WEKO3
アイテム
{"_buckets": {"deposit": "b2c3dc39-58ec-4d6c-bd64-f7f0a04df15c"}, "_deposit": {"created_by": 3, "id": "7863", "owners": [3], "pid": {"revision_id": 0, "type": "depid", "value": "7863"}, "status": "published"}, "_oai": {"id": "oai:kyutech.repo.nii.ac.jp:00007863", "sets": ["9"]}, "author_link": ["402", "34552", "34557", "34555", "34561", "34560", "15968", "34556"], "item_21_alternative_title_18": {"attribute_name": "その他のタイトル", "attribute_value_mlt": [{"subitem_alternative_title": "Classification of Respiratory Sounds by scSE-CRNN from Triple Types of Respiratory Sound Images"}]}, "item_21_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2021-12-27", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "4", "bibliographicPageEnd": "159", "bibliographicPageStart": "152", "bibliographicVolumeNumber": "38", "bibliographic_titles": [{"bibliographic_title": "医用画像情報学会雑誌"}]}]}, "item_21_description_4": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "Due to the respiratory diseases such as chronic obstructive pulmonary disease and lower respiratory tract infections nearly 8 million people were died worldwide each year. Reducing the number of deaths from respiratory diseases is a challenge to be solved worldwide. Early detection is the most efficient way to reduce the number of deaths in respiratory illness. As a result, the spread of infection can be suppressed, and the therapeutic effect can be enhanced. Currently, auscultation is performed as a promising method for early detection of respiratory diseases. Auscultation can estimate respiratory diseases by distinguishing abnormal sounds contained in respiratory sounds. However, medical staff need to be trained to perform auscultation with high accuracy. Also, the diagnostic results depend on each staff subjectively, which can lead to inconsistent results. Therefore, in some environments, a shortage of specialized health care workers can lead to the spread of respiratory illness. To solve this problem, an application that analyzes respiratory sounds and outputs diagnostic results is needed. In this paper, we use a newly proposed deep learning model to automatically classify the respiratory sound data from the ICBHI 2017 Challenge Dataset. Short-Time Fourier Transform, Constant-Q Transform, and Continuous Wavelet Transform are applied to the respiratory sound data to convert it into the time-frequency region. Then, the obtained three types of breath sound images are input to CRNN (Convolutional Recurrent Neural Network) having scSE (Spatial and Channel Squeeze \u0026 Excitation) Block. The accuracy is improved by weighting the features of each image. As a result, AUC (Area Under the Curve): (Normal:0.87, Crackle:0.88, Wheeze:0.92, Both:0.89), Sensitivity: 0.67, Specificity: 0.82, Average Score: 0.75, Harmonic Score: 0.74, Accuracy: 0.75 were obtained.", "subitem_description_type": "Abstract"}]}, "item_21_description_60": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"subitem_description": "Journal Article", "subitem_description_type": "Other"}]}, "item_21_full_name_3": {"attribute_name": "著者別名", "attribute_value_mlt": [{"nameIdentifiers": [{"nameIdentifier": "34557", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "Asatani, Naoki"}]}, {"nameIdentifiers": [{"nameIdentifier": "15968", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "40742466", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000040742466/"}, {"nameIdentifier": "57209823396", "nameIdentifierScheme": "Scopus著者ID", "nameIdentifierURI": "https://www.scopus.com/authid/detail.uri?authorId=57209823396"}, {"nameIdentifier": "0000-0001-9794-3221", "nameIdentifierScheme": "ORCiD", "nameIdentifierURI": "https://orcid.org/0000-0001-9794-3221"}, {"nameIdentifier": "100000960", "nameIdentifierScheme": "九工大研究者情報", "nameIdentifierURI": "https://hyokadb02.jimu.kyutech.ac.jp/html/100000960_ja.html"}], "names": [{"name": "Lu, Huimin"}]}, {"nameIdentifiers": [{"nameIdentifier": "402", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "80295005", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000080295005/"}, {"nameIdentifier": "55739611300", "nameIdentifierScheme": "Scopus著者ID", "nameIdentifierURI": "https://www.scopus.com/authid/detail.uri?authorId=55739611300"}, {"nameIdentifier": "25", "nameIdentifierScheme": "九工大研究者情報", "nameIdentifierURI": "https://hyokadb02.jimu.kyutech.ac.jp/html/25_ja.html"}], "names": [{"name": "Kamiya, Tohru"}]}, {"nameIdentifiers": [{"nameIdentifier": "34560", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "Mabu, Shingo"}]}, {"nameIdentifiers": [{"nameIdentifier": "34561", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "Kido, Shoji"}]}]}, "item_21_publisher_7": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "医用画像情報学会"}]}, "item_21_relation_12": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "https://doi.org/10.11318/mii.38.152", "subitem_relation_type_select": "DOI"}}]}, "item_21_relation_66": {"attribute_name": "論文ID(NAID)", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "http://ci.nii.ac.jp/naid/130008136055", "subitem_relation_type_select": "NAID"}}]}, "item_21_rights_13": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "Copyright (c) 2021 医用画像情報学会"}]}, "item_21_select_59": {"attribute_name": "査読の有無", "attribute_value_mlt": [{"subitem_select_item": "yes"}]}, "item_21_source_id_10": {"attribute_name": "書誌レコードID", "attribute_value_mlt": [{"subitem_source_identifier": "AN10156808", "subitem_source_identifier_type": "NCID"}]}, "item_21_source_id_8": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "1880-4977", "subitem_source_identifier_type": "ISSN"}, {"subitem_source_identifier": "0910-1543", "subitem_source_identifier_type": "ISSN"}]}, "item_21_subject_16": {"attribute_name": "日本十進分類法", "attribute_value_mlt": [{"subitem_subject": "492", "subitem_subject_scheme": "NDC"}]}, "item_21_text_36": {"attribute_name": "著者所属", "attribute_value_mlt": [{"subitem_text_value": "九州工業大学"}, {"subitem_text_value": "九州工業大学"}, {"subitem_text_value": "九州工業大学"}, {"subitem_text_value": "山口大学"}, {"subitem_text_value": "大阪大学"}]}, "item_21_text_63": {"attribute_name": "連携ID", "attribute_value_mlt": [{"subitem_text_value": "10861"}]}, "item_21_version_type_58": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "浅谷, 尚希"}], "nameIdentifiers": [{"nameIdentifier": "34552", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "陸, 慧敏"}], "nameIdentifiers": [{"nameIdentifier": "15968", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "40742466", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000040742466/"}, {"nameIdentifier": "57209823396", "nameIdentifierScheme": "Scopus著者ID", "nameIdentifierURI": "https://www.scopus.com/authid/detail.uri?authorId=57209823396"}, {"nameIdentifier": "0000-0001-9794-3221", "nameIdentifierScheme": "ORCiD", "nameIdentifierURI": "https://orcid.org/0000-0001-9794-3221"}, {"nameIdentifier": "100000960", "nameIdentifierScheme": "九工大研究者情報", "nameIdentifierURI": "https://hyokadb02.jimu.kyutech.ac.jp/html/100000960_ja.html"}]}, {"creatorNames": [{"creatorName": "神谷, 亨"}], "nameIdentifiers": [{"nameIdentifier": "402", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "80295005", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000080295005/"}, {"nameIdentifier": "55739611300", "nameIdentifierScheme": "Scopus著者ID", "nameIdentifierURI": "https://www.scopus.com/authid/detail.uri?authorId=55739611300"}, {"nameIdentifier": "25", "nameIdentifierScheme": "九工大研究者情報", "nameIdentifierURI": "https://hyokadb02.jimu.kyutech.ac.jp/html/25_ja.html"}]}, {"creatorNames": [{"creatorName": "間普, 真吾"}], "nameIdentifiers": [{"nameIdentifier": "34555", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "木戸, 尚治"}], "nameIdentifiers": [{"nameIdentifier": "34556", "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": "2023-02-02"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "LaSEINE-2021_032.pdf", "filesize": [{"value": "2.3 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 2300000.0, "url": {"label": "LaSEINE-2021_032.pdf", "url": "https://kyutech.repo.nii.ac.jp/record/7863/files/LaSEINE-2021_032.pdf"}, "version_id": "25a77e86-fede-4413-a224-81848ae8d2a6"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "Respiratory Sounds Classification", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Computer Aided Diagnosis", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Time-Frequency Analysis", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Deep Learning", "subitem_subject_scheme": "Other"}]}, "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": "scSE-CRNNと3種類の呼吸音変換画像による呼吸音の分類", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "scSE-CRNNと3種類の呼吸音変換画像による呼吸音の分類"}]}, "item_type_id": "21", "owner": "3", "path": ["9"], "permalink_uri": "http://hdl.handle.net/10228/00009066", "pubdate": {"attribute_name": "公開日", "attribute_value": "2023-02-02"}, "publish_date": "2023-02-02", "publish_status": "0", "recid": "7863", "relation": {}, "relation_version_is_last": true, "title": ["scSE-CRNNと3種類の呼吸音変換画像による呼吸音の分類"], "weko_shared_id": 3}
scSE-CRNNと3種類の呼吸音変換画像による呼吸音の分類
http://hdl.handle.net/10228/00009066
http://hdl.handle.net/10228/000090661310a348-9e59-43dd-a5c9-d139082cf400
名前 / ファイル | ライセンス | アクション |
---|---|---|
![]() |
|
Item type | 学術雑誌論文 = Journal Article(1) | |||||||
---|---|---|---|---|---|---|---|---|
公開日 | 2023-02-02 | |||||||
タイトル | ||||||||
タイトル | scSE-CRNNと3種類の呼吸音変換画像による呼吸音の分類 | |||||||
その他のタイトル | ||||||||
その他のタイトル | Classification of Respiratory Sounds by scSE-CRNN from Triple Types of Respiratory Sound Images | |||||||
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 | |||||||
著者 |
浅谷, 尚希
× 浅谷, 尚希× 陸, 慧敏
WEKO
15968
× 神谷, 亨× 間普, 真吾× 木戸, 尚治 |
|||||||
抄録 | ||||||||
内容記述タイプ | Abstract | |||||||
内容記述 | Due to the respiratory diseases such as chronic obstructive pulmonary disease and lower respiratory tract infections nearly 8 million people were died worldwide each year. Reducing the number of deaths from respiratory diseases is a challenge to be solved worldwide. Early detection is the most efficient way to reduce the number of deaths in respiratory illness. As a result, the spread of infection can be suppressed, and the therapeutic effect can be enhanced. Currently, auscultation is performed as a promising method for early detection of respiratory diseases. Auscultation can estimate respiratory diseases by distinguishing abnormal sounds contained in respiratory sounds. However, medical staff need to be trained to perform auscultation with high accuracy. Also, the diagnostic results depend on each staff subjectively, which can lead to inconsistent results. Therefore, in some environments, a shortage of specialized health care workers can lead to the spread of respiratory illness. To solve this problem, an application that analyzes respiratory sounds and outputs diagnostic results is needed. In this paper, we use a newly proposed deep learning model to automatically classify the respiratory sound data from the ICBHI 2017 Challenge Dataset. Short-Time Fourier Transform, Constant-Q Transform, and Continuous Wavelet Transform are applied to the respiratory sound data to convert it into the time-frequency region. Then, the obtained three types of breath sound images are input to CRNN (Convolutional Recurrent Neural Network) having scSE (Spatial and Channel Squeeze & Excitation) Block. The accuracy is improved by weighting the features of each image. As a result, AUC (Area Under the Curve): (Normal:0.87, Crackle:0.88, Wheeze:0.92, Both:0.89), Sensitivity: 0.67, Specificity: 0.82, Average Score: 0.75, Harmonic Score: 0.74, Accuracy: 0.75 were obtained. | |||||||
書誌情報 |
医用画像情報学会雑誌 巻 38, 号 4, p. 152-159, 発行日 2021-12-27 |
|||||||
出版者 | ||||||||
出版者 | 医用画像情報学会 | |||||||
ISSN | ||||||||
収録物識別子タイプ | ISSN | |||||||
収録物識別子 | 1880-4977 | |||||||
ISSN | ||||||||
収録物識別子タイプ | ISSN | |||||||
収録物識別子 | 0910-1543 | |||||||
NCID | ||||||||
収録物識別子タイプ | NCID | |||||||
収録物識別子 | AN10156808 | |||||||
DOI | ||||||||
関連タイプ | isIdenticalTo | |||||||
識別子タイプ | DOI | |||||||
関連識別子 | https://doi.org/10.11318/mii.38.152 | |||||||
論文ID(NAID) | ||||||||
関連タイプ | isIdenticalTo | |||||||
識別子タイプ | NAID | |||||||
関連識別子 | http://ci.nii.ac.jp/naid/130008136055 | |||||||
キーワード | ||||||||
主題Scheme | Other | |||||||
主題 | Respiratory Sounds Classification | |||||||
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 | Time-Frequency Analysis | |||||||
キーワード | ||||||||
主題Scheme | Other | |||||||
主題 | Deep Learning | |||||||
日本十進分類法 | ||||||||
主題Scheme | NDC | |||||||
主題 | 492 | |||||||
著作権関連情報 | ||||||||
権利情報 | Copyright (c) 2021 医用画像情報学会 | |||||||
出版タイプ | ||||||||
出版タイプ | VoR | |||||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||
査読の有無 | ||||||||
値 | yes | |||||||
連携ID | ||||||||
10861 |