{"updated":"2025-01-21T20:01:36.307086+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00079981","sets":["581:6644:6645"]},"path":["6645"],"owner":"11","recid":"79981","title":["統計解剖学的モデルに基づく胸部X線CT画像からの肺病巣陰影の検出"],"pubdate":{"attribute_name":"公開日","attribute_value":"2012-01-15"},"_buckets":{"deposit":"d2a3064c-02b0-42c3-925a-27de234cbafa"},"_deposit":{"id":"79981","pid":{"type":"depid","value":"79981","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"統計解剖学的モデルに基づく胸部X線CT画像からの肺病巣陰影の検出","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"統計解剖学的モデルに基づく胸部X線CT画像からの肺病巣陰影の検出"},{"subitem_title":"Lung Lesion Detection from Chest X-ray CT Based on Statistical-anatomical Models","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"一般論文","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2012-01-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東芝メディカルシステムズ株式会社"},{"subitem_text_value":"筑波大学大学院システム情報工学研究科"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Toshiba Medical Systems Corporation","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Systems and Information Engineering, University of Tsukuba","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/79981/files/IPSJ-JNL5301044.pdf"},"date":[{"dateType":"Available","dateValue":"2014-01-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL5301044.pdf","filesize":[{"value":"1.9 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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"988b56ae-6a3d-4836-907c-864bf604770b","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2012 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"石井, 茂如"},{"creatorName":"滝沢, 穂高"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shigeyuki, Ishii","creatorNameLang":"en"},{"creatorName":"Hotaka, Takizawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","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_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究の目的は胸部X線CT画像から肺結節（肺がんの候補）を検出するための計算機診断支援（CAD）システムを開発することである．我々のCADシステムの最も重要な構成要素の1つとして，結節と血管の3次元物体モデルを用いた結節認識手法であるモデルマッチング法を提案している．この手法は高い精度で結節を認識可能だが，いまだ十分ではない．そこで，本論文ではモデルマッチング法に以下の3つの改良を加える．第1に，肺野内血管の位置とサイズとの関係を表す統計的な分布モデルを構築する．これを事前知識として利用することによって，より信頼性の高い血管モデルを生成し，認識率を向上させる．第2に，血管に隣接する結節を認識するために結節モデルと血管モデルを組み合わせた新たなモデルを導入する．第3に，単円筒モデルを用いた新たなアルゴリズムを用いることで最適モデルの探索を高速化する．これらの改良を8mmスライス間隔のCT画像98例に適用したところ，TP率90%でのFP数を従来法の15.5[個/症例]から9.2[個/症例]に削減することができ，本手法の有効性が確認された．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The purpose of this work is to build a computer-aided diagnosis (CAD) system for detection of pulmonary nodules on thoracic X-ray computed tomography (CT) scans. As a core component of our CAD system, nodule recognition method based on three-dimensional nodule and blood vessel models was proposed. The method achieved high accuracy in recognition, but is not sufficient yet. Therefore, in this paper, we improve the model-based method as follows. First, the distribution of blood vessel sizes in lungs is modeled to represent the relationship between their sizes and positions in lungs. The distribution model is used as a priori knowledge for generating more reliable blood vessel models. Second, the nodule models are combined with the blood vessel models for recognizing nodules adjacent to blood vessels. Third, the model optimization is made faster by use of the improved algorithm based on simplified blood vessel models. The improved model-based recognition method is applied to actual 98 CT scans that include total 98 nodules. The number of false positives is successfully reduced from 15.5 per case by our previous method to 9.2 per case by the improved method at the 90% sensitivity.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"420","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"412","bibliographicIssueDates":{"bibliographicIssueDate":"2012-01-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"53"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-18T23:34:33.742146+00:00","id":79981,"links":{}}