WEKO3
アイテム
{"_buckets": {"deposit": "22427d24-d842-4826-bfa9-ca64507db7b4"}, "_deposit": {"id": "44749", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "44749"}, "status": "published"}, "_oai": {"id": "oai:tsukuba.repo.nii.ac.jp:00044749", "sets": ["352", "7235"]}, "item_5_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2018-03", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "1", "bibliographicPageEnd": "53", "bibliographicPageStart": "43", "bibliographicVolumeNumber": "11", "bibliographic_titles": [{"bibliographic_title": "Radiological physics and technology"}]}]}, "item_5_creator_3": {"attribute_name": "著者別名", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "照沼, 利之"}], "nameIdentifiers": [{"nameIdentifier": "58", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "40361349", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000040361349"}, {"nameIdentifier": "0000002334", "nameIdentifierScheme": "筑波大学研究者総覧", "nameIdentifierURI": "http://trios.tsukuba.ac.jp/researcher/0000002334"}]}]}, "item_5_description_4": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Robustness to obstacles is the most important factor necessary to achieve accurate tumor tracking without fiducial markers. Some high-density structures, such as bone, are enhanced on X-ray fluoroscopic images, which cause tumor mistracking. Tumor tracking should be performed by controlling “importance recognition”: the understanding that soft-tissue is an important tracking feature and bone structure is unimportant. We propose a new real-time tumor-contouring method that uses deep learning with importance recognition control. The novelty of the proposed method is the combination of the devised random overlay method and supervised deep learning to induce the recognition of structures in tumor contouring as important or unimportant. This method can be used for tumor contouring because it uses deep learning to perform image segmentation. Our results from a simulated fluoroscopy model showed accurate tracking of a low-visibility tumor with an error of approximately 1 mm, even if enhanced bone structure acted as an obstacle. A high similarity of approximately 0.95 on the Jaccard index was observed between the segmented and ground truth tumor regions. A short processing time of 25 ms was achieved. The results of this simulated fluoroscopy model support the feasibility of robust real-time tumor contouring with fluoroscopy. Further studies using clinical fluoroscopy are highly anticipated.", "subitem_description_type": "Abstract"}]}, "item_5_publisher_27": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "Springer"}]}, "item_5_relation_10": {"attribute_name": "PubMed番号", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "29285686 ", "subitem_relation_type_select": "PMID"}}]}, "item_5_relation_11": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "10.1007/s12194-017-0435-0", "subitem_relation_type_select": "DOI"}}]}, "item_5_rights_12": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": " ©The Author(s) 2017. "}, {"subitem_rights": " This article is an open access publication"}, {"subitem_rights": "This article is distributed under the terms of the Creative Commons Attribution 4.0 International License ( http://creative commons.org/licenses/by/4.0/ ), which permits unrestricted use, dis- tribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made."}]}, "item_5_select_15": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_select_item": "publisher"}]}, "item_5_source_id_7": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "1865-0333", "subitem_source_identifier_type": "ISSN"}]}, "item_5_source_id_9": {"attribute_name": "書誌レコードID", "attribute_value_mlt": [{"subitem_source_identifier": "AA12236881", "subitem_source_identifier_type": "NCID"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Terunuma, Toshiyuki"}], "nameIdentifiers": [{"nameIdentifier": "180024", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Tokui, Aoi"}], "nameIdentifiers": [{"nameIdentifier": "180025", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Sakae, Takeji"}], "nameIdentifiers": [{"nameIdentifier": "180026", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2018-01-11"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "RPT_11-1.pdf", "filesize": [{"value": "2.3 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_6", "mimetype": "application/pdf", "size": 2300000.0, "url": {"label": "RPT", "url": "https://tsukuba.repo.nii.ac.jp/record/44749/files/RPT_11-1.pdf"}, "version_id": "85495d13-e98b-47ce-833f-0fb58209ce08"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopy", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopy"}]}, "item_type_id": "5", "owner": "1", "path": ["352", "7235"], "permalink_uri": "http://hdl.handle.net/2241/00150023", "pubdate": {"attribute_name": "公開日", "attribute_value": "2018-01-11"}, "publish_date": "2018-01-11", "publish_status": "0", "recid": "44749", "relation": {}, "relation_version_is_last": true, "title": ["Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopy"], "weko_shared_id": 5}
Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopy
http://hdl.handle.net/2241/00150023
http://hdl.handle.net/2241/00150023d2fb6df8-5b3e-450f-a092-d32318b6ab5c
名前 / ファイル | ライセンス | アクション |
---|---|---|
RPT (2.3 MB)
|
Item type | Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2018-01-11 | |||||
タイトル | ||||||
タイトル | Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopy | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源 | http://purl.org/coar/resource_type/c_6501 | |||||
タイプ | journal article | |||||
著者 |
Terunuma, Toshiyuki
× Terunuma, Toshiyuki× Tokui, Aoi× Sakae, Takeji |
|||||
著者別名 |
照沼, 利之
× 照沼, 利之 |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | Robustness to obstacles is the most important factor necessary to achieve accurate tumor tracking without fiducial markers. Some high-density structures, such as bone, are enhanced on X-ray fluoroscopic images, which cause tumor mistracking. Tumor tracking should be performed by controlling “importance recognition”: the understanding that soft-tissue is an important tracking feature and bone structure is unimportant. We propose a new real-time tumor-contouring method that uses deep learning with importance recognition control. The novelty of the proposed method is the combination of the devised random overlay method and supervised deep learning to induce the recognition of structures in tumor contouring as important or unimportant. This method can be used for tumor contouring because it uses deep learning to perform image segmentation. Our results from a simulated fluoroscopy model showed accurate tracking of a low-visibility tumor with an error of approximately 1 mm, even if enhanced bone structure acted as an obstacle. A high similarity of approximately 0.95 on the Jaccard index was observed between the segmented and ground truth tumor regions. A short processing time of 25 ms was achieved. The results of this simulated fluoroscopy model support the feasibility of robust real-time tumor contouring with fluoroscopy. Further studies using clinical fluoroscopy are highly anticipated. | |||||
書誌情報 |
Radiological physics and technology 巻 11, 号 1, p. 43-53, 発行日 2018-03 |
|||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 1865-0333 | |||||
書誌レコードID | ||||||
収録物識別子タイプ | NCID | |||||
収録物識別子 | AA12236881 | |||||
PubMed番号 | ||||||
識別子タイプ | PMID | |||||
関連識別子 | 29285686 | |||||
DOI | ||||||
識別子タイプ | DOI | |||||
関連識別子 | 10.1007/s12194-017-0435-0 | |||||
権利 | ||||||
権利情報 | ©The Author(s) 2017. | |||||
権利 | ||||||
権利情報 | This article is an open access publication | |||||
権利 | ||||||
権利情報 | This article is distributed under the terms of the Creative Commons Attribution 4.0 International License ( http://creative commons.org/licenses/by/4.0/ ), which permits unrestricted use, dis- tribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. | |||||
著者版フラグ | ||||||
値 | publisher | |||||
出版者 | ||||||
出版者 | Springer |