WEKO3
アイテム
{"_buckets": {"deposit": "54bf88eb-e152-4550-b553-cfd60491f292"}, "_deposit": {"created_by": 1, "id": "48828", "owners": [1], "pid": {"revision_id": 0, "type": "depid", "value": "48828"}, "status": "published"}, "_oai": {"id": "oai:repo.qst.go.jp:00048828", "sets": ["1"]}, "author_link": ["491779", "491778"], "item_8_biblio_info_7": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2017-07", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "87", "bibliographicPageStart": "79", "bibliographicVolumeNumber": "40", "bibliographic_titles": [{"bibliographic_title": "Physica medica"}]}]}, "item_8_description_5": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Introduction: To develop real-time image processing for image-guided radiotherapy, we evaluated several neural network models for use with different imaging modalities, including X-ray fluoroscopic image denoising.\n\\nMethods \u0026 Materials: Setup images of prostate cancer patients were acquired with two oblique X-ray fluoroscopic units. Two types of residual network were designed: a convolutional autoencoder (rCAE) and a convolutional neural network (rCNN). We changed the convolutional kernel size and number of convolutional layers for both networks, and the number of pooling and upsampling layers for rCAE. The ground-truth image was applied to the contrast-limited adaptive histogram equalization (CLAHE) method of image processing. Network models were trained to keep the quality of the output image close to that of the ground-truth image from the input image without image processing. For image denoising evaluation, noisy input images were used for the training.\n\\nResults: More than 6 convolutional layers with convolutional kernels \u003e 5×5 improved image quality. However, this did not allow real-time imaging. After applying a pair of pooling and upsampling layers to both networks, rCAEs with \u003e 3 convolutions each and rCNNs with \u003e 12 convolutions with a pair of pooling and upsampling layers achieved real-time processing at 30 frames per second (fps) with acceptable image quality.\n\\nConclusions: Use of our suggested network achieved real-time image processing for contrast enhancement and image denoising by the use of a conventional modern personal computer.", "subitem_description_type": "Abstract"}]}, "item_8_publisher_8": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "Istituti Editoriali e Poligrafici Internazionali"}]}, "item_8_relation_14": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "10.1016/j.ejmp.2017.07.013", "subitem_relation_type_select": "DOI"}}]}, "item_8_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "1120-1797", "subitem_source_identifier_type": "ISSN"}]}, "item_access_right": {"attribute_name": "アクセス権", "attribute_value_mlt": [{"subitem_access_right": "metadata only access", "subitem_access_right_uri": "http://purl.org/coar/access_right/c_14cb"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "森, 慎一郎"}], "nameIdentifiers": [{"nameIdentifier": "491778", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "森 慎一郎", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "491779", "nameIdentifierScheme": "WEKO"}]}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "jpn"}]}, "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": "Deep architecture neural network-based real-time image processing for image-guided radiotherapy", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Deep architecture neural network-based real-time image processing for image-guided radiotherapy"}]}, "item_type_id": "8", "owner": "1", "path": ["1"], "permalink_uri": "https://repo.qst.go.jp/records/48828", "pubdate": {"attribute_name": "公開日", "attribute_value": "2018-04-27"}, "publish_date": "2018-04-27", "publish_status": "0", "recid": "48828", "relation": {}, "relation_version_is_last": true, "title": ["Deep architecture neural network-based real-time image processing for image-guided radiotherapy"], "weko_shared_id": -1}
Deep architecture neural network-based real-time image processing for image-guided radiotherapy
https://repo.qst.go.jp/records/48828
https://repo.qst.go.jp/records/488284398d800-0919-484a-be82-cf373cfc9331
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2018-04-27 | |||||
タイトル | ||||||
タイトル | Deep architecture neural network-based real-time image processing for image-guided radiotherapy | |||||
言語 | ||||||
言語 | jpn | |||||
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 | |||||
アクセス権 | ||||||
アクセス権 | metadata only access | |||||
アクセス権URI | http://purl.org/coar/access_right/c_14cb | |||||
著者 |
森, 慎一郎
× 森, 慎一郎× 森 慎一郎 |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | Introduction: To develop real-time image processing for image-guided radiotherapy, we evaluated several neural network models for use with different imaging modalities, including X-ray fluoroscopic image denoising. \nMethods & Materials: Setup images of prostate cancer patients were acquired with two oblique X-ray fluoroscopic units. Two types of residual network were designed: a convolutional autoencoder (rCAE) and a convolutional neural network (rCNN). We changed the convolutional kernel size and number of convolutional layers for both networks, and the number of pooling and upsampling layers for rCAE. The ground-truth image was applied to the contrast-limited adaptive histogram equalization (CLAHE) method of image processing. Network models were trained to keep the quality of the output image close to that of the ground-truth image from the input image without image processing. For image denoising evaluation, noisy input images were used for the training. \nResults: More than 6 convolutional layers with convolutional kernels > 5×5 improved image quality. However, this did not allow real-time imaging. After applying a pair of pooling and upsampling layers to both networks, rCAEs with > 3 convolutions each and rCNNs with > 12 convolutions with a pair of pooling and upsampling layers achieved real-time processing at 30 frames per second (fps) with acceptable image quality. \nConclusions: Use of our suggested network achieved real-time image processing for contrast enhancement and image denoising by the use of a conventional modern personal computer. |
|||||
書誌情報 |
Physica medica 巻 40, p. 79-87, 発行日 2017-07 |
|||||
出版者 | ||||||
出版者 | Istituti Editoriali e Poligrafici Internazionali | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 1120-1797 | |||||
DOI | ||||||
識別子タイプ | DOI | |||||
関連識別子 | 10.1016/j.ejmp.2017.07.013 |