Cargando…
Human embryonic stem cell classification: random network with autoencoded feature extractor
Significance: Automated understanding of human embryonic stem cell (hESC) videos is essential for the quantified analysis and classification of various states of hESCs and their health for diverse applications in regenerative medicine. Aim: This paper aims to develop an ensemble method and bagging o...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Society of Photo-Optical Instrumentation Engineers
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8084167/ https://www.ncbi.nlm.nih.gov/pubmed/33928769 http://dx.doi.org/10.1117/1.JBO.26.5.052913 |
_version_ | 1783686099165511680 |
---|---|
author | Guan, Benjamin X. Bhanu, Bir Theagarajan, Rajkumar Liu, Hengyue Talbot, Prue Weng, Nikki |
author_facet | Guan, Benjamin X. Bhanu, Bir Theagarajan, Rajkumar Liu, Hengyue Talbot, Prue Weng, Nikki |
author_sort | Guan, Benjamin X. |
collection | PubMed |
description | Significance: Automated understanding of human embryonic stem cell (hESC) videos is essential for the quantified analysis and classification of various states of hESCs and their health for diverse applications in regenerative medicine. Aim: This paper aims to develop an ensemble method and bagging of deep learning classifiers as a model for hESC classification on a video dataset collected using a phase contrast microscope. Approach: The paper describes a deep learning-based random network (RandNet) with an autoencoded feature extractor for the classification of hESCs into six different classes, namely, (1) cell clusters, (2) debris, (3) unattached cells, (4) attached cells, (5) dynamically blebbing cells, and (6) apoptotically blebbing cells. The approach uses unlabeled data to pre-train the autoencoder network and fine-tunes it using the available annotated data. Results: The proposed approach achieves a classification accuracy of [Formula: see text] and outperforms the state-of-the-art methods. Additionally, the approach has a very low training cost compared with the other deep-learning-based approaches, and it can be used as a tool for annotating new videos, saving enormous hours of manual labor. Conclusions: RandNet is an efficient and effective method that uses a combination of subnetworks trained using both labeled and unlabeled data to classify hESC images. |
format | Online Article Text |
id | pubmed-8084167 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Society of Photo-Optical Instrumentation Engineers |
record_format | MEDLINE/PubMed |
spelling | pubmed-80841672021-04-30 Human embryonic stem cell classification: random network with autoencoded feature extractor Guan, Benjamin X. Bhanu, Bir Theagarajan, Rajkumar Liu, Hengyue Talbot, Prue Weng, Nikki J Biomed Opt Special Series on Artificial Intelligence and Machine Learning in Biomedical Optics Significance: Automated understanding of human embryonic stem cell (hESC) videos is essential for the quantified analysis and classification of various states of hESCs and their health for diverse applications in regenerative medicine. Aim: This paper aims to develop an ensemble method and bagging of deep learning classifiers as a model for hESC classification on a video dataset collected using a phase contrast microscope. Approach: The paper describes a deep learning-based random network (RandNet) with an autoencoded feature extractor for the classification of hESCs into six different classes, namely, (1) cell clusters, (2) debris, (3) unattached cells, (4) attached cells, (5) dynamically blebbing cells, and (6) apoptotically blebbing cells. The approach uses unlabeled data to pre-train the autoencoder network and fine-tunes it using the available annotated data. Results: The proposed approach achieves a classification accuracy of [Formula: see text] and outperforms the state-of-the-art methods. Additionally, the approach has a very low training cost compared with the other deep-learning-based approaches, and it can be used as a tool for annotating new videos, saving enormous hours of manual labor. Conclusions: RandNet is an efficient and effective method that uses a combination of subnetworks trained using both labeled and unlabeled data to classify hESC images. Society of Photo-Optical Instrumentation Engineers 2021-04-29 2021-05 /pmc/articles/PMC8084167/ /pubmed/33928769 http://dx.doi.org/10.1117/1.JBO.26.5.052913 Text en © 2021 The Authors https://creativecommons.org/licenses/by/4.0/Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. |
spellingShingle | Special Series on Artificial Intelligence and Machine Learning in Biomedical Optics Guan, Benjamin X. Bhanu, Bir Theagarajan, Rajkumar Liu, Hengyue Talbot, Prue Weng, Nikki Human embryonic stem cell classification: random network with autoencoded feature extractor |
title | Human embryonic stem cell classification: random network with autoencoded feature extractor |
title_full | Human embryonic stem cell classification: random network with autoencoded feature extractor |
title_fullStr | Human embryonic stem cell classification: random network with autoencoded feature extractor |
title_full_unstemmed | Human embryonic stem cell classification: random network with autoencoded feature extractor |
title_short | Human embryonic stem cell classification: random network with autoencoded feature extractor |
title_sort | human embryonic stem cell classification: random network with autoencoded feature extractor |
topic | Special Series on Artificial Intelligence and Machine Learning in Biomedical Optics |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8084167/ https://www.ncbi.nlm.nih.gov/pubmed/33928769 http://dx.doi.org/10.1117/1.JBO.26.5.052913 |
work_keys_str_mv | AT guanbenjaminx humanembryonicstemcellclassificationrandomnetworkwithautoencodedfeatureextractor AT bhanubir humanembryonicstemcellclassificationrandomnetworkwithautoencodedfeatureextractor AT theagarajanrajkumar humanembryonicstemcellclassificationrandomnetworkwithautoencodedfeatureextractor AT liuhengyue humanembryonicstemcellclassificationrandomnetworkwithautoencodedfeatureextractor AT talbotprue humanembryonicstemcellclassificationrandomnetworkwithautoencodedfeatureextractor AT wengnikki humanembryonicstemcellclassificationrandomnetworkwithautoencodedfeatureextractor |