Quantification of histopathological findings using a novel image analysis platform
Digital pathology, including image analysis and automatic diagnosis of pathological tissue, has been developed remarkably. HALO is an image analysis platform specialized for the study of pathological tissues, which enables tissue segmentation by using artificial intelligence. In this study, we used...
Gespeichert in:
| Veröffentlicht in: | Journal of Toxicologic Pathology 2019, Vol.32(4), pp.319-327 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 327 |
|---|---|
| container_issue | 4 |
| container_start_page | 319 |
| container_title | Journal of Toxicologic Pathology |
| container_volume | 32 |
| creator | Horai, Yasushi Mizukawa, Mao Nishina, Hironobu Nishikawa, Satomi Ono, Yuko Takemoto, Kana Baba, Nobuyuki |
| description | Digital pathology, including image analysis and automatic diagnosis of pathological tissue, has been developed remarkably. HALO is an image analysis platform specialized for the study of pathological tissues, which enables tissue segmentation by using artificial intelligence. In this study, we used HALO to quantify various histopathological changes and findings that were difficult to analyze using conventional image processing software. Using the tissue classifier module, the morphological features of degeneration/necrosis of the hepatocytes and muscle fibers, bile duct in the liver, basophilic tubules and hyaline casts in the kidney, cortex in the thymus, and red pulp, white pulp, and marginal zone in the spleen were learned and separated, and areas of interest were quantified. Furthermore, using the cytonuclear module and vacuole module in combination with the tissue classifier module, the number of erythroblasts in the red pulp of the spleen and each area of acinar cells in the parotid gland were quantified. The results of quantitative analysis were correlated with the histopathological grades evaluated by pathologists. By using artificial intelligence and other functions of HALO, we recognized morphological features, analyzed histopathological changes, and quantified the histopathological grades of various findings. The analysis of histopathological changes using HALO is expected to support pathology evaluations. |
| doi_str_mv | 10.1293/tox.2019-0022 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6831494</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2314250561</sourcerecordid><originalsourceid>FETCH-LOGICAL-c734t-4531dacf99283480b8b9c0c3b32cd2f88efd1e9786ab1bbcf62db72719907cb63</originalsourceid><addsrcrecordid>eNpdUc9vFCEUJkZjt6tH75N48TKVXzPAxcRsbGvSxGjaxBthGNhlw8IITGP_-zLdukYP8ID3ve99jw-AdwheICzIxxJ_X2CIRAshxi_ACnGOWoG6ny_BCgpE61nwM3Ce874iGOzIa3BGEEOC9WgFfnyfVSjOOq2Ki6GJttm5XOKkyi76uK3vvrEujC5sczPnGhrVhHhvfOMOamsaFZR_yC43k1fFxnR4A15Z5bN5-xzX4O7yy-3mur35dvV18_mm1YzQ0tKOoFFpKwTmhHI48EFoqMlAsB6x5dzYERnBeK8GNAza9ngcGK7CBWR66MkafDryTvNwMKM2oSTl5ZSqrvQgo3Ly30xwO7mN97LnBFFBK8GHZ4IUf80mF3lwWRvvVTBxzhJXGO5g16MKff8fdB_nVCd_QiFMKavzrEF7ROkUc07GnsQgKBe3ZHVLLm7Jxa2Kvzriq8jlo2PwLpi_1ONIasGk_pQQDKmEqC6y3AlmhAjBIatMmyPTPpdqyqmvSsVpb576Eizpsp36n7J6p5I0gTwCAQK2zA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2311244745</pqid></control><display><type>article</type><title>Quantification of histopathological findings using a novel image analysis platform</title><source>J-STAGE Free</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><source>PubMed Central Open Access</source><creator>Horai, Yasushi ; Mizukawa, Mao ; Nishina, Hironobu ; Nishikawa, Satomi ; Ono, Yuko ; Takemoto, Kana ; Baba, Nobuyuki</creator><creatorcontrib>Horai, Yasushi ; Mizukawa, Mao ; Nishina, Hironobu ; Nishikawa, Satomi ; Ono, Yuko ; Takemoto, Kana ; Baba, Nobuyuki ; Sohyaku Innovative Research Division ; Mitsubishi Tanabe Pharma Corporation</creatorcontrib><description>Digital pathology, including image analysis and automatic diagnosis of pathological tissue, has been developed remarkably. HALO is an image analysis platform specialized for the study of pathological tissues, which enables tissue segmentation by using artificial intelligence. In this study, we used HALO to quantify various histopathological changes and findings that were difficult to analyze using conventional image processing software. Using the tissue classifier module, the morphological features of degeneration/necrosis of the hepatocytes and muscle fibers, bile duct in the liver, basophilic tubules and hyaline casts in the kidney, cortex in the thymus, and red pulp, white pulp, and marginal zone in the spleen were learned and separated, and areas of interest were quantified. Furthermore, using the cytonuclear module and vacuole module in combination with the tissue classifier module, the number of erythroblasts in the red pulp of the spleen and each area of acinar cells in the parotid gland were quantified. The results of quantitative analysis were correlated with the histopathological grades evaluated by pathologists. By using artificial intelligence and other functions of HALO, we recognized morphological features, analyzed histopathological changes, and quantified the histopathological grades of various findings. The analysis of histopathological changes using HALO is expected to support pathology evaluations.</description><identifier>ISSN: 0914-9198</identifier><identifier>EISSN: 1881-915X</identifier><identifier>EISSN: 1347-7404</identifier><identifier>DOI: 10.1293/tox.2019-0022</identifier><identifier>PMID: 31719761</identifier><language>eng</language><publisher>Tokyo: JAPANESE SOCIETY OF TOXICOLOGIC PATHOLOGY</publisher><subject>Acinar cells ; Artificial intelligence ; Bile ducts ; Classifiers ; Correlation analysis ; Degeneration ; Digital imaging ; digital pathology ; Erythroblasts ; Evaluation ; Feature recognition ; HALO ; Hepatocytes ; Image analysis ; Image processing ; Image segmentation ; Modules ; Morphology ; morphometry ; Muscles ; Necrosis ; Parotid gland ; Pathology ; Quantitative analysis ; Red pulp ; Renal cortex ; Spleen ; Tissues ; Tubules</subject><ispartof>Journal of Toxicologic Pathology, 2019, Vol.32(4), pp.319-327</ispartof><rights>2019 The Japanese Society of Toxicologic Pathology</rights><rights>Copyright Japan Science and Technology Agency 2019</rights><rights>2019 The Japanese Society of Toxicologic Pathology 2019</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c734t-4531dacf99283480b8b9c0c3b32cd2f88efd1e9786ab1bbcf62db72719907cb63</citedby><cites>FETCH-LOGICAL-c734t-4531dacf99283480b8b9c0c3b32cd2f88efd1e9786ab1bbcf62db72719907cb63</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC6831494/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC6831494/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,723,776,780,881,1877,27901,27902,53766,53768</link.rule.ids></links><search><creatorcontrib>Horai, Yasushi</creatorcontrib><creatorcontrib>Mizukawa, Mao</creatorcontrib><creatorcontrib>Nishina, Hironobu</creatorcontrib><creatorcontrib>Nishikawa, Satomi</creatorcontrib><creatorcontrib>Ono, Yuko</creatorcontrib><creatorcontrib>Takemoto, Kana</creatorcontrib><creatorcontrib>Baba, Nobuyuki</creatorcontrib><creatorcontrib>Sohyaku Innovative Research Division</creatorcontrib><creatorcontrib>Mitsubishi Tanabe Pharma Corporation</creatorcontrib><title>Quantification of histopathological findings using a novel image analysis platform</title><title>Journal of Toxicologic Pathology</title><addtitle>J Toxicol Pathol</addtitle><description>Digital pathology, including image analysis and automatic diagnosis of pathological tissue, has been developed remarkably. HALO is an image analysis platform specialized for the study of pathological tissues, which enables tissue segmentation by using artificial intelligence. In this study, we used HALO to quantify various histopathological changes and findings that were difficult to analyze using conventional image processing software. Using the tissue classifier module, the morphological features of degeneration/necrosis of the hepatocytes and muscle fibers, bile duct in the liver, basophilic tubules and hyaline casts in the kidney, cortex in the thymus, and red pulp, white pulp, and marginal zone in the spleen were learned and separated, and areas of interest were quantified. Furthermore, using the cytonuclear module and vacuole module in combination with the tissue classifier module, the number of erythroblasts in the red pulp of the spleen and each area of acinar cells in the parotid gland were quantified. The results of quantitative analysis were correlated with the histopathological grades evaluated by pathologists. By using artificial intelligence and other functions of HALO, we recognized morphological features, analyzed histopathological changes, and quantified the histopathological grades of various findings. The analysis of histopathological changes using HALO is expected to support pathology evaluations.</description><subject>Acinar cells</subject><subject>Artificial intelligence</subject><subject>Bile ducts</subject><subject>Classifiers</subject><subject>Correlation analysis</subject><subject>Degeneration</subject><subject>Digital imaging</subject><subject>digital pathology</subject><subject>Erythroblasts</subject><subject>Evaluation</subject><subject>Feature recognition</subject><subject>HALO</subject><subject>Hepatocytes</subject><subject>Image analysis</subject><subject>Image processing</subject><subject>Image segmentation</subject><subject>Modules</subject><subject>Morphology</subject><subject>morphometry</subject><subject>Muscles</subject><subject>Necrosis</subject><subject>Parotid gland</subject><subject>Pathology</subject><subject>Quantitative analysis</subject><subject>Red pulp</subject><subject>Renal cortex</subject><subject>Spleen</subject><subject>Tissues</subject><subject>Tubules</subject><issn>0914-9198</issn><issn>1881-915X</issn><issn>1347-7404</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNpdUc9vFCEUJkZjt6tH75N48TKVXzPAxcRsbGvSxGjaxBthGNhlw8IITGP_-zLdukYP8ID3ve99jw-AdwheICzIxxJ_X2CIRAshxi_ACnGOWoG6ny_BCgpE61nwM3Ce874iGOzIa3BGEEOC9WgFfnyfVSjOOq2Ki6GJttm5XOKkyi76uK3vvrEujC5sczPnGhrVhHhvfOMOamsaFZR_yC43k1fFxnR4A15Z5bN5-xzX4O7yy-3mur35dvV18_mm1YzQ0tKOoFFpKwTmhHI48EFoqMlAsB6x5dzYERnBeK8GNAza9ngcGK7CBWR66MkafDryTvNwMKM2oSTl5ZSqrvQgo3Ly30xwO7mN97LnBFFBK8GHZ4IUf80mF3lwWRvvVTBxzhJXGO5g16MKff8fdB_nVCd_QiFMKavzrEF7ROkUc07GnsQgKBe3ZHVLLm7Jxa2Kvzriq8jlo2PwLpi_1ONIasGk_pQQDKmEqC6y3AlmhAjBIatMmyPTPpdqyqmvSsVpb576Eizpsp36n7J6p5I0gTwCAQK2zA</recordid><startdate>20190101</startdate><enddate>20190101</enddate><creator>Horai, Yasushi</creator><creator>Mizukawa, Mao</creator><creator>Nishina, Hironobu</creator><creator>Nishikawa, Satomi</creator><creator>Ono, Yuko</creator><creator>Takemoto, Kana</creator><creator>Baba, Nobuyuki</creator><general>JAPANESE SOCIETY OF TOXICOLOGIC PATHOLOGY</general><general>The Japanese Society of Toxicologic Pathology</general><general>Japan Science and Technology Agency</general><general>Japanese Society of Toxicologic Pathology</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7U7</scope><scope>C1K</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20190101</creationdate><title>Quantification of histopathological findings using a novel image analysis platform</title><author>Horai, Yasushi ; Mizukawa, Mao ; Nishina, Hironobu ; Nishikawa, Satomi ; Ono, Yuko ; Takemoto, Kana ; Baba, Nobuyuki</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c734t-4531dacf99283480b8b9c0c3b32cd2f88efd1e9786ab1bbcf62db72719907cb63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Acinar cells</topic><topic>Artificial intelligence</topic><topic>Bile ducts</topic><topic>Classifiers</topic><topic>Correlation analysis</topic><topic>Degeneration</topic><topic>Digital imaging</topic><topic>digital pathology</topic><topic>Erythroblasts</topic><topic>Evaluation</topic><topic>Feature recognition</topic><topic>HALO</topic><topic>Hepatocytes</topic><topic>Image analysis</topic><topic>Image processing</topic><topic>Image segmentation</topic><topic>Modules</topic><topic>Morphology</topic><topic>morphometry</topic><topic>Muscles</topic><topic>Necrosis</topic><topic>Parotid gland</topic><topic>Pathology</topic><topic>Quantitative analysis</topic><topic>Red pulp</topic><topic>Renal cortex</topic><topic>Spleen</topic><topic>Tissues</topic><topic>Tubules</topic><toplevel>online_resources</toplevel><creatorcontrib>Horai, Yasushi</creatorcontrib><creatorcontrib>Mizukawa, Mao</creatorcontrib><creatorcontrib>Nishina, Hironobu</creatorcontrib><creatorcontrib>Nishikawa, Satomi</creatorcontrib><creatorcontrib>Ono, Yuko</creatorcontrib><creatorcontrib>Takemoto, Kana</creatorcontrib><creatorcontrib>Baba, Nobuyuki</creatorcontrib><creatorcontrib>Sohyaku Innovative Research Division</creatorcontrib><creatorcontrib>Mitsubishi Tanabe Pharma Corporation</creatorcontrib><collection>CrossRef</collection><collection>Toxicology Abstracts</collection><collection>Environmental Sciences and Pollution Management</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Journal of Toxicologic Pathology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Horai, Yasushi</au><au>Mizukawa, Mao</au><au>Nishina, Hironobu</au><au>Nishikawa, Satomi</au><au>Ono, Yuko</au><au>Takemoto, Kana</au><au>Baba, Nobuyuki</au><aucorp>Sohyaku Innovative Research Division</aucorp><aucorp>Mitsubishi Tanabe Pharma Corporation</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Quantification of histopathological findings using a novel image analysis platform</atitle><jtitle>Journal of Toxicologic Pathology</jtitle><addtitle>J Toxicol Pathol</addtitle><date>2019-01-01</date><risdate>2019</risdate><volume>32</volume><issue>4</issue><spage>319</spage><epage>327</epage><pages>319-327</pages><issn>0914-9198</issn><eissn>1881-915X</eissn><eissn>1347-7404</eissn><abstract>Digital pathology, including image analysis and automatic diagnosis of pathological tissue, has been developed remarkably. HALO is an image analysis platform specialized for the study of pathological tissues, which enables tissue segmentation by using artificial intelligence. In this study, we used HALO to quantify various histopathological changes and findings that were difficult to analyze using conventional image processing software. Using the tissue classifier module, the morphological features of degeneration/necrosis of the hepatocytes and muscle fibers, bile duct in the liver, basophilic tubules and hyaline casts in the kidney, cortex in the thymus, and red pulp, white pulp, and marginal zone in the spleen were learned and separated, and areas of interest were quantified. Furthermore, using the cytonuclear module and vacuole module in combination with the tissue classifier module, the number of erythroblasts in the red pulp of the spleen and each area of acinar cells in the parotid gland were quantified. The results of quantitative analysis were correlated with the histopathological grades evaluated by pathologists. By using artificial intelligence and other functions of HALO, we recognized morphological features, analyzed histopathological changes, and quantified the histopathological grades of various findings. The analysis of histopathological changes using HALO is expected to support pathology evaluations.</abstract><cop>Tokyo</cop><pub>JAPANESE SOCIETY OF TOXICOLOGIC PATHOLOGY</pub><pmid>31719761</pmid><doi>10.1293/tox.2019-0022</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0914-9198 |
| ispartof | Journal of Toxicologic Pathology, 2019, Vol.32(4), pp.319-327 |
| issn | 0914-9198 1881-915X 1347-7404 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_6831494 |
| source | J-STAGE Free; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central; PubMed Central Open Access |
| subjects | Acinar cells Artificial intelligence Bile ducts Classifiers Correlation analysis Degeneration Digital imaging digital pathology Erythroblasts Evaluation Feature recognition HALO Hepatocytes Image analysis Image processing Image segmentation Modules Morphology morphometry Muscles Necrosis Parotid gland Pathology Quantitative analysis Red pulp Renal cortex Spleen Tissues Tubules |
| title | Quantification of histopathological findings using a novel image analysis platform |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T16%3A02%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Quantification%20of%20histopathological%20findings%20using%20a%20novel%20image%20analysis%20platform&rft.jtitle=Journal%20of%20Toxicologic%20Pathology&rft.au=Horai,%20Yasushi&rft.aucorp=Sohyaku%20Innovative%20Research%20Division&rft.date=2019-01-01&rft.volume=32&rft.issue=4&rft.spage=319&rft.epage=327&rft.pages=319-327&rft.issn=0914-9198&rft.eissn=1881-915X&rft_id=info:doi/10.1293/tox.2019-0022&rft_dat=%3Cproquest_pubme%3E2314250561%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2311244745&rft_id=info:pmid/31719761&rfr_iscdi=true |