Cytopathological image analysis using deep-learning networks in microfluidic microscopy

Cytopathologic testing is one of the most critical steps in the diagnosis of diseases, including cancer. However, the task is laborious and demands skill. Associated high cost and low throughput drew considerable interest in automating the testing process. Several neural network architectures were d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of the Optical Society of America. A, Optics, image science, and vision Optics, image science, and vision, 2017-01, Vol.34 (1), p.111-121
Hauptverfasser: Gopakumar, G, Hari Babu, K, Mishra, Deepak, Gorthi, Sai Siva, Sai Subrahmanyam, Gorthi R K
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 121
container_issue 1
container_start_page 111
container_title Journal of the Optical Society of America. A, Optics, image science, and vision
container_volume 34
creator Gopakumar, G
Hari Babu, K
Mishra, Deepak
Gorthi, Sai Siva
Sai Subrahmanyam, Gorthi R K
description Cytopathologic testing is one of the most critical steps in the diagnosis of diseases, including cancer. However, the task is laborious and demands skill. Associated high cost and low throughput drew considerable interest in automating the testing process. Several neural network architectures were designed to provide human expertise to machines. In this paper, we explore and propose the feasibility of using deep-learning networks for cytopathologic analysis by performing the classification of three important unlabeled, unstained leukemia cell lines (K562, MOLT, and HL60). The cell images used in the classification are captured using a low-cost, high-throughput cell imaging technique: microfluidics-based imaging flow cytometry. We demonstrate that without any conventional fine segmentation followed by explicit feature extraction, the proposed deep-learning algorithms effectively classify the coarsely localized cell lines. We show that the designed deep belief network as well as the deeply pretrained convolutional neural network outperform the conventionally used decision systems and are important in the medical domain, where the availability of labeled data is limited for training. We hope that our work enables the development of a clinically significant high-throughput microfluidic microscopy-based tool for disease screening/triaging, especially in resource-limited settings.
doi_str_mv 10.1364/JOSAA.34.000111
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1879997294</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1879997294</sourcerecordid><originalsourceid>FETCH-LOGICAL-c330t-e4a4218a1d5277b4626f87208bb0be5d0ea2d0f4b9c576cd1b99b8e0f5fa034f3</originalsourceid><addsrcrecordid>eNqNkDtPwzAURi0EoqUws6GMLGn9jO2xqniqUgdAjJHt2MXgPIgTofx7UlqYme79pHM_6R4ALhGcI5LRxePmabmcEzqHECKEjsAUMQxTwQg-HncoaMoZlhNwFuP7yNBM8FMwwQIyiQmZgtfV0NWN6t7qUG-9USHxpdraRFUqDNHHpI--2iaFtU0arGqrXaps91W3HzHxVVJ609Yu9L7wZh-iqZvhHJw4FaK9OMwZeLm9eV7dp-vN3cNquU4NIbBLLVUUI6FQwTDnmmY4c4JjKLSG2rICWoUL6KiWhvHMFEhLqYWFjjkFCXVkBq73vU1bf_Y2dnnpo7EhqMrWfcyR4FJKjiX9B8oyJnkmxYgu9ujundhalzft6KUdcgTznfj8R3xOaL4XP15cHcp7Xdrij_81Tb4Bvlp_nQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1856597698</pqid></control><display><type>article</type><title>Cytopathological image analysis using deep-learning networks in microfluidic microscopy</title><source>Optica Publishing Group Journals</source><creator>Gopakumar, G ; Hari Babu, K ; Mishra, Deepak ; Gorthi, Sai Siva ; Sai Subrahmanyam, Gorthi R K</creator><creatorcontrib>Gopakumar, G ; Hari Babu, K ; Mishra, Deepak ; Gorthi, Sai Siva ; Sai Subrahmanyam, Gorthi R K</creatorcontrib><description>Cytopathologic testing is one of the most critical steps in the diagnosis of diseases, including cancer. However, the task is laborious and demands skill. Associated high cost and low throughput drew considerable interest in automating the testing process. Several neural network architectures were designed to provide human expertise to machines. In this paper, we explore and propose the feasibility of using deep-learning networks for cytopathologic analysis by performing the classification of three important unlabeled, unstained leukemia cell lines (K562, MOLT, and HL60). The cell images used in the classification are captured using a low-cost, high-throughput cell imaging technique: microfluidics-based imaging flow cytometry. We demonstrate that without any conventional fine segmentation followed by explicit feature extraction, the proposed deep-learning algorithms effectively classify the coarsely localized cell lines. We show that the designed deep belief network as well as the deeply pretrained convolutional neural network outperform the conventionally used decision systems and are important in the medical domain, where the availability of labeled data is limited for training. We hope that our work enables the development of a clinically significant high-throughput microfluidic microscopy-based tool for disease screening/triaging, especially in resource-limited settings.</description><identifier>ISSN: 1084-7529</identifier><identifier>EISSN: 1520-8532</identifier><identifier>DOI: 10.1364/JOSAA.34.000111</identifier><identifier>PMID: 28059233</identifier><language>eng</language><publisher>United States</publisher><subject>Algorithms ; Belief networks ; Biotechnology ; Classification ; Diseases ; Microfluidics ; Networks ; Neural networks</subject><ispartof>Journal of the Optical Society of America. A, Optics, image science, and vision, 2017-01, Vol.34 (1), p.111-121</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c330t-e4a4218a1d5277b4626f87208bb0be5d0ea2d0f4b9c576cd1b99b8e0f5fa034f3</citedby><cites>FETCH-LOGICAL-c330t-e4a4218a1d5277b4626f87208bb0be5d0ea2d0f4b9c576cd1b99b8e0f5fa034f3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,777,781,3245,27905,27906</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/28059233$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Gopakumar, G</creatorcontrib><creatorcontrib>Hari Babu, K</creatorcontrib><creatorcontrib>Mishra, Deepak</creatorcontrib><creatorcontrib>Gorthi, Sai Siva</creatorcontrib><creatorcontrib>Sai Subrahmanyam, Gorthi R K</creatorcontrib><title>Cytopathological image analysis using deep-learning networks in microfluidic microscopy</title><title>Journal of the Optical Society of America. A, Optics, image science, and vision</title><addtitle>J Opt Soc Am A Opt Image Sci Vis</addtitle><description>Cytopathologic testing is one of the most critical steps in the diagnosis of diseases, including cancer. However, the task is laborious and demands skill. Associated high cost and low throughput drew considerable interest in automating the testing process. Several neural network architectures were designed to provide human expertise to machines. In this paper, we explore and propose the feasibility of using deep-learning networks for cytopathologic analysis by performing the classification of three important unlabeled, unstained leukemia cell lines (K562, MOLT, and HL60). The cell images used in the classification are captured using a low-cost, high-throughput cell imaging technique: microfluidics-based imaging flow cytometry. We demonstrate that without any conventional fine segmentation followed by explicit feature extraction, the proposed deep-learning algorithms effectively classify the coarsely localized cell lines. We show that the designed deep belief network as well as the deeply pretrained convolutional neural network outperform the conventionally used decision systems and are important in the medical domain, where the availability of labeled data is limited for training. We hope that our work enables the development of a clinically significant high-throughput microfluidic microscopy-based tool for disease screening/triaging, especially in resource-limited settings.</description><subject>Algorithms</subject><subject>Belief networks</subject><subject>Biotechnology</subject><subject>Classification</subject><subject>Diseases</subject><subject>Microfluidics</subject><subject>Networks</subject><subject>Neural networks</subject><issn>1084-7529</issn><issn>1520-8532</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><recordid>eNqNkDtPwzAURi0EoqUws6GMLGn9jO2xqniqUgdAjJHt2MXgPIgTofx7UlqYme79pHM_6R4ALhGcI5LRxePmabmcEzqHECKEjsAUMQxTwQg-HncoaMoZlhNwFuP7yNBM8FMwwQIyiQmZgtfV0NWN6t7qUG-9USHxpdraRFUqDNHHpI--2iaFtU0arGqrXaps91W3HzHxVVJ609Yu9L7wZh-iqZvhHJw4FaK9OMwZeLm9eV7dp-vN3cNquU4NIbBLLVUUI6FQwTDnmmY4c4JjKLSG2rICWoUL6KiWhvHMFEhLqYWFjjkFCXVkBq73vU1bf_Y2dnnpo7EhqMrWfcyR4FJKjiX9B8oyJnkmxYgu9ujundhalzft6KUdcgTznfj8R3xOaL4XP15cHcp7Xdrij_81Tb4Bvlp_nQ</recordid><startdate>20170101</startdate><enddate>20170101</enddate><creator>Gopakumar, G</creator><creator>Hari Babu, K</creator><creator>Mishra, Deepak</creator><creator>Gorthi, Sai Siva</creator><creator>Sai Subrahmanyam, Gorthi R K</creator><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>7SP</scope><scope>7U5</scope><scope>8FD</scope><scope>H8D</scope><scope>L7M</scope></search><sort><creationdate>20170101</creationdate><title>Cytopathological image analysis using deep-learning networks in microfluidic microscopy</title><author>Gopakumar, G ; Hari Babu, K ; Mishra, Deepak ; Gorthi, Sai Siva ; Sai Subrahmanyam, Gorthi R K</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c330t-e4a4218a1d5277b4626f87208bb0be5d0ea2d0f4b9c576cd1b99b8e0f5fa034f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Algorithms</topic><topic>Belief networks</topic><topic>Biotechnology</topic><topic>Classification</topic><topic>Diseases</topic><topic>Microfluidics</topic><topic>Networks</topic><topic>Neural networks</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Gopakumar, G</creatorcontrib><creatorcontrib>Hari Babu, K</creatorcontrib><creatorcontrib>Mishra, Deepak</creatorcontrib><creatorcontrib>Gorthi, Sai Siva</creatorcontrib><creatorcontrib>Sai Subrahmanyam, Gorthi R K</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Solid State and Superconductivity Abstracts</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Journal of the Optical Society of America. A, Optics, image science, and vision</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Gopakumar, G</au><au>Hari Babu, K</au><au>Mishra, Deepak</au><au>Gorthi, Sai Siva</au><au>Sai Subrahmanyam, Gorthi R K</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Cytopathological image analysis using deep-learning networks in microfluidic microscopy</atitle><jtitle>Journal of the Optical Society of America. A, Optics, image science, and vision</jtitle><addtitle>J Opt Soc Am A Opt Image Sci Vis</addtitle><date>2017-01-01</date><risdate>2017</risdate><volume>34</volume><issue>1</issue><spage>111</spage><epage>121</epage><pages>111-121</pages><issn>1084-7529</issn><eissn>1520-8532</eissn><abstract>Cytopathologic testing is one of the most critical steps in the diagnosis of diseases, including cancer. However, the task is laborious and demands skill. Associated high cost and low throughput drew considerable interest in automating the testing process. Several neural network architectures were designed to provide human expertise to machines. In this paper, we explore and propose the feasibility of using deep-learning networks for cytopathologic analysis by performing the classification of three important unlabeled, unstained leukemia cell lines (K562, MOLT, and HL60). The cell images used in the classification are captured using a low-cost, high-throughput cell imaging technique: microfluidics-based imaging flow cytometry. We demonstrate that without any conventional fine segmentation followed by explicit feature extraction, the proposed deep-learning algorithms effectively classify the coarsely localized cell lines. We show that the designed deep belief network as well as the deeply pretrained convolutional neural network outperform the conventionally used decision systems and are important in the medical domain, where the availability of labeled data is limited for training. We hope that our work enables the development of a clinically significant high-throughput microfluidic microscopy-based tool for disease screening/triaging, especially in resource-limited settings.</abstract><cop>United States</cop><pmid>28059233</pmid><doi>10.1364/JOSAA.34.000111</doi><tpages>11</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1084-7529
ispartof Journal of the Optical Society of America. A, Optics, image science, and vision, 2017-01, Vol.34 (1), p.111-121
issn 1084-7529
1520-8532
language eng
recordid cdi_proquest_miscellaneous_1879997294
source Optica Publishing Group Journals
subjects Algorithms
Belief networks
Biotechnology
Classification
Diseases
Microfluidics
Networks
Neural networks
title Cytopathological image analysis using deep-learning networks in microfluidic microscopy
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T22%3A04%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Cytopathological%20image%20analysis%20using%20deep-learning%20networks%20in%20microfluidic%20microscopy&rft.jtitle=Journal%20of%20the%20Optical%20Society%20of%20America.%20A,%20Optics,%20image%20science,%20and%20vision&rft.au=Gopakumar,%20G&rft.date=2017-01-01&rft.volume=34&rft.issue=1&rft.spage=111&rft.epage=121&rft.pages=111-121&rft.issn=1084-7529&rft.eissn=1520-8532&rft_id=info:doi/10.1364/JOSAA.34.000111&rft_dat=%3Cproquest_cross%3E1879997294%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1856597698&rft_id=info:pmid/28059233&rfr_iscdi=true