Case-based Similar Image Retrieval for Weakly Annotated Large Histopathological Images of Malignant Lymphoma Using Deep Metric Learning

In the present study, we propose a novel case-based similar image retrieval (SIR) method for hematoxylin and eosin (H&E)-stained histopathological images of malignant lymphoma. When a whole slide image (WSI) is used as an input query, it is desirable to be able to retrieve similar cases by focus...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hashimoto, Noriaki, Takagi, Yusuke, Masuda, Hiroki, Miyoshi, Hiroaki, Kohno, Kei, Nagaishi, Miharu, Sato, Kensaku, Takeuchi, Mai, Furuta, Takuya, Kawamoto, Keisuke, Yamada, Kyohei, Moritsubo, Mayuko, Inoue, Kanako, Shimasaki, Yasumasa, Ogura, Yusuke, Imamoto, Teppei, Mishina, Tatsuzo, Tanaka, Ken, Kawaguchi, Yoshino, Nakamura, Shigeo, Ohshima, Koichi, Hontani, Hidekata, Takeuchi, Ichiro
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Hashimoto, Noriaki
Takagi, Yusuke
Masuda, Hiroki
Miyoshi, Hiroaki
Kohno, Kei
Nagaishi, Miharu
Sato, Kensaku
Takeuchi, Mai
Furuta, Takuya
Kawamoto, Keisuke
Yamada, Kyohei
Moritsubo, Mayuko
Inoue, Kanako
Shimasaki, Yasumasa
Ogura, Yusuke
Imamoto, Teppei
Mishina, Tatsuzo
Tanaka, Ken
Kawaguchi, Yoshino
Nakamura, Shigeo
Ohshima, Koichi
Hontani, Hidekata
Takeuchi, Ichiro
description In the present study, we propose a novel case-based similar image retrieval (SIR) method for hematoxylin and eosin (H&E)-stained histopathological images of malignant lymphoma. When a whole slide image (WSI) is used as an input query, it is desirable to be able to retrieve similar cases by focusing on image patches in pathologically important regions such as tumor cells. To address this problem, we employ attention-based multiple instance learning, which enables us to focus on tumor-specific regions when the similarity between cases is computed. Moreover, we employ contrastive distance metric learning to incorporate immunohistochemical (IHC) staining patterns as useful supervised information for defining appropriate similarity between heterogeneous malignant lymphoma cases. In the experiment with 249 malignant lymphoma patients, we confirmed that the proposed method exhibited higher evaluation measures than the baseline case-based SIR methods. Furthermore, the subjective evaluation by pathologists revealed that our similarity measure using IHC staining patterns is appropriate for representing the similarity of H&E-stained tissue images for malignant lymphoma.
doi_str_mv 10.48550/arxiv.2107.03602
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2107_03602</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2107_03602</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-5ad1708db902f693a9dfa0ffb2d24336714a3fa2a3126349b94f37a5e157606b3</originalsourceid><addsrcrecordid>eNotkE1OwzAQhbNhgQoHYMVcIMGxE7tZVuGnlVIhQRHLaNLYqYVjR45VkRNwbdLA5o309M1bfFF0l5IkW-c5eUD_rc8JTYlICOOEXkc_JY4ybuZo4V332qCHXY-dhDcZvJZnNKCch0-JX2aCjbUuYJjhCv0MbfUY3IDh5Izr9HGGl-cRnII9Gt1ZtAGqqR9Orkf4GLXt4FHKAfaX-SNUEr2dy5voSqEZ5e3_XUWH56dDuY2r15dduali5ILGObapIOu2KQhVvGBYtAqJUg1tacYYF2mGTCFFllLOsqIpMsUE5jLNBSe8Yavo_m92MVEPXvfop_pipF6MsF-6slz3</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Case-based Similar Image Retrieval for Weakly Annotated Large Histopathological Images of Malignant Lymphoma Using Deep Metric Learning</title><source>arXiv.org</source><creator>Hashimoto, Noriaki ; Takagi, Yusuke ; Masuda, Hiroki ; Miyoshi, Hiroaki ; Kohno, Kei ; Nagaishi, Miharu ; Sato, Kensaku ; Takeuchi, Mai ; Furuta, Takuya ; Kawamoto, Keisuke ; Yamada, Kyohei ; Moritsubo, Mayuko ; Inoue, Kanako ; Shimasaki, Yasumasa ; Ogura, Yusuke ; Imamoto, Teppei ; Mishina, Tatsuzo ; Tanaka, Ken ; Kawaguchi, Yoshino ; Nakamura, Shigeo ; Ohshima, Koichi ; Hontani, Hidekata ; Takeuchi, Ichiro</creator><creatorcontrib>Hashimoto, Noriaki ; Takagi, Yusuke ; Masuda, Hiroki ; Miyoshi, Hiroaki ; Kohno, Kei ; Nagaishi, Miharu ; Sato, Kensaku ; Takeuchi, Mai ; Furuta, Takuya ; Kawamoto, Keisuke ; Yamada, Kyohei ; Moritsubo, Mayuko ; Inoue, Kanako ; Shimasaki, Yasumasa ; Ogura, Yusuke ; Imamoto, Teppei ; Mishina, Tatsuzo ; Tanaka, Ken ; Kawaguchi, Yoshino ; Nakamura, Shigeo ; Ohshima, Koichi ; Hontani, Hidekata ; Takeuchi, Ichiro</creatorcontrib><description>In the present study, we propose a novel case-based similar image retrieval (SIR) method for hematoxylin and eosin (H&amp;E)-stained histopathological images of malignant lymphoma. When a whole slide image (WSI) is used as an input query, it is desirable to be able to retrieve similar cases by focusing on image patches in pathologically important regions such as tumor cells. To address this problem, we employ attention-based multiple instance learning, which enables us to focus on tumor-specific regions when the similarity between cases is computed. Moreover, we employ contrastive distance metric learning to incorporate immunohistochemical (IHC) staining patterns as useful supervised information for defining appropriate similarity between heterogeneous malignant lymphoma cases. In the experiment with 249 malignant lymphoma patients, we confirmed that the proposed method exhibited higher evaluation measures than the baseline case-based SIR methods. Furthermore, the subjective evaluation by pathologists revealed that our similarity measure using IHC staining patterns is appropriate for representing the similarity of H&amp;E-stained tissue images for malignant lymphoma.</description><identifier>DOI: 10.48550/arxiv.2107.03602</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2021-07</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2107.03602$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2107.03602$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Hashimoto, Noriaki</creatorcontrib><creatorcontrib>Takagi, Yusuke</creatorcontrib><creatorcontrib>Masuda, Hiroki</creatorcontrib><creatorcontrib>Miyoshi, Hiroaki</creatorcontrib><creatorcontrib>Kohno, Kei</creatorcontrib><creatorcontrib>Nagaishi, Miharu</creatorcontrib><creatorcontrib>Sato, Kensaku</creatorcontrib><creatorcontrib>Takeuchi, Mai</creatorcontrib><creatorcontrib>Furuta, Takuya</creatorcontrib><creatorcontrib>Kawamoto, Keisuke</creatorcontrib><creatorcontrib>Yamada, Kyohei</creatorcontrib><creatorcontrib>Moritsubo, Mayuko</creatorcontrib><creatorcontrib>Inoue, Kanako</creatorcontrib><creatorcontrib>Shimasaki, Yasumasa</creatorcontrib><creatorcontrib>Ogura, Yusuke</creatorcontrib><creatorcontrib>Imamoto, Teppei</creatorcontrib><creatorcontrib>Mishina, Tatsuzo</creatorcontrib><creatorcontrib>Tanaka, Ken</creatorcontrib><creatorcontrib>Kawaguchi, Yoshino</creatorcontrib><creatorcontrib>Nakamura, Shigeo</creatorcontrib><creatorcontrib>Ohshima, Koichi</creatorcontrib><creatorcontrib>Hontani, Hidekata</creatorcontrib><creatorcontrib>Takeuchi, Ichiro</creatorcontrib><title>Case-based Similar Image Retrieval for Weakly Annotated Large Histopathological Images of Malignant Lymphoma Using Deep Metric Learning</title><description>In the present study, we propose a novel case-based similar image retrieval (SIR) method for hematoxylin and eosin (H&amp;E)-stained histopathological images of malignant lymphoma. When a whole slide image (WSI) is used as an input query, it is desirable to be able to retrieve similar cases by focusing on image patches in pathologically important regions such as tumor cells. To address this problem, we employ attention-based multiple instance learning, which enables us to focus on tumor-specific regions when the similarity between cases is computed. Moreover, we employ contrastive distance metric learning to incorporate immunohistochemical (IHC) staining patterns as useful supervised information for defining appropriate similarity between heterogeneous malignant lymphoma cases. In the experiment with 249 malignant lymphoma patients, we confirmed that the proposed method exhibited higher evaluation measures than the baseline case-based SIR methods. Furthermore, the subjective evaluation by pathologists revealed that our similarity measure using IHC staining patterns is appropriate for representing the similarity of H&amp;E-stained tissue images for malignant lymphoma.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotkE1OwzAQhbNhgQoHYMVcIMGxE7tZVuGnlVIhQRHLaNLYqYVjR45VkRNwbdLA5o309M1bfFF0l5IkW-c5eUD_rc8JTYlICOOEXkc_JY4ybuZo4V332qCHXY-dhDcZvJZnNKCch0-JX2aCjbUuYJjhCv0MbfUY3IDh5Izr9HGGl-cRnII9Gt1ZtAGqqR9Orkf4GLXt4FHKAfaX-SNUEr2dy5voSqEZ5e3_XUWH56dDuY2r15dduali5ILGObapIOu2KQhVvGBYtAqJUg1tacYYF2mGTCFFllLOsqIpMsUE5jLNBSe8Yavo_m92MVEPXvfop_pipF6MsF-6slz3</recordid><startdate>20210708</startdate><enddate>20210708</enddate><creator>Hashimoto, Noriaki</creator><creator>Takagi, Yusuke</creator><creator>Masuda, Hiroki</creator><creator>Miyoshi, Hiroaki</creator><creator>Kohno, Kei</creator><creator>Nagaishi, Miharu</creator><creator>Sato, Kensaku</creator><creator>Takeuchi, Mai</creator><creator>Furuta, Takuya</creator><creator>Kawamoto, Keisuke</creator><creator>Yamada, Kyohei</creator><creator>Moritsubo, Mayuko</creator><creator>Inoue, Kanako</creator><creator>Shimasaki, Yasumasa</creator><creator>Ogura, Yusuke</creator><creator>Imamoto, Teppei</creator><creator>Mishina, Tatsuzo</creator><creator>Tanaka, Ken</creator><creator>Kawaguchi, Yoshino</creator><creator>Nakamura, Shigeo</creator><creator>Ohshima, Koichi</creator><creator>Hontani, Hidekata</creator><creator>Takeuchi, Ichiro</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210708</creationdate><title>Case-based Similar Image Retrieval for Weakly Annotated Large Histopathological Images of Malignant Lymphoma Using Deep Metric Learning</title><author>Hashimoto, Noriaki ; Takagi, Yusuke ; Masuda, Hiroki ; Miyoshi, Hiroaki ; Kohno, Kei ; Nagaishi, Miharu ; Sato, Kensaku ; Takeuchi, Mai ; Furuta, Takuya ; Kawamoto, Keisuke ; Yamada, Kyohei ; Moritsubo, Mayuko ; Inoue, Kanako ; Shimasaki, Yasumasa ; Ogura, Yusuke ; Imamoto, Teppei ; Mishina, Tatsuzo ; Tanaka, Ken ; Kawaguchi, Yoshino ; Nakamura, Shigeo ; Ohshima, Koichi ; Hontani, Hidekata ; Takeuchi, Ichiro</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-5ad1708db902f693a9dfa0ffb2d24336714a3fa2a3126349b94f37a5e157606b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Hashimoto, Noriaki</creatorcontrib><creatorcontrib>Takagi, Yusuke</creatorcontrib><creatorcontrib>Masuda, Hiroki</creatorcontrib><creatorcontrib>Miyoshi, Hiroaki</creatorcontrib><creatorcontrib>Kohno, Kei</creatorcontrib><creatorcontrib>Nagaishi, Miharu</creatorcontrib><creatorcontrib>Sato, Kensaku</creatorcontrib><creatorcontrib>Takeuchi, Mai</creatorcontrib><creatorcontrib>Furuta, Takuya</creatorcontrib><creatorcontrib>Kawamoto, Keisuke</creatorcontrib><creatorcontrib>Yamada, Kyohei</creatorcontrib><creatorcontrib>Moritsubo, Mayuko</creatorcontrib><creatorcontrib>Inoue, Kanako</creatorcontrib><creatorcontrib>Shimasaki, Yasumasa</creatorcontrib><creatorcontrib>Ogura, Yusuke</creatorcontrib><creatorcontrib>Imamoto, Teppei</creatorcontrib><creatorcontrib>Mishina, Tatsuzo</creatorcontrib><creatorcontrib>Tanaka, Ken</creatorcontrib><creatorcontrib>Kawaguchi, Yoshino</creatorcontrib><creatorcontrib>Nakamura, Shigeo</creatorcontrib><creatorcontrib>Ohshima, Koichi</creatorcontrib><creatorcontrib>Hontani, Hidekata</creatorcontrib><creatorcontrib>Takeuchi, Ichiro</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hashimoto, Noriaki</au><au>Takagi, Yusuke</au><au>Masuda, Hiroki</au><au>Miyoshi, Hiroaki</au><au>Kohno, Kei</au><au>Nagaishi, Miharu</au><au>Sato, Kensaku</au><au>Takeuchi, Mai</au><au>Furuta, Takuya</au><au>Kawamoto, Keisuke</au><au>Yamada, Kyohei</au><au>Moritsubo, Mayuko</au><au>Inoue, Kanako</au><au>Shimasaki, Yasumasa</au><au>Ogura, Yusuke</au><au>Imamoto, Teppei</au><au>Mishina, Tatsuzo</au><au>Tanaka, Ken</au><au>Kawaguchi, Yoshino</au><au>Nakamura, Shigeo</au><au>Ohshima, Koichi</au><au>Hontani, Hidekata</au><au>Takeuchi, Ichiro</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Case-based Similar Image Retrieval for Weakly Annotated Large Histopathological Images of Malignant Lymphoma Using Deep Metric Learning</atitle><date>2021-07-08</date><risdate>2021</risdate><abstract>In the present study, we propose a novel case-based similar image retrieval (SIR) method for hematoxylin and eosin (H&amp;E)-stained histopathological images of malignant lymphoma. When a whole slide image (WSI) is used as an input query, it is desirable to be able to retrieve similar cases by focusing on image patches in pathologically important regions such as tumor cells. To address this problem, we employ attention-based multiple instance learning, which enables us to focus on tumor-specific regions when the similarity between cases is computed. Moreover, we employ contrastive distance metric learning to incorporate immunohistochemical (IHC) staining patterns as useful supervised information for defining appropriate similarity between heterogeneous malignant lymphoma cases. In the experiment with 249 malignant lymphoma patients, we confirmed that the proposed method exhibited higher evaluation measures than the baseline case-based SIR methods. Furthermore, the subjective evaluation by pathologists revealed that our similarity measure using IHC staining patterns is appropriate for representing the similarity of H&amp;E-stained tissue images for malignant lymphoma.</abstract><doi>10.48550/arxiv.2107.03602</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2107.03602
ispartof
issn
language eng
recordid cdi_arxiv_primary_2107_03602
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Case-based Similar Image Retrieval for Weakly Annotated Large Histopathological Images of Malignant Lymphoma Using Deep Metric Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T16%3A32%3A18IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Case-based%20Similar%20Image%20Retrieval%20for%20Weakly%20Annotated%20Large%20Histopathological%20Images%20of%20Malignant%20Lymphoma%20Using%20Deep%20Metric%20Learning&rft.au=Hashimoto,%20Noriaki&rft.date=2021-07-08&rft_id=info:doi/10.48550/arxiv.2107.03602&rft_dat=%3Carxiv_GOX%3E2107_03602%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true