ログイン
言語:

WEKO3

  • トップ
  • ランキング
To
lat lon distance
To

Field does not validate



インデックスリンク

インデックスツリー

メールアドレスを入力してください。

WEKO

One fine body…

WEKO

One fine body…

アイテム

{"_buckets": {"deposit": "75494ba6-712f-4565-aafe-c2dc2261b8c3"}, "_deposit": {"created_by": 17, "id": "2004240", "owner": "17", "owners": [17], "owners_ext": {"displayname": "repository", "username": "repository"}, "pid": {"revision_id": 0, "type": "depid", "value": "2004240"}, "status": "published"}, "_oai": {"id": "oai:nagoya.repo.nii.ac.jp:02004240", "sets": ["314"]}, "author_link": [], "item_1615768549627": {"attribute_name": "出版タイプ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_ab4af688f83e57aa", "subitem_version_type": "AM"}]}, "item_1629683748249": {"attribute_name": "日付", "attribute_value_mlt": [{"subitem_date_issued_datetime": "2023-11-01", "subitem_date_issued_type": "Available"}]}, "item_9_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2022-11", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "11", "bibliographicPageEnd": "2063", "bibliographicPageStart": "2051", "bibliographicVolumeNumber": "17", "bibliographic_titles": [{"bibliographic_title": "International Journal of Computer Assisted Radiology and Surgery", "bibliographic_titleLang": "en"}]}]}, "item_9_description_4": {"attribute_name": "内容記述", "attribute_value_mlt": [{"subitem_description": "Purpose: Precise polyp detection and localisation are essential for colonoscopy diagnosis. Statistical machine learning with a large-scale data set can contribute to the construction of a computer-aided diagnosis system for the prevention of overlooking and miss-localisation of a polyp in colonoscopy. We propose new visual explaining methods for a well-trained object detector, which achieves fast and accurate polyp detection with a bounding box towards a precise automated polyp localisation. Method: We refine gradient-weighted class activation mapping for more accurate highlighting of important patterns in processing a convolutional neural network. Extending the refined mapping into multiscaled processing, we define object activation mapping that highlights important object patterns in an image for a detection task. Finally, we define polyp activation mapping to achieve precise polyp localisation by integrating adaptive local thresholding into object activation mapping. We experimentally evaluate the proposed visual explaining methods with four publicly available databases. Results: The refined mapping visualises important patterns in each convolutional layer more accurately than the original gradient-weighted class activation mapping. The object activation mapping clearly visualises important patterns in colonoscopic images for polyp detection. The polyp activation mapping localises the detected polyps in ETIS-Larib, CVC-Clinic and Kvasir-SEG database with mean Dice scores of 0.76, 0.72 and 0.72, respectively. Conclusions: We developed new visual explaining methods for a convolutional neural network by refining and extending gradient-weighted class activation mapping. Experimental results demonstrated the validity of the proposed methods by showing that accurate visualisation of important patterns and localisation of polyps in a colonoscopic image. The proposed visual explaining methods are useful for the interpreting and applying a trained polyp detector.", "subitem_description_language": "en", "subitem_description_type": "Abstract"}]}, "item_9_publisher_32": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "Springer", "subitem_publisher_language": "en"}]}, "item_9_relation_43": {"attribute_name": "関連情報", "attribute_value_mlt": [{"subitem_relation_type": "isVersionOf", "subitem_relation_type_id": {"subitem_relation_type_id_text": "https://doi.org/10.1007/s11548-022-02696-y", "subitem_relation_type_select": "DOI"}}]}, "item_9_rights_12": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/10.1007/s11548-022-02696-y", "subitem_rights_language": "en"}]}, "item_9_source_id_7": {"attribute_name": "収録物識別子", "attribute_value_mlt": [{"subitem_source_identifier": "1861-6429", "subitem_source_identifier_type": "EISSN"}]}, "item_access_right": {"attribute_name": "アクセス権", "attribute_value_mlt": [{"subitem_access_right": "embargoed access", "subitem_access_right_uri": "http://purl.org/coar/access_right/c_f1cf"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Itoh, Hayato", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Misawa, Masashi", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Mori, Yuichi", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Kudo, Shin-Ei", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Oda, Masahiro", "creatorNameLang": "en"}]}, {"creatorNames": [{"creatorName": "Mori, Kensaku", "creatorNameLang": "en"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2023-11-01"}], "displaytype": "detail", "download_preview_message": "Download / Preview is available from 2023/10/31.", "file_order": 0, "filename": "IJCARS2021_OAM_NR.pdf", "filesize": [{"value": "3.7 MB"}], "format": "application/pdf", "future_date_message": "Download is available from 2023/10/31.", "is_thumbnail": false, "mimetype": "application/pdf", "size": 3700000.0, "url": {"objectType": "fulltext", "url": "https://nagoya.repo.nii.ac.jp/record/2004240/files/IJCARS2021_OAM_NR.pdf"}, "version_id": "67054414-0da3-43d2-8537-d68ddff72dc3"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Colonoscopy", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Polyp detection", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Polyp localisation", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Model analysis", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Computer-aided diagnosis", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Deep learning", "subitem_subject_scheme": "Other"}]}, "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": "Positive-gradient-weighted object activation mapping: visual explanation of object detector towards precise colorectal-polyp localisation", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Positive-gradient-weighted object activation mapping: visual explanation of object detector towards precise colorectal-polyp localisation", "subitem_title_language": "en"}]}, "item_type_id": "40001", "owner": "17", "path": ["314"], "permalink_uri": "http://hdl.handle.net/2237/0002004240", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2022-11-30"}, "publish_date": "2022-11-30", "publish_status": "0", "recid": "2004240", "relation": {}, "relation_version_is_last": true, "title": ["Positive-gradient-weighted object activation mapping: visual explanation of object detector towards precise colorectal-polyp localisation"], "weko_shared_id": -1}
  1. A500 情報学部/情報学研究科・情報文化学部・情報科学研究科
  2. A500a 雑誌掲載論文
  3. 学術雑誌

Positive-gradient-weighted object activation mapping: visual explanation of object detector towards precise colorectal-polyp localisation

http://hdl.handle.net/2237/0002004240
http://hdl.handle.net/2237/0002004240
a4c04881-9322-4e34-8f99-76703fe449fd
名前 / ファイル ライセンス アクション
IJCARS2021_OAM_NR.pdf IJCARS2021_OAM_NR.pdf (3.7 MB)
 Download is available from 2023/10/31.
Item type itemtype_ver1(1)
公開日 2022-11-30
タイトル
タイトル Positive-gradient-weighted object activation mapping: visual explanation of object detector towards precise colorectal-polyp localisation
言語 en
著者 Itoh, Hayato

× Itoh, Hayato

en Itoh, Hayato

Search repository
Misawa, Masashi

× Misawa, Masashi

en Misawa, Masashi

Search repository
Mori, Yuichi

× Mori, Yuichi

en Mori, Yuichi

Search repository
Kudo, Shin-Ei

× Kudo, Shin-Ei

en Kudo, Shin-Ei

Search repository
Oda, Masahiro

× Oda, Masahiro

en Oda, Masahiro

Search repository
Mori, Kensaku

× Mori, Kensaku

en Mori, Kensaku

Search repository
アクセス権
アクセス権 embargoed access
アクセス権URI http://purl.org/coar/access_right/c_f1cf
権利
言語 en
権利情報 This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/10.1007/s11548-022-02696-y
キーワード
主題Scheme Other
主題 Colonoscopy
キーワード
主題Scheme Other
主題 Polyp detection
キーワード
主題Scheme Other
主題 Polyp localisation
キーワード
主題Scheme Other
主題 Model analysis
キーワード
主題Scheme Other
主題 Computer-aided diagnosis
キーワード
主題Scheme Other
主題 Deep learning
内容記述
内容記述 Purpose: Precise polyp detection and localisation are essential for colonoscopy diagnosis. Statistical machine learning with a large-scale data set can contribute to the construction of a computer-aided diagnosis system for the prevention of overlooking and miss-localisation of a polyp in colonoscopy. We propose new visual explaining methods for a well-trained object detector, which achieves fast and accurate polyp detection with a bounding box towards a precise automated polyp localisation. Method: We refine gradient-weighted class activation mapping for more accurate highlighting of important patterns in processing a convolutional neural network. Extending the refined mapping into multiscaled processing, we define object activation mapping that highlights important object patterns in an image for a detection task. Finally, we define polyp activation mapping to achieve precise polyp localisation by integrating adaptive local thresholding into object activation mapping. We experimentally evaluate the proposed visual explaining methods with four publicly available databases. Results: The refined mapping visualises important patterns in each convolutional layer more accurately than the original gradient-weighted class activation mapping. The object activation mapping clearly visualises important patterns in colonoscopic images for polyp detection. The polyp activation mapping localises the detected polyps in ETIS-Larib, CVC-Clinic and Kvasir-SEG database with mean Dice scores of 0.76, 0.72 and 0.72, respectively. Conclusions: We developed new visual explaining methods for a convolutional neural network by refining and extending gradient-weighted class activation mapping. Experimental results demonstrated the validity of the proposed methods by showing that accurate visualisation of important patterns and localisation of polyps in a colonoscopic image. The proposed visual explaining methods are useful for the interpreting and applying a trained polyp detector.
言語 en
内容記述タイプ Abstract
出版者
言語 en
出版者 Springer
言語
言語 eng
資源タイプ
資源タイプresource http://purl.org/coar/resource_type/c_6501
タイプ journal article
出版タイプ
出版タイプ AM
出版タイプResource http://purl.org/coar/version/c_ab4af688f83e57aa
関連情報
関連タイプ isVersionOf
識別子タイプ DOI
関連識別子 https://doi.org/10.1007/s11548-022-02696-y
収録物識別子
収録物識別子タイプ EISSN
収録物識別子 1861-6429
書誌情報 en : International Journal of Computer Assisted Radiology and Surgery

巻 17, 号 11, p. 2051-2063, 発行日 2022-11
ファイル公開日
日付 2023-11-01
日付タイプ Available
戻る
0
views
See details
Views

Versions

Ver.1 2022-11-30 06:55:01.635550
Show All versions

Share

Mendeley Twitter Facebook Print Addthis

Cite as

エクスポート

OAI-PMH
  • OAI-PMH JPCOAR
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX

Confirm


Powered by WEKO3


Powered by WEKO3