{"created":"2025-01-19T01:28:12.486538+00:00","updated":"2025-01-19T11:37:32.016224+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229133","sets":["1164:3206:11201:11417"]},"path":["11417"],"owner":"44499","recid":"229133","title":["重症度クラスを条件とした拡散モデルによる医用画像生成"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-11-09"},"_buckets":{"deposit":"a4ff5129-0751-439e-81b3-d15b59aa2d60"},"_deposit":{"id":"229133","pid":{"type":"depid","value":"229133","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"重症度クラスを条件とした拡散モデルによる医用画像生成","author_link":["615635","615636"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"重症度クラスを条件とした拡散モデルによる医用画像生成"}]},"item_type_id":"4","publish_date":"2023-11-09","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"九州大学"},{"subitem_text_value":"九州大学"}]},"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/229133/files/IPSJ-CG23192019.pdf","label":"IPSJ-CG23192019.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CG23192019.pdf","filesize":[{"value":"1.8 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"28"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"b254dc7f-c12c-4e7b-a4fc-8a52395df37b","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 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":"竹崎, 隼平"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"内田, 誠一"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10100541","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":"2188-8949","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"生成モデルを用いた医用画像生成は，生成画像の様々な応用が期待できるため非常に重要なタスクである．医用画像に付与されているクラスラベルには一般的なクラスと異なり，各クラス間で順序関係を満たす重症度クラスが付けられているものがある．重症度クラスが付与された医用画像の深層学習では，クラスラベルの他に順序関係を取り入れることで，クラス単体の学習では獲得できない特徴を捉えることが可能である．本研究では，生成モデルの一つである拡散モデルにおいて重症度クラスの順序関係を学習する重症度クラス拡散モデルを提案する．提案手法では，推定ノイズによって順序関係を捉える損失関数である順序損失での学習と，拡散モデルの時刻情報を使った損失関数の重み付けを行う．本手法は重症度クラスを持つ眼底画像及び内視鏡画像を使用した評価実験を通じて，従来の拡散モデルに比べて高い生成精度を達成することを確認した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータグラフィックスとビジュアル情報学（CG）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-11-09","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"19","bibliographicVolumeNumber":"2023-CG-192"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":229133,"links":{}}