{"id":214261,"updated":"2025-01-19T16:50:40.045292+00:00","links":{},"created":"2025-01-19T01:15:05.171399+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00214261","sets":["1164:3980:10496:10732"]},"path":["10732"],"owner":"44499","recid":"214261","title":["深層学習を用いた新生児熱画像の部位検出に基づく体温抽出手法の検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-11-30"},"_buckets":{"deposit":"7c797dc0-e8a3-4308-a0ff-5aad00f3dd0b"},"_deposit":{"id":"214261","pid":{"type":"depid","value":"214261","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"深層学習を用いた新生児熱画像の部位検出に基づく体温抽出手法の検討","author_link":["549285","549287","549288","549290","549289","549286"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"深層学習を用いた新生児熱画像の部位検出に基づく体温抽出手法の検討"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"学習","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2021-11-30","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"大阪大学大学院情報科学研究科"},{"subitem_text_value":"大阪大学大学院情報科学研究科"},{"subitem_text_value":"大阪大学大学院情報科学研究科"},{"subitem_text_value":"大阪大学大学院情報科学研究科"},{"subitem_text_value":"長崎みなとメディカルセンター臨床工学部／長崎大学大学院医歯薬学総合研究科"},{"subitem_text_value":"鹿児島市立病院新生児内科"}]},"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/214261/files/IPSJ-ITS21087001.pdf","label":"IPSJ-ITS21087001.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-30"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-ITS21087001.pdf","filesize":[{"value":"3.2 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"37"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"154bb4e0-f363-4037-93a1-2bc364d6fb3f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"別府, 文香"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"吉川, 寛樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"内山, 彰"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"東野, 輝夫"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"濱田, 啓介"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"平川, 英司"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11515904","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":"2188-8965","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"新生児は体温調節機能が未熟なため，保育器を適切な温度に管理することが不可欠である．現在は，プローブで測定した体表温度を基に，医療者が手動で保育器の温度管理を行っている．しかし，新生児の皮膚は未熟なため，プローブが剥がれやすく，長時間の安定した測定は難しい．これに対して，サーモグラフィを用いることで，新生児に違和感やストレスを与えることなく体表温度の測定が可能となる．一方，サーモグラフィを用いた場合には，得られた熱画像から部位ごとの体表温度を抽出する必要がある．そこで本研究では，深層学習を用いて，新生児の熱画像から頭部・胸部・四肢の 6 箇所を検出する手法を提案する．提案手法では，CNN を用いて対象部位が見えない画像を分類した上で，YOLOv5 を用いて身体部位 6 箇所の検出モデルを構築する．さらに，検出部位を基に k-means 法を用いたクラスタリングを適用し，末梢温度や首元温度を取得する．新生児 26 名の熱画像 4820 枚を使用して性能評価を行った結果，部位検出の適合率，再現率はそれぞれ 94.8%，77.5% となった．また，取得温度とプローブで測定した体温には強い正の相関が見られ，体温取得方法として有効であることが分かった．末梢温度の抽出においては，クラスタリングを適用することで背景を除外し，末梢部位の温度分布を抽出可能な見通しを得た．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"7","bibliographic_titles":[{"bibliographic_title":"研究報告高度交通システムとスマートコミュニティ（ITS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-11-30","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2021-ITS-87"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}