{"updated":"2025-01-19T23:56:23.749389+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00192960","sets":["934:989:9407:9598"]},"path":["9598"],"owner":"44499","recid":"192960","title":["Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer―An Application for Diffuse Lung Disease Classification"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-12-20"},"_buckets":{"deposit":"155587e6-2fdd-43d2-888e-2a995582a608"},"_deposit":{"id":"192960","pid":{"type":"depid","value":"192960","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer―An Application for Diffuse Lung Disease Classification","author_link":["451656","451658","451660","451657","451661","451663","451659","451662"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer―An Application for Diffuse Lung Disease Classification"},{"subitem_title":"Feature Representation Analysis of Deep Convolutional Neural Network using Two-stage Feature Transfer―An Application for Diffuse Lung Disease Classification","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[オリジナル論文] deep convolutional neural networks, transfer learning, image recognition, textural recognition, medical imaging","subitem_subject_scheme":"Other"}]},"item_type_id":"3","publish_date":"2018-12-20","item_3_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology／University of Tsukuba"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology"},{"subitem_text_value":"Yamaguchi University"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology／University of Electro-Communications"}]},"item_3_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology / University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology","subitem_text_language":"en"},{"subitem_text_value":"Yamaguchi University","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology / University of Electro-Communications","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/192960/files/IPSJ-TOM1103008.pdf","label":"IPSJ-TOM1103008.pdf"},"date":[{"dateType":"Available","dateValue":"2020-12-20"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-TOM1103008.pdf","filesize":[{"value":"5.1 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":"17"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"b5ce808a-aaad-446f-a1e3-23aeb0454f1a","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2018 by the Information Processing Society of Japan"}]},"item_3_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Aiga, Suzuki"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hidenori, Sakanashi"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shoji, Kido"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hayaru, Shouno"}],"nameIdentifiers":[{}]}]},"item_3_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Aiga, Suzuki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hidenori, Sakanashi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shoji, Kido","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hayaru, Shouno","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_3_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11464803","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_3_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7780","subitem_source_identifier_type":"ISSN"}]},"item_3_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Transfer learning is a machine learning technique designed to improve generalization performance by using pre-trained parameters obtained from other learning tasks. For image recognition tasks, many previous studies have reported that, when transfer learning is applied to deep neural networks, performance improves, despite having limited training data. This paper proposes a two-stage feature transfer learning method focusing on the recognition of textural medical images. During the proposed method, a model is successively trained with massive amounts of natural images, some textural images, and the target images. We applied this method to the classification task of textural X-ray computed tomography images of diffuse lung diseases. In our experiment, the two-stage feature transfer achieves the best performance compared to a from-scratch learning and a conventional single-stage feature transfer. We also investigated the robustness of the target dataset, based on size. Two-stage feature transfer shows better robustness than the other two learning methods. Moreover, we analyzed the feature representations obtained from DLDs imagery inputs for each feature transfer models using a visualization method. We showed that the two-stage feature transfer obtains both edge and textural features of DLDs, which does not occur in conventional single-stage feature transfer models.","subitem_description_type":"Other"}]},"item_3_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Transfer learning is a machine learning technique designed to improve generalization performance by using pre-trained parameters obtained from other learning tasks. For image recognition tasks, many previous studies have reported that, when transfer learning is applied to deep neural networks, performance improves, despite having limited training data. This paper proposes a two-stage feature transfer learning method focusing on the recognition of textural medical images. During the proposed method, a model is successively trained with massive amounts of natural images, some textural images, and the target images. We applied this method to the classification task of textural X-ray computed tomography images of diffuse lung diseases. In our experiment, the two-stage feature transfer achieves the best performance compared to a from-scratch learning and a conventional single-stage feature transfer. We also investigated the robustness of the target dataset, based on size. Two-stage feature transfer shows better robustness than the other two learning methods. Moreover, we analyzed the feature representations obtained from DLDs imagery inputs for each feature transfer models using a visualization method. We showed that the two-stage feature transfer obtains both edge and textural features of DLDs, which does not occur in conventional single-stage feature transfer models.","subitem_description_type":"Other"}]},"item_3_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"83","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌数理モデル化と応用（TOM）"}],"bibliographicPageStart":"74","bibliographicIssueDates":{"bibliographicIssueDate":"2018-12-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"11"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T00:58:38.108560+00:00","id":192960,"links":{}}