WEKO3
アイテム
{"_buckets": {"deposit": "1bd313e7-7df1-4fc9-becd-7a24f47c5a79"}, "_deposit": {"created_by": 13, "id": "10069", "owners": [13], "pid": {"revision_id": 0, "type": "depid", "value": "10069"}, "status": "published"}, "_oai": {"id": "oai:uec.repo.nii.ac.jp:00010069", "sets": ["6"]}, "author_link": ["26893", "26894", "26895", "26896"], "control_number": "10069", "item_10001_biblio_info_7": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2021-06", "bibliographicIssueDateType": "Issued"}, "bibliographicPageStart": "101920", "bibliographicVolumeNumber": "90", "bibliographic_titles": [{"bibliographic_title": "Computerized Medical Imaging and Graphics", "bibliographic_titleLang": "en"}]}]}, "item_10001_description_5": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Since the development of deep learning methods, many researchers have focused on image quality improvement using convolutional neural networks. They proved its effectivity in noise reduction, single-image super-resolution, and segmentation. In this study, we apply stacked U-Net, a deep learning method, for X-ray computed tomography image reconstruction to generate high-quality images in a short time with a small number of projections. It is not easy to create highly accurate models because medical images have few training images due to patients’ privacy issues. Thus, we utilize various images from the ImageNet, a widely known visual database. Results show that a cross-sectional image with a peak signal-to-noise ratio of 27.93 db and a structural similarity of 0.886 is recovered for a 512*512 image using 360-degree rotation, 512 detectors, and 64 projections, with a processing time of 0.11 s on the GPU. Therefore, the proposed method has a shorter reconstruction time and better image quality than the existing methods.", "subitem_description_type": "Abstract"}]}, "item_10001_publisher_8": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "Elsevier"}]}, "item_10001_relation_14": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isVersionOf", "subitem_relation_type_id": {"subitem_relation_type_id_text": "10.1016/j.compmedimag.2021.101920", "subitem_relation_type_select": "DOI"}}]}, "item_10001_relation_17": {"attribute_name": "関連サイト", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "https://doi.org/10.1016/j.compmedimag.2021.101920", "subitem_relation_type_select": "DOI"}}]}, "item_10001_rights_15": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "(c) 2021 Elsevier"}]}, "item_10001_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "08956111", "subitem_source_identifier_type": "ISSN"}]}, "item_10001_version_type_20": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_ab4af688f83e57aa", "subitem_version_type": "AM"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Mizusawa, Satoru", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "26893", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Sei, Yuichi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "26894", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Orihara, Ryohei", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "26895", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Ohsuga, Akihiko", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "26896", "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": "2022-07-01"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "1.pdf", "filesize": [{"value": "487.5 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 487500.0, "url": {"label": "1.pdf", "url": "https://uec.repo.nii.ac.jp/record/10069/files/1.pdf"}, "version_id": "2d37026d-79df-43d7-95a7-6de173d2ecaa"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Deep learning", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Reconstruction", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Inverse problem", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Computed tomography", "subitem_subject_language": "en", "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": "Computed tomography image reconstruction using stacked U-Net", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Computed tomography image reconstruction using stacked U-Net", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "13", "path": ["6"], "permalink_uri": "https://uec.repo.nii.ac.jp/records/10069", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2022-07-01"}, "publish_date": "2022-07-01", "publish_status": "0", "recid": "10069", "relation": {}, "relation_version_is_last": true, "title": ["Computed tomography image reconstruction using stacked U-Net"], "weko_shared_id": -1}
Computed tomography image reconstruction using stacked U-Net
https://uec.repo.nii.ac.jp/records/10069
https://uec.repo.nii.ac.jp/records/10069bee039f3-ac8c-4e07-9cb3-8a2b2650fc4d
名前 / ファイル | ライセンス | アクション |
---|---|---|
1.pdf (487.5 kB)
|
|
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2022-07-01 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Computed tomography image reconstruction using stacked U-Net | |||||
言語 | ||||||
言語 | eng | |||||
キーワード | ||||||
言語 | en | |||||
主題 | Deep learning | |||||
キーワード | ||||||
言語 | en | |||||
主題 | Reconstruction | |||||
キーワード | ||||||
言語 | en | |||||
主題 | Inverse problem | |||||
キーワード | ||||||
言語 | en | |||||
主題 | Computed tomography | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
資源タイプ | journal article | |||||
著者 |
Mizusawa, Satoru
× Mizusawa, Satoru× Sei, Yuichi× Orihara, Ryohei× Ohsuga, Akihiko |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | Since the development of deep learning methods, many researchers have focused on image quality improvement using convolutional neural networks. They proved its effectivity in noise reduction, single-image super-resolution, and segmentation. In this study, we apply stacked U-Net, a deep learning method, for X-ray computed tomography image reconstruction to generate high-quality images in a short time with a small number of projections. It is not easy to create highly accurate models because medical images have few training images due to patients’ privacy issues. Thus, we utilize various images from the ImageNet, a widely known visual database. Results show that a cross-sectional image with a peak signal-to-noise ratio of 27.93 db and a structural similarity of 0.886 is recovered for a 512*512 image using 360-degree rotation, 512 detectors, and 64 projections, with a processing time of 0.11 s on the GPU. Therefore, the proposed method has a shorter reconstruction time and better image quality than the existing methods. | |||||
書誌情報 |
en : Computerized Medical Imaging and Graphics 巻 90, p. 101920, 発行日 2021-06 |
|||||
出版者 | ||||||
出版者 | Elsevier | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 08956111 | |||||
DOI | ||||||
関連タイプ | isVersionOf | |||||
識別子タイプ | DOI | |||||
関連識別子 | 10.1016/j.compmedimag.2021.101920 | |||||
権利 | ||||||
権利情報 | (c) 2021 Elsevier | |||||
関連サイト | ||||||
識別子タイプ | DOI | |||||
関連識別子 | https://doi.org/10.1016/j.compmedimag.2021.101920 | |||||
著者版フラグ | ||||||
出版タイプ | AM | |||||
出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa |