{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00217857","sets":["1164:4619:10826:10925"]},"path":["10925"],"owner":"44499","recid":"217857","title":["深層学習を用いた子宮頸がん細胞の自動分類"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-05-05"},"_buckets":{"deposit":"cc862bdf-5dc7-464e-9bb8-296aacc76423"},"_deposit":{"id":"217857","pid":{"type":"depid","value":"217857","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"深層学習を用いた子宮頸がん細胞の自動分類","author_link":["565225","565223","565226","565224"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"深層学習を用いた子宮頸がん細胞の自動分類"},{"subitem_title":"Automatic classification of cervical cancer cells using deep learning","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"一般講演セッション2","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-05-05","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"杏林大学保健学部臨床検査技術学科"},{"subitem_text_value":"杏林大学保健学部臨床検査技術学科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Faculty of Health Sciences, Department of Medical Technology","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Health Sciences, Department of Medical Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/217857/files/IPSJ-CVIM22230044.pdf","label":"IPSJ-CVIM22230044.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM22230044.pdf","filesize":[{"value":"2.0 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"4cf69abc-6034-48a2-8786-52b5c7f06e0b","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"坪下, 幸寛"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"大河戸, 光章"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yukihiro, Tsuboshita","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Mitsuaki, Okodo","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11131797","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8701","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"現在，我々は画像認識において近年目覚ましい進展を見せている深層学習を子宮頸部の細胞診標本に適用し，専門技師の識別性能を超える自動がん細胞識別を実現させるため，子宮頸がん検診で得られた細胞診標本にアノテーションを付与した大規模なデータセットの作成を行っている．本レポートではこの取り組みについて報告する．現在，専門技師によるアノテーションが付与された画像数は約 1,181 枚，患者数は 246 人となり，現時点でも細胞診のデータセットとしては世界有数の規模となっている．このデータセットは，単に細胞診の検査結果の分類が付与されているだけはなく，HPV 検査，組織診に基づいた分類も付与されている．このデータセットを用いることで，細胞診で得られた顕微鏡標本データから，組織診で得られた結果を推定するといった実験も可能である．さらに，このデータセットを用いた深層学習による分類実験を実施した．ResNet34 を用いて細胞診で得られた顕微鏡画像で組織診の診断を予測する実験を行ったところ，正確度 0.796，感度 0.723，特異度 0.878 となり専門技師の行う形態学検査の性能 (感度 0.7，特異度 0.9) とほぼ匹敵する結果を得た．また，FullGrad を用いた注目点の可視化を行ったところ，得られた学習済みモデルは正しく異型細胞を注目していることが分かった．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2022-05-05","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"44","bibliographicVolumeNumber":"2022-CVIM-230"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":217857,"updated":"2025-01-19T15:21:22.245094+00:00","links":{},"created":"2025-01-19T01:18:17.095682+00:00"}