The potential of an artificial intelligence for diagnosing MRI images in rectal cancer: multicenter collaborative trial

Hamabe, Atsushi; Takemasa, Ichiro; Ishii, Masayuki; Okuya, Koichi; Hida, Koya; Nishizaki, Daisuke; Sumii, Atsuhiko; Arizono, Shigeki; Kohno, Shigeshi; Tokunaga, Koji; Nakai, Hirotsugu; Sakai, Yoshiharu; Watanabe, Masahiko

doi:https://doi.org/10.1007/s00535-024-02133-8

The potential of an artificial intelligence for diagnosing MRI images in rectal cancer: multicenter collaborative trial

Hamabe, Atsushi; Takemasa, Ichiro; Ishii, Masayuki et al.

Journal of Gastroenterology, 2024, 59(10), 896-904

アクセス数:927件（2025-07-17 06:21 集計）

固定URL: https://hdl.handle.net/11094/98107

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
Jgastroenterol_s00535-024-02133-8	pdf	なし	1.12 MB	231	2024.09.19

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	The potential of an artificial intelligence for diagnosing MRI images in rectal cancer: multicenter collaborative trial
著者	NRID 1000060621034 1000060621034 ORCID 0000-0001-5535-3514 0000-0001-5535-3514 researchmap permalink hamabe_atsushi hamabe_atsushi 著者名 Hamabe, Atsushi
	NRID 1000050379252 1000050379252 著者名 Takemasa, Ichiro
	NRID 1000050643201 1000050643201 著者名 Ishii, Masayuki
	NRID 1000070457703 1000070457703 著者名 Okuya, Koichi
	NRID 1000040447983 1000040447983 著者名 Hida, Koya
	著者名 Nishizaki, Daisuke
	著者名 Sumii, Atsuhiko
	著者名 Arizono, Shigeki
	著者名 Kohno, Shigeshi
	著者名 Tokunaga, Koji
	著者名 Nakai, Hirotsugu
	NRID 1000060273455 1000060273455 著者名 Sakai, Yoshiharu
	NRID 1000080146604 1000080146604 著者名 Watanabe, Masahiko
キーワード等	Artificial intelligence
	MRI
	Rectal cancer
内容	The version of record of this article, first published in Journal of Gastroenterology, is available online at Publisher’s website: https://doi.org/10.1007/s00535-024-02133-8.
抄録	Background: An artificial intelligence-based algorithm we developed, mrAI, satisfactorily segmented the rectal tumor, rectum, and mesorectum from MRI data of rectal cancer patients in an initial study. Herein, we aimed to validate mrAI using an independent dataset. Methods: We utilized MRI images collected in another nationwide research project, "Open versus Laparoscopic Surgery for Advanced Low Rectal Cancer Patients". MRIs from 467 cases with upfront surgery were utilized; six radiologists centralized the MRI evaluations. The diagnostic accuracies of mrAI and the radiologists for tumor depth were compared using pathologic diagnosis as a reference. Results: For all cases, centralized diagnosis demonstrated 84.2% sensitivity, 37.7% specificity, and 73.7% accuracy; mrAI exhibited 70.6% sensitivity, 61.3% specificity, and 68.5% accuracy. After limiting MRIs to those acquired by a Philips scanner, with an inter-slice spacing of ≤ 6 mm—both conditions similar to those used in the development of mrAI—the performance of mrAI improved to 76.8% sensitivity, 76.7% specificity, and 76.7% accuracy, while the centralized diagnosis showed 81.8% sensitivity, 36.7% specificity, and 71.3% accuracy. Regarding relapse-free survival, the prognosis for tumors staged ≥ T3 was significantly worse than for tumors staged ≤ T2 (P = 0.0484) in the pathologic diagnosis. While no significant difference was observed between ≥ T3 and ≤ T2 tumors in the centralized diagnosis (P = 0.1510), the prognosis for ≥ T3 was significantly worse in the mrAI diagnosis (P = 0.0318). Conclusion: Proper imaging conditions for MRI can enhance the accuracy of mrAI, which has the potential to provide feedback to radiologists without overestimating tumor stage.
出版者	Springer
収録物名	Journal of Gastroenterology
巻(号)	59(10)
ページ	896-904
刊行年月	2024-07-31
言語	英語
ハンドルURL	https://hdl.handle.net/11094/98107
PISSN	09441174
eISSN	14355922
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1007/s00535-024-02133-8
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
DCTERMS.bibliographicCitation	Journal of Gastroenterology. 2024, 59(10), p. 896-904
DC.title	The potential of an artificial intelligence for diagnosing MRI images in rectal cancer: multicenter collaborative trial
DC.creator	Hamabe, Atsushi
	Takemasa, Ichiro
	Ishii, Masayuki
	Okuya, Koichi
	Hida, Koya
	Nishizaki, Daisuke
	Sumii, Atsuhiko
	Arizono, Shigeki
	Kohno, Shigeshi
	Tokunaga, Koji
	Nakai, Hirotsugu
	Sakai, Yoshiharu
	Watanabe, Masahiko
DC.publisher	Springer
DC.language' scheme='DCTERMS.RFC1766	英語
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2024-07-31
DC.identifier	https://doi.org/10.1007/s00535-024-02133-8
DC.subject	Artificial intelligence
	MRI
	Rectal cancer
DC.description	The version of record of this article, first published in Journal of Gastroenterology, is available online at Publisher’s website: https://doi.org/10.1007/s00535-024-02133-8.
DCTERMS.abstract	Background: An artificial intelligence-based algorithm we developed, mrAI, satisfactorily segmented the rectal tumor, rectum, and mesorectum from MRI data of rectal cancer patients in an initial study. Herein, we aimed to validate mrAI using an independent dataset. Methods: We utilized MRI images collected in another nationwide research project, "Open versus Laparoscopic Surgery for Advanced Low Rectal Cancer Patients". MRIs from 467 cases with upfront surgery were utilized; six radiologists centralized the MRI evaluations. The diagnostic accuracies of mrAI and the radiologists for tumor depth were compared using pathologic diagnosis as a reference. Results: For all cases, centralized diagnosis demonstrated 84.2% sensitivity, 37.7% specificity, and 73.7% accuracy; mrAI exhibited 70.6% sensitivity, 61.3% specificity, and 68.5% accuracy. After limiting MRIs to those acquired by a Philips scanner, with an inter-slice spacing of ≤ 6 mm—both conditions similar to those used in the development of mrAI—the performance of mrAI improved to 76.8% sensitivity, 76.7% specificity, and 76.7% accuracy, while the centralized diagnosis showed 81.8% sensitivity, 36.7% specificity, and 71.3% accuracy. Regarding relapse-free survival, the prognosis for tumors staged ≥ T3 was significantly worse than for tumors staged ≤ T2 (P = 0.0484) in the pathologic diagnosis. While no significant difference was observed between ≥ T3 and ≤ T2 tumors in the centralized diagnosis (P = 0.1510), the prognosis for ≥ T3 was significantly worse in the mrAI diagnosis (P = 0.0318). Conclusion: Proper imaging conditions for MRI can enhance the accuracy of mrAI, which has the potential to provide feedback to radiologists without overestimating tumor stage.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	98107
citation_title	The potential of an artificial intelligence for diagnosing MRI images in rectal cancer: multicenter collaborative trial
citation_author	Hamabe, Atsushi
	Takemasa, Ichiro
	Ishii, Masayuki
	Okuya, Koichi
	Hida, Koya
	Nishizaki, Daisuke
	Sumii, Atsuhiko
	Arizono, Shigeki
	Kohno, Shigeshi
	Tokunaga, Koji
	Nakai, Hirotsugu
	Sakai, Yoshiharu
	Watanabe, Masahiko
citation_publisher	Springer
citation_language	英語
citation_date	2024-07-31
citation_journal_title	Journal of Gastroenterology
citation_volume	59
citation_issue	10
citation_firstpage	896
citation_lastpage	904
citation_doi	https://doi.org/10.1007/s00535-024-02133-8
citation_public_url	https://hdl.handle.net/11094/98107

The potential of an artificial intelligence for diagnosing MRI images in rectal cancer: multicenter collaborative trial

閲覧可能ファイル

論文情報

論文詳細を表示