EUVIMEDEUVIMED entdecken
ValidierungsstudieMultizentrische StudieOpen Access · CC BY 4.0

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

Ryotaro Uema, Yoshito Hayashi, Takashi Kizu, Takumi Igura, Hideharu Ogiyama, Takuya Yamada, Risato Takeda, Kengo Nagai, Takuya Inoue, Masashi Yamamoto, Shinjiro Yamaguchi, Takashi Kanesaka und 6 weitere

Journal of Gastroenterology · 2024-07 · 59 (7) · 543-555

DOI: 10.1007/s00535-024-02102-1 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Journal of Gastroenterology, online erschienen am 07.05.2024. Verfasst von Ryotaro Uema und 17 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastroenterology and Hepatology, Osaka University Graduate School of Medicine, 2-2, Yamadaoka, Suita, Osaka, 565-0871, Japan. Hauptthemen laut MEDLINE: Stomach Neoplasms, Artificial Intelligence, Endosonography, Neoplasm Invasiveness. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS KAKENHI, Osaka University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Stomach NeoplasmsArtificial IntelligenceEndosonographyNeoplasm InvasivenessHumansMaleFemaleMiddle AgedAgedSensitivity and SpecificityEarly Detection of CancerAged, 80 and overAdultArea Under Curve

Stichwörter der Autor:innen

Artificial intelligenceDeep learningEarly gastric cancerEndoscopic ultrasonography

Autor:innen und Institutionen

  • Department of Gastroenterology and Hepatology, Osaka University Graduate School of Medicine, 2-2, Yamadaoka, Suita, Osaka, 565-0871, Japan.
  • Department of Gastroenterology, Yao Municipal Hospital, Yao, 581-0069, Japan.
  • Department of Gastroenterology, Sumitomo Hospital, Osaka, 530-0005, Japan.
  • Department of Gastroenterology, Ikeda Municipal Hospital, Ikeda, 563-0025, Japan.
  • Department of Gastroenterology, Osaka Rosai Hospital, Sakai, 591-8025, Japan.
  • Department of Gastroenterology, Itami City Hospital, Itami, 664-0015, Japan.

Förderung

  • JSPS KAKENHI
  • Osaka University

Zitieren

APA

Uema, R., Hayashi, Y., Kizu, T., Igura, T., Ogiyama, H., Yamada, T., Takeda, R., Nagai, K., Inoue, T., Yamamoto, M., Yamaguchi, S., Kanesaka, T., Yoshihara, T., Kato, M., Yoshii, S., Tsujii, Y., Shinzaki, S., & Takehara, T. (2024). A novel artificial intelligence-based endoscopic ultrasonography diagnostic system for diagnosing the invasion depth of early gastric cancer. Journal of Gastroenterology, 59(7), 543-555. https://doi.org/10.1007/s00535-024-02102-1

Vancouver

Uema R, Hayashi Y, Kizu T, Igura T, Ogiyama H, Yamada T, et al. A novel artificial intelligence-based endoscopic ultrasonography diagnostic system for diagnosing the invasion depth of early gastric cancer. Journal of Gastroenterology. 2024;59(7):543-555. doi:10.1007/s00535-024-02102-1

BibTeX
@article{Uema2024,
  author = {Uema, Ryotaro and Hayashi, Yoshito and Kizu, Takashi and Igura, Takumi and Ogiyama, Hideharu and Yamada, Takuya and Takeda, Risato and Nagai, Kengo and Inoue, Takuya and Yamamoto, Masashi and Yamaguchi, Shinjiro and Kanesaka, Takashi and Yoshihara, Takeo and Kato, Minoru and Yoshii, Shunsuke and Tsujii, Yoshiki and Shinzaki, Shinichiro and Takehara, Tetsuo},
  title = {A novel artificial intelligence-based endoscopic ultrasonography diagnostic system for diagnosing the invasion depth of early gastric cancer},
  journal = {Journal of Gastroenterology},
  year = {2024},
  volume = {59},
  number = {7},
  pages = {543--555},
  doi = {10.1007/s00535-024-02102-1}
}
Kostenlos starten →