Patient Re-Identification Based on Deep Metric Learning in Trunk Computed Tomography Images Acquired from Devices from Different Vendors

Ueda, Yasuyuki; Ogawa, Daiki; Ishida, Takayuki

doi:https://doi.org/10.1007/s10278-024-01017-w

Patient Re-Identification Based on Deep Metric Learning in Trunk Computed Tomography Images Acquired from Devices from Different Vendors

Ueda, Yasuyuki; Ogawa, Daiki; Ishida, Takayuki

Journal of Imaging Informatics in Medicine, 2024, 141, 931

アクセス数:537件（2025-08-29 23:56 集計）

固定URL: https://hdl.handle.net/11094/94700

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
JDigitImagingInformmed_141_931	pdf	なし	1.98 MB	108	2024.03.18

Creative Commons : 表示

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Patient Re-Identification Based on Deep Metric Learning in Trunk Computed Tomography Images Acquired from Devices from Different Vendors
著者	NRID 1000050780805 1000050780805 ORCID 0000-0003-0975-2164 0000-0003-0975-2164 researchmap permalink uedacci uedacci Scopus Author ID 37001274700 37001274700 著者名 Ueda, Yasuyuki
	著者名 Ogawa, Daiki
	NRID 1000060309656 1000060309656 researchmap permalink Taka_Ishida00 Taka_Ishida00 Scopus Author ID 35406489400 35406489400 ORCID 0000-0002-6851-0598 0000-0002-6851-0598 著者名 Ishida, Takayuki
キーワード等	Deep metric learning
	Medical imaging
	Patient re-identification
	Augmentation technique
	Convolutional neural network
内容	The version of record of this article, first published in Journal of Imaging Informatics in Medicine, is available online at Publisher’s website: https://doi.org/10.1007/s10278-024-01017-w.
抄録	During radiologic interpretation, radiologists read patient identifiers from the metadata of medical images to recognize the patient being examined. However, it is challenging for radiologists to identify “incorrect” metadata and patient identification errors. We propose a method that uses a patient re-identification technique to link correct metadata to an image set of computed tomography images of a trunk with lost or wrongly assigned metadata. This method is based on a feature vector matching technique that uses a deep feature extractor to adapt to the cross-vendor domain contained in the scout computed tomography image dataset. To identify “incorrect” metadata, we calculated the highest similarity score between a follow-up image and a stored baseline image linked to the correct metadata. The re-identification performance tests whether the image with the highest similarity score belongs to the same patient, i.e., whether the metadata attached to the image are correct. The similarity scores between the follow-up and baseline images for the same “correct” patients were generally greater than those for “incorrect” patients. The proposed feature extractor was sufficiently robust to extract individual distinguishable features without additional training, even for unknown scout computed tomography images. Furthermore, the proposed augmentation technique further improved the re-identification performance of the subset for different vendors by incorporating changes in width magnification due to changes in patient table height during each examination. We believe that metadata checking using the proposed method would help detect the metadata with an “incorrect” patient identifier assigned due to unavoidable errors such as human error.
出版者	Springer Science and Business Media LLC
収録物名	Journal of Imaging Informatics in Medicine
巻(号)	141
ページ	931
刊行年月	2024-02-16
言語	英語
ハンドルURL	https://hdl.handle.net/11094/94700
eISSN	29482933
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1007/s10278-024-01017-w
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution 4.0 International License.
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	Journal of Imaging Informatics in Medicine. 2024, 141, p. 931
DC.title	Patient Re-Identification Based on Deep Metric Learning in Trunk Computed Tomography Images Acquired from Devices from Different Vendors
DC.creator	Ueda, Yasuyuki
	Ogawa, Daiki
	Ishida, Takayuki
DC.publisher	Springer Science and Business Media LLC
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2024-02-16
DC.identifier	https://doi.org/10.1007/s10278-024-01017-w
DC.subject	Deep metric learning
	Medical imaging
	Patient re-identification
	Augmentation technique
	Convolutional neural network
DC.description	The version of record of this article, first published in Journal of Imaging Informatics in Medicine, is available online at Publisher’s website: https://doi.org/10.1007/s10278-024-01017-w.
DCTERMS.abstract	During radiologic interpretation, radiologists read patient identifiers from the metadata of medical images to recognize the patient being examined. However, it is challenging for radiologists to identify “incorrect” metadata and patient identification errors. We propose a method that uses a patient re-identification technique to link correct metadata to an image set of computed tomography images of a trunk with lost or wrongly assigned metadata. This method is based on a feature vector matching technique that uses a deep feature extractor to adapt to the cross-vendor domain contained in the scout computed tomography image dataset. To identify “incorrect” metadata, we calculated the highest similarity score between a follow-up image and a stored baseline image linked to the correct metadata. The re-identification performance tests whether the image with the highest similarity score belongs to the same patient, i.e., whether the metadata attached to the image are correct. The similarity scores between the follow-up and baseline images for the same “correct” patients were generally greater than those for “incorrect” patients. The proposed feature extractor was sufficiently robust to extract individual distinguishable features without additional training, even for unknown scout computed tomography images. Furthermore, the proposed augmentation technique further improved the re-identification performance of the subset for different vendors by incorporating changes in width magnification due to changes in patient table height during each examination. We believe that metadata checking using the proposed method would help detect the metadata with an “incorrect” patient identifier assigned due to unavoidable errors such as human error.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	94700
citation_title	Patient Re-Identification Based on Deep Metric Learning in Trunk Computed Tomography Images Acquired from Devices from Different Vendors
citation_author	Ueda, Yasuyuki
	Ogawa, Daiki
	Ishida, Takayuki
citation_publisher	Springer Science and Business Media LLC
citation_language	英語
citation_date	2024-02-16
citation_journal_title	Journal of Imaging Informatics in Medicine
citation_volume	141
citation_firstpage	931
citation_doi	https://doi.org/10.1007/s10278-024-01017-w
citation_public_url	https://hdl.handle.net/11094/94700

Patient Re-Identification Based on Deep Metric Learning in Trunk Computed Tomography Images Acquired from Devices from Different Vendors

閲覧可能ファイル

論文情報

論文詳細を表示