A deep learning–based, real-time image report system for linear EUS - 08/05/25
Abstract |
Background and Aims |
The integrity of image acquisition is critical for biliopancreatic EUS reporting, significantly affecting the quality of EUS examinations and disease-related decision-making. However, the quality of EUS reports varies among endoscopists. To address this issue, we developed a deep learning–based EUS automatic image report system (EUS-AIRS), aiming to achieve automatic photodocumentation in real-time during EUS, including capturing standard stations, lesions, and puncture procedures.
Methods |
Eight deep learning models trained and tested using 235,784 images were integrated to construct the EUS-AIRS. The performance of EUS-AIRS was tested through man–machine comparisons at 2 levels: a retrospective test (include internal and external testing) and a prospective test. From May 2023 to October 2023, a total of 114 patients undergoing EUS at Renmin Hospital of Wuhan University were consecutively recruited for prospective testing. The primary outcome was the completeness of the EUS-AIRS for capturing standard stations.
Results |
In terms of completeness in capturing biliopancreatic standard stations, EUS-AIRS exceeded the capabilities of endoscopists at all levels of expertise in retrospective internal testing (90.8% [95% confidence interval (CI), 88.7%-92.9%] vs 70.5% [95% CI, 67.2%-73.8%]; P < .001) and external testing (91.4% [95% CI, 88.4%-94.4%] vs 68.2% [95% CI, 63.3%-73.2%]; P < .001). EUS-AIRS exhibited high accuracy and completeness in capturing standard station images. The completeness of the EUS-AIRS significantly outperformed manual endoscopist reports (91.4% [95% CI, 89.4%-93.4%] vs 78.1% [95% CI, 75.1%-81.0%); P < .001).
Conclusions |
EUS-AIRS exhibits exceptional capabilities in real-time, capturing high-quality and high-integrity biliopancreatic EUS images. This showcases the potential of applying an artificial intelligence image report system in the EUS field.
Il testo completo di questo articolo è disponibile in PDF.Abbreviations : AI, CI, DCNN, EUS-AIRS
Mappa
| DIVERSITY, EQUITY, AND INCLUSION: We worked to ensure gender balance in the recruitment of human subjects. The author list of this paper includes contributors from the location where the research was conducted who participated in the data collection, design, analysis, and/or interpretation of the work. |
|
| Data-sharing statement: Individual de-identified participant data that underlie the results reported in this article will be shared for investigators after article publication. To gain access, the data requester will need to contact the corresponding author. |
Vol 101 - N° 6
P. 1166 - giugno 2025 Ritorno al numero
Articolo precedente
- Interobserver agreement in dysplasia grading of intraductal papillary mucinous neoplasms: performance of Kyoto guidelines and optimization of endomicroscopy biomarkers through pathology reclassification
- Matthew Leupold, Wei Chen, Ashwini K. Esnakula, Wendy L. Frankel, Stacey Culp, Philip A. Hart, Ahmed Abdelbaki, Zarine K. Shah, Erica Park, Peter Lee, Mitchell L. Ramsey, Samuel Han, Hamza Shah, Jordan Burlen, Georgios I. Papachristou, Zobeida Cruz-Monserrate, Mary Dillhoff, Jordan M. Cloyd, Timothy M. Pawlik, Somashekar G. Krishna
- Necrosectomy and its timing in relation to clinical outcomes of EUS-guided treatment of walled-off pancreatic necrosis: a multicenter study
- Masahiro Tsujimae, Tomotaka Saito, Arata Sakai, Mamoru Takenaka, Shunsuke Omoto, Tsuyoshi Hamada, Shogo Ota, Hideyuki Shiomi, Sho Takahashi, Toshio Fujisawa, Kentaro Suda, Saburo Matsubara, Shinya Uemura, Takuji Iwashita, Kensaku Yoshida, Akinori Maruta, Mitsuru Okuno, Keisuke Iwata, Nobuhiko Hayashi, Tsuyoshi Mukai, Ichiro Yasuda, Hiroyuki Isayama, Yousuke Nakai, Atsuhiro Masuda, WONDERFUL study group in Japan
Benvenuto su EM|consulte, il riferimento dei professionisti della salute.
L'accesso al testo integrale di questo articolo richiede un abbonamento.
Già abbonato a @@106933@@ rivista ?