbi.nlm.nih.gov/pubmed/35877621
http://dx.doi.org/10.3390/jimaging8070177
work_keys_str_mv AT hiroseikumi unetbasedsegmentationofmicroscopicimagesofcolorantsandsimplificationoflabelinginthelearningprocess
AT tsunomuramari unetbasedsegmentationofmicroscopicimagesofcolorantsandsimplificationoflabelinginthelearningprocess
AT shishikuramasami unetbasedsegmentationofmicroscopicimagesofcolorantsandsimplificationoflabelinginthelearningprocess
AT ishiitoru unetbasedsegmentationofmicroscopicimagesofcolorantsandsimplificationoflabelinginthelearningprocess
AT yoshimurayuichiro unetbasedsegmentationofmicroscopicimagesofcolorantsandsimplificationoflabelinginthelearningprocess
AT ogawaochiaikeiko unetbasedsegmentationofmicroscopicimagesofcolorantsandsimplificationoflabelinginthelearningprocess
AT tsumuranorimichi unetbasedsegmentationofmicroscopicimagesofcolorantsandsimplificationoflabelinginthelearningprocess