EUVIMEDEUVIMED entdecken
Video/Audio

AI ‐Assisted Real‐Time Cytologic Diagnosis During EUS ‐ FNA of Pancreatic Masses (With Video)

Reiko Ashida iD, Takamichi Kuwahara, Takashi Koshikawa, Katsunori Hashimoto, Nozomi Okuno iD, Shin Haba iD, Yuki Kawaji, Takashi Tamura, Yasunobu Yamashita iD, Masahiro Itonaga iD, Yuka Kiriyama, Kenji Yamao und 2 weitere

Digestive Endoscopy · 2026-01 · 38 (1)

DOI: 10.1111/den.70081 ↗

Kurz gefasst

Video/Audio in der Zeitschrift Digestive Endoscopy, online erschienen am 15.12.2025. Verfasst von Reiko Ashida und 13 weiteren Autor:innen. Beteiligte Einrichtung: Second Department of Internal Medicine, Wakayama Medical University, Wakayama, Japan. Hauptthemen laut MEDLINE: Endoscopic Ultrasound-Guided Fine Needle Aspiration, Pancreatic Neoplasms, Artificial Intelligence. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 24 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Rapid on‐site evaluation enhances the diagnostic yield of endoscopic ultrasound‐guided fine needle aspiration (EUS‐FNA), but the cytopathologists are limited. This study aimed to assess the diagnostic capability of an artificial intelligence‐assisted ROSE (AI‐ROSE) for EUS‐FNA.

Methods

The study included 137 patients who underwent EUS‐FNA of a pancreatic mass between April 2019 and August 2021. Participants were divided into training ( n = 96), validation ( n = 15), and test cohorts ( n = 26). From the training/validation cohort, 5157/615 digital images of cell clusters were extracted and divided into 288 × 288‐pixel patches. These cell clusters were annotated and labeled into five classes. A semantic segmentation architecture was developed. From the test cohort, 120 cell clusters were extracted to compare diagnostic performance between AI‐ROSE and 21 endosonographers and 5 cytotechnologists with varying experience levels in ROSE.

Results

In total, 1,097,840 training, 31,817 validation, and 1920 test regions were extracted. In the test cohort, AI‐ROSE accuracy for three‐category classification (class 1/2, class 3, and class 4/5) was 89.8%. For two‐category classification (class 1/2/3 and class 4/5), sensitivity, specificity, and accuracy were 89.3%, 98.1%, and 95.1%, respectively. In the comparison cohort, AI‐ROSE accuracy for two‐category classification was 93.3%, significantly higher than all endosonographers (68.3%; range, 45.8%–86.7%) and cytotechnologists (76.3%; range, 72.5%–78.3%). The AI‐ROSE evaluation time for 120 cell clusters was 6.04 s, much shorter than that of all endosonographers (1800; 480–6000 s) and cytotechnologists (2160; 1020–3600 s).

Conclusions

The AI‐ROSE model shows remarkable speed and accuracy in diagnosing pancreatic cell clusters, enabling rapid decision‐making during EUS‐FNA. UMIN‐CTR; No. 000042212.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Endoscopic Ultrasound-Guided Fine Needle AspirationPancreatic NeoplasmsArtificial IntelligenceHumansMaleFemaleMiddle AgedAgedRetrospective StudiesAdult

Stichwörter der Autor:innen

artificial intelligencedeep learningendoscopic ultrasound‐guided fine needle aspirationpancreatic cancer

Autor:innen und Institutionen

  • Second Department of Internal Medicine, Wakayama Medical University, Wakayama, Japan.
  • Department of Gastroenterology, Aichi Cancer Center Hospital, Nagoya, Japan.
  • Department of Medical Technology, Shubun University Faculty of Medical Sciences, Ichinomiya, Aichi, Japan.
  • Department of Pathology, Narita Memorial Hospital, Toyohashi, Aichi, Japan.
  • Department of Gastroenterology, Narita Memorial Hospital, Toyohashi, Aichi, Japan.

ORCID-Profile: Reiko Ashida, Nozomi Okuno, Shin Haba, Yasunobu Yamashita, Masahiro Itonaga, Kazuo Hara, Masayuki Kitano

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Ashida, R., Kuwahara, T., Koshikawa, T., Hashimoto, K., Okuno, N., Haba, S., Kawaji, Y., Tamura, T., Yamashita, Y., Itonaga, M., Kiriyama, Y., Yamao, K., Hara, K., & Kitano, M. (2026). AI ‐Assisted Real‐Time Cytologic Diagnosis During EUS ‐ FNA of Pancreatic Masses (With Video). Digestive Endoscopy, 38(1). https://doi.org/10.1111/den.70081

Vancouver

Ashida R, Kuwahara T, Koshikawa T, Hashimoto K, Okuno N, Haba S, et al. AI ‐Assisted Real‐Time Cytologic Diagnosis During EUS ‐ FNA of Pancreatic Masses (With Video). Digestive Endoscopy. 2026;38(1). doi:10.1111/den.70081

BibTeX
@article{Ashida2026,
  author = {Ashida, Reiko and Kuwahara, Takamichi and Koshikawa, Takashi and Hashimoto, Katsunori and Okuno, Nozomi and Haba, Shin and Kawaji, Yuki and Tamura, Takashi and Yamashita, Yasunobu and Itonaga, Masahiro and Kiriyama, Yuka and Yamao, Kenji and Hara, Kazuo and Kitano, Masayuki},
  title = {AI ‐Assisted Real‐Time Cytologic Diagnosis During EUS ‐ FNA of Pancreatic Masses (With Video)},
  journal = {Digestive Endoscopy},
  year = {2026},
  volume = {38},
  number = {1},
  doi = {10.1111/den.70081}
}
Kostenlos starten →