A novel artificial intelligence-based endoscopic ultrasonography diagnostic system for diagnosing the invasion depth of early gastric cancer

Uema, Ryotaro; Hayashi, Yoshito; Kizu, Takashi; Igura, Takumi; Ogiyama, Hideharu; Yamada, Takuya; Takeda, Risato; Nagai, Kengo; Inoue, Takuya; Yamamoto, Masashi; Yamaguchi, Shinjiro; Kanesaka, Takashi; Yoshihara, Takeo; Kato, Minoru; Yoshii, Shunsuke; Tsujii, Yoshiki; Shinzaki, Shinichiro; Takehara, Tetsuo

doi:https://doi.org/10.1007/s00535-024-02102-1

A novel artificial intelligence-based endoscopic ultrasonography diagnostic system for diagnosing the invasion depth of early gastric cancer

Uema, Ryotaro; Hayashi, Yoshito; Kizu, Takashi et al.

Journal of Gastroenterology, 2024, 59, 543-555

Number of Access:2,432（2025-09-06 08:20 Counts）

Identifier to cite or link to this item: https://hdl.handle.net/11094/97114

Link to primary information

File	Format	Terms of use	Size	Views	Date.Available	Description	information
Jgastroenterol_59_543	pdf	None	7.99 MB	151	2024.07.05

Creative Commons : Attribution

Item Information

Output File Export EndNote Basic Export Mendeley

Title	A novel artificial intelligence-based endoscopic ultrasonography diagnostic system for diagnosing the invasion depth of early gastric cancer
Creator	NRID 1000030939161 1000030939161 researchmap permalink ryotarouema ryotarouema CreatorName Uema, Ryotaro
	NRID 1000080647123 1000080647123 researchmap permalink y-h y-h Scopus Author ID 35219993200 35219993200 CreatorName Hayashi, Yoshito
	NRID 1000030748299 1000030748299 CreatorName Kizu, Takashi
	CreatorName Igura, Takumi
	CreatorName Ogiyama, Hideharu
	CreatorName Yamada, Takuya
	CreatorName Takeda, Risato
	CreatorName Nagai, Kengo
	CreatorName Inoue, Takuya
	CreatorName Yamamoto, Masashi
	CreatorName Yamaguchi, Shinjiro
	CreatorName Kanesaka, Takashi
	NRID 1000020814601 1000020814601 researchmap permalink ty_gh ty_gh CreatorName Yoshihara, Takeo
	NRID 1000080939249 1000080939249 CreatorName Kato, Minoru
	NRID 1000090771882 1000090771882 CreatorName Yoshii, Shunsuke
	NRID 1000080795170 1000080795170 researchmap permalink yhcks yhcks Scopus Author ID 57192176408 57192176408 CreatorName Tsujii, Yoshiki
	NRID 1000060546860 1000060546860 CreatorName Shinzaki, Shinichiro
	NRID 1000070335355 1000070335355 researchmap permalink takeharatetsuo takeharatetsuo Scopus Author ID 7103332258 7103332258 CreatorName Takehara, Tetsuo
Subject	Artificial intelligence
	Deep learning
	Early gastric cancer
	Endoscopic ultrasonography
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/s00535-024-02102-1.
Abstract	Background: We developed an artificial intelligence (AI)-based endoscopic ultrasonography (EUS) system for diagnosing the invasion depth of early gastric cancer (EGC), and we evaluated the performance of this system. Methods: A total of 8280 EUS images from 559 EGC cases were collected from 11 institutions. Within this dataset, 3451 images (285 cases) from one institution were used as a development dataset. The AI model consisted of segmentation and classification steps, followed by the CycleGAN method to bridge differences in EUS images captured by different equipment. AI model performance was evaluated using an internal validation dataset collected from the same institution as the development dataset (1726 images, 135 cases). External validation was conducted using images collected from the other 10 institutions (3103 images, 139 cases). Results: The area under the curve (AUC) of the AI model in the internal validation dataset was 0.870 (95% CI: 0.796–0.944). Regarding diagnostic performance, the accuracy/sensitivity/specificity values of the AI model, experts (n = 6), and nonexperts (n = 8) were 82.2/63.4/90.4%, 81.9/66.3/88.7%, and 68.3/60.9/71.5%, respectively. The AUC of the AI model in the external validation dataset was 0.815 (95% CI: 0.743–0.886). The accuracy/sensitivity/specificity values of the AI model (74.1/73.1/75.0%) and the real-time diagnoses of experts (75.5/79.1/72.2%) in the external validation dataset were comparable. Conclusions: Our AI model demonstrated a diagnostic performance equivalent to that of experts.
Publisher	Springer
Source Title	Journal of Gastroenterology
Volume (Issue)	59
Page	543-555
Date of Issued	2024-07-01
Language	English
Handle URL	https://hdl.handle.net/11094/97114
PISSN	09441174
eISSN	14355922
Relation.isIdenticalTo	DOI (Publisher Version) https://doi.org/10.1007/s00535-024-02102-1
Access Rights	open access
CopyRight	This article is licensed under a Creative Commons Attribution 4.0 International License.
oaire:version	Version of Record
Category	学術雑誌論文 Journal Article

Resource Type	journal article
Local Type	Journal Article
DCTERMS.bibliographicCitation	Journal of Gastroenterology. 2024, 59, p. 543-555
DC.title	A novel artificial intelligence-based endoscopic ultrasonography diagnostic system for diagnosing the invasion depth of early gastric cancer
DC.creator	Uema, Ryotaro
	Hayashi, Yoshito
	Kizu, Takashi
	Igura, Takumi
	Ogiyama, Hideharu
	Yamada, Takuya
	Takeda, Risato
	Nagai, Kengo
	Inoue, Takuya
	Yamamoto, Masashi
	Yamaguchi, Shinjiro
	Kanesaka, Takashi
	Yoshihara, Takeo
	Kato, Minoru
	Yoshii, Shunsuke
	Tsujii, Yoshiki
	Shinzaki, Shinichiro
	Takehara, Tetsuo
DC.publisher	Springer
DC.language' scheme='DCTERMS.RFC1766	English
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2024-07-01
DC.identifier	https://doi.org/10.1007/s00535-024-02102-1
DC.subject	Artificial intelligence
	Deep learning
	Early gastric cancer
	Endoscopic ultrasonography
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/s00535-024-02102-1.
DCTERMS.abstract	Background: We developed an artificial intelligence (AI)-based endoscopic ultrasonography (EUS) system for diagnosing the invasion depth of early gastric cancer (EGC), and we evaluated the performance of this system. Methods: A total of 8280 EUS images from 559 EGC cases were collected from 11 institutions. Within this dataset, 3451 images (285 cases) from one institution were used as a development dataset. The AI model consisted of segmentation and classification steps, followed by the CycleGAN method to bridge differences in EUS images captured by different equipment. AI model performance was evaluated using an internal validation dataset collected from the same institution as the development dataset (1726 images, 135 cases). External validation was conducted using images collected from the other 10 institutions (3103 images, 139 cases). Results: The area under the curve (AUC) of the AI model in the internal validation dataset was 0.870 (95% CI: 0.796–0.944). Regarding diagnostic performance, the accuracy/sensitivity/specificity values of the AI model, experts (n = 6), and nonexperts (n = 8) were 82.2/63.4/90.4%, 81.9/66.3/88.7%, and 68.3/60.9/71.5%, respectively. The AUC of the AI model in the external validation dataset was 0.815 (95% CI: 0.743–0.886). The accuracy/sensitivity/specificity values of the AI model (74.1/73.1/75.0%) and the real-time diagnoses of experts (75.5/79.1/72.2%) in the external validation dataset were comparable. Conclusions: Our AI model demonstrated a diagnostic performance equivalent to that of experts.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	97114
citation_title	A novel artificial intelligence-based endoscopic ultrasonography diagnostic system for diagnosing the invasion depth of early gastric cancer
citation_author	Uema, Ryotaro
	Hayashi, Yoshito
	Kizu, Takashi
	Igura, Takumi
	Ogiyama, Hideharu
	Yamada, Takuya
	Takeda, Risato
	Nagai, Kengo
	Inoue, Takuya
	Yamamoto, Masashi
	Yamaguchi, Shinjiro
	Kanesaka, Takashi
	Yoshihara, Takeo
	Kato, Minoru
	Yoshii, Shunsuke
	Tsujii, Yoshiki
	Shinzaki, Shinichiro
	Takehara, Tetsuo
citation_publisher	Springer
citation_language	English
citation_date	2024-07-01
citation_journal_title	Journal of Gastroenterology
citation_volume	59
citation_firstpage	543
citation_lastpage	555
citation_doi	https://doi.org/10.1007/s00535-024-02102-1
citation_public_url	https://hdl.handle.net/11094/97114

A novel artificial intelligence-based endoscopic ultrasonography diagnostic system for diagnosing the invasion depth of early gastric cancer

Link to primary information

Item Information

Show details