WEKO3
AND
アイテム
{"_buckets": {"deposit": "eb59d9f2-3e98-4a0e-b6ce-74b22d05bc61"}, "_deposit": {"id": "53736", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "53736"}, "status": "published"}, "_oai": {"id": "oai:tsukuba.repo.nii.ac.jp:00053736"}, "item_5_biblio_info_6": {"attribute_name": "\u66f8\u8a8c\u60c5\u5831", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2019-06", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "25", "bibliographicPageStart": "e16119", "bibliographicVolumeNumber": "98", "bibliographic_titles": [{"bibliographic_title": "Medicine"}]}]}, "item_5_description_4": {"attribute_name": "\u6284\u9332", "attribute_value_mlt": [{"subitem_description": "To compare results for radiological prediction of pathological invasiveness in lung adenocarcinoma between radiologists and a deep learning (DL) system.\n\nNinety patients (50 men, 40 women; mean age, 66 years; range, 40-88 years) who underwent pre-operative chest computed tomography (CT) with 0.625-mm slice thickness were included in this retrospective study. Twenty-four cases of adenocarcinoma in situ (AIS), 20 cases of minimally invasive adenocarcinoma (MIA), and 46 cases of invasive adenocarcinoma (IVA) were pathologically diagnosed. Three radiologists of different levels of experience diagnosed each nodule by using previously documented CT findings to predict pathological invasiveness. DL was structured using a 3-dimensional (3D) convolutional neural network (3D-CNN) constructed with 2 successive pairs of convolution and max-pooling layers, and 2 fully connected layers. The output layer comprises 3 nodes to recognize the 3 conditions of adenocarcinoma (AIS, MIA, and IVA) or 2 nodes for 2 conditions (AIS and MIA/IVA). Results from DL and the 3 radiologists were statistically compared.\n\nNo significant differences in pathological diagnostic accuracy rates were seen between DL and the 3 radiologists (P\u003e. 11). Receiver operating characteristic analysis demonstrated that area under the curve for DL (0.712) was almost the same as that for the radiologist with extensive experience (0.714; P=. 98). Compared with the consensus results from radiologists, DL offered significantly inferior sensitivity (P=. 0005), but significantly superior specificity (P=. 02).\n\nDespite the small training data set, diagnostic performance of DL was almost the same as the radiologist with extensive experience. In particular, DL provided higher specificity than radiologists.", "subitem_description_type": "Abstract"}]}, "item_5_publisher_27": {"attribute_name": "\u51fa\u7248\u8005", "attribute_value_mlt": [{"subitem_publisher": "Wolters Kluwer Health, Inc."}]}, "item_5_relation_10": {"attribute_name": "PubMed\u756a\u53f7", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "31232960", "subitem_relation_type_select": "PMID"}}]}, "item_5_relation_11": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "10.1097/MD.0000000000016119", "subitem_relation_type_select": "DOI"}}]}, "item_5_rights_12": {"attribute_name": "\u6a29\u5229", "attribute_value_mlt": [{"subitem_rights": "\u00a9 2019 the Author(s). Published by Wolters Kluwer Health, Inc. This is an open access article distributed under the terms of the Creative Commons Attribution-Non Commercial-No Derivatives License 4.0 (CCBY-NCND), where it is permissible to download and share the work provided it is properly cited. The work cannot be changed in any way or used commercially without permission from the journal."}]}, "item_5_select_15": {"attribute_name": "\u8457\u8005\u7248\u30d5\u30e9\u30b0", "attribute_value_mlt": [{"subitem_select_item": "publisher"}]}, "item_5_source_id_7": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "0025-7974", "subitem_source_identifier_type": "ISSN"}]}, "item_creator": {"attribute_name": "\u8457\u8005", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "\u91ce\u53e3, \u96c5\u4e4b"}, {"creatorName": "\u30ce\u30b0\u30c1, \u30de\u30b5\u30e6\u30ad", "creatorNameLang": "ja-Kana"}, {"creatorName": "NOGUCHI, Masayuki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "124641", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "00198582", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000000198582"}, {"nameIdentifier": "0000001620", "nameIdentifierScheme": "\u7b51\u6ce2\u5927\u5b66\u7814\u7a76\u8005\u7dcf\u89a7", "nameIdentifierURI": "http://trios.tsukuba.ac.jp/researcher/0000001620"}]}, {"creatorNames": [{"creatorName": "Yanagawa, Masahiro", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "216716", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Niioka, Hirohiko", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "216717", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Hata, Akinori", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "216718", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Kikuchi, Noriko", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "216719", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Honda, Osamu", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "216720", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Kurakami, Hiroyuki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "216721", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Morii, Eiichi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "216722", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Watanabe, Yoshiyuki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "216723", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Miyake, Jun", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "216724", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Tomiyama, Noriyuki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "216725", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "\u30d5\u30a1\u30a4\u30eb\u60c5\u5831", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2019-12-12"}], "displaytype": "detail", "download_preview_message": "", "filename": "Medicine_98-25.pdf", "filesize": [{"value": "1.1 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_11", "mimetype": "application/pdf", "size": 11000000, "url": {"label": "Medicine_98-25", "url": "https://tsukuba.repo.nii.ac.jp/record/53736/files/Medicine_98-25.pdf"}, "version_id": "22cbe515-ee00-495e-9ff7-4e5720e02160"}]}, "item_language": {"attribute_name": "\u8a00\u8a9e", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "\u8cc7\u6e90\u30bf\u30a4\u30d7", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Application of deep learning (3-dimensional convolutional neural network) for the prediction of pathological invasiveness in lung adenocarcinoma", "item_titles": {"attribute_name": "\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_title": "Application of deep learning (3-dimensional convolutional neural network) for the prediction of pathological invasiveness in lung adenocarcinoma"}]}, "item_type_id": "5", "owner": "1", "path": ["2780/2618", "3/62/5595/5172"], "permalink_uri": "http://hdl.handle.net/2241/00159155", "pubdate": {"attribute_name": "\u516c\u958b\u65e5", "attribute_name_i18n": "\u516c\u958b\u65e5", "attribute_value": "2019-12-12"}, "publish_date": "2019-12-12", "publish_status": "0", "recid": "53736", "relation": {}, "relation_version_is_last": true, "title": ["Application of deep learning (3-dimensional convolutional neural network) for the prediction of pathological invasiveness in lung adenocarcinoma"], "weko_shared_id": 5}
Application of deep learning (3-dimensional convolutional neural network) for the prediction of pathological invasiveness in lung adenocarcinoma
http://hdl.handle.net/2241/00159155
d611087f-7e0f-45b1-8aca-2777e6757fc8
名前 / ファイル | ライセンス | Actions | |
---|---|---|---|
![]() |
item type | Journal Article(1) | |||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
公開日 | 2019-12-12 | |||||||||||
タイトル | ||||||||||||
タイトル | Application of deep learning (3-dimensional convolutional neural network) for the prediction of pathological invasiveness in lung adenocarcinoma | |||||||||||
言語 | ||||||||||||
言語 | eng | |||||||||||
資源タイプ | ||||||||||||
タイプ | journal article | |||||||||||
著者 |
野口, 雅之
× 野口, 雅之
WEKO
124641
× Yanagawa, Masahiro× Niioka, Hirohiko× Hata, Akinori× Kikuchi, Noriko× Honda, Osamu× Kurakami, Hiroyuki× Morii, Eiichi× Watanabe, Yoshiyuki× Miyake, Jun× Tomiyama, Noriyuki |
|||||||||||
抄録 | ||||||||||||
内容記述 | To compare results for radiological prediction of pathological invasiveness in lung adenocarcinoma between radiologists and a deep learning (DL) system. Ninety patients (50 men, 40 women; mean age, 66 years; range, 40-88 years) who underwent pre-operative chest computed tomography (CT) with 0.625-mm slice thickness were included in this retrospective study. Twenty-four cases of adenocarcinoma in situ (AIS), 20 cases of minimally invasive adenocarcinoma (MIA), and 46 cases of invasive adenocarcinoma (IVA) were pathologically diagnosed. Three radiologists of different levels of experience diagnosed each nodule by using previously documented CT findings to predict pathological invasiveness. DL was structured using a 3-dimensional (3D) convolutional neural network (3D-CNN) constructed with 2 successive pairs of convolution and max-pooling layers, and 2 fully connected layers. The output layer comprises 3 nodes to recognize the 3 conditions of adenocarcinoma (AIS, MIA, and IVA) or 2 nodes for 2 conditions (AIS and MIA/IVA). Results from DL and the 3 radiologists were statistically compared. No significant differences in pathological diagnostic accuracy rates were seen between DL and the 3 radiologists (P>. 11). Receiver operating characteristic analysis demonstrated that area under the curve for DL (0.712) was almost the same as that for the radiologist with extensive experience (0.714; P=. 98). Compared with the consensus results from radiologists, DL offered significantly inferior sensitivity (P=. 0005), but significantly superior specificity (P=. 02). Despite the small training data set, diagnostic performance of DL was almost the same as the radiologist with extensive experience. In particular, DL provided higher specificity than radiologists. |
|||||||||||
書誌情報 |
Medicine 巻 98, 号 25, p. e16119, 発行日 2019-06 |
|||||||||||
ISSN | ||||||||||||
収録物識別子 | 0025-7974 | |||||||||||
PubMed番号 | ||||||||||||
DOI | ||||||||||||
権利 | ||||||||||||
権利情報 | © 2019 the Author(s). Published by Wolters Kluwer Health, Inc. This is an open access article distributed under the terms of the Creative Commons Attribution-Non Commercial-No Derivatives License 4.0 (CCBY-NCND), where it is permissible to download and share the work provided it is properly cited. The work cannot be changed in any way or used commercially without permission from the journal. | |||||||||||
著者版フラグ | ||||||||||||
値 | publisher | |||||||||||
出版者 | ||||||||||||
出版者 | Wolters Kluwer Health, Inc. |