{"created":"2025-01-19T01:18:16.514342+00:00","updated":"2025-01-19T15:21:33.268172+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00217847","sets":["1164:4619:10826:10925"]},"path":["10925"],"owner":"44499","recid":"217847","title":["胚画像からの染色体異常の識別予測の可能性検証"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-05-05"},"_buckets":{"deposit":"a810a1ce-f568-444e-b1c8-a0053b651d0a"},"_deposit":{"id":"217847","pid":{"type":"depid","value":"217847","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"胚画像からの染色体異常の識別予測の可能性検証","author_link":["565180","565179","565184","565182","565183","565181"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"胚画像からの染色体異常の識別予測の可能性検証"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"卒論スポットライトセッション","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":"豊田工業大学"},{"subitem_text_value":"名古屋市立大学"},{"subitem_text_value":"名古屋市立大学"},{"subitem_text_value":"さわだウイメンズクリニック"},{"subitem_text_value":"名古屋市立大学"},{"subitem_text_value":"豊田工業大学"}]},"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/217847/files/IPSJ-CVIM22230034.pdf","label":"IPSJ-CVIM22230034.pdf"},"date":[{"dateType":"Available","dateValue":"2024-05-05"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM22230034.pdf","filesize":[{"value":"5.3 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":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"2013f71e-57b5-4785-af1b-3859c20d1e4d","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"宮田, 陸"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"澤田, 祐季"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"佐藤, 剛"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"澤田, 富夫"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"杉浦, 真弓"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"浮田, 宗伯"}],"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":"年々，出産の高齢化が進んでおり，不妊治療の需要の高まりとともに体外受精の需要が高まっている．体外受精を行うにあたって，出産成功確率の高い染色体異常の無い胚を選ぶことが重要である．染色体異常の胚の識別は専門家であっても非常に困難である．本研究では深層学習を用いてこの染色体異常を胚画像から識別予測の可能性を検証する．本研究では Attention Branch Network（ABN)[1] をベースとした [2][3] のモデルを用いて学習を行った．結果は過学習が起こってしまい精度は悪かった．また，データセットの選別とデータ拡張を行った．時間が十分に経過していない，特徴が少ない胚画像を除去するためにある経過時間後以降の胚画像を使用した．さらに，データの少なさのカバーと過学習の抑制のためにデータ拡張を行った．様々な条件を試した結果，受精後 100 時間後以降の画像を使い，Crop のデータ拡張を行った場合に，accuracy, auc-roc, precision が最も高い値をとった．また，上記に加え画像の明度，コントラストを変更するデータ拡張を行った場合に，recall, f-measure が最も高い値をとった．全体を通して精度は悪く，染色体異常を胚画像から識別するのは非常に困難であるのが分かった．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","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":"34","bibliographicVolumeNumber":"2022-CVIM-230"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":217847,"links":{}}