EUVIMEDEUVIMED entdecken
Crossref

Fully Automated Detection of Pancreaticobiliary Maljunction Based on 3D Magnetic Resonance Cholangiopancreatography Using Deep Learning

Xiaoyu Zhang, Weizheng Liu, Ziyue Chang, Chunyan Chai, Wenping Lu

Digestion · 09.06.2026 · 1-10

DOI: 10.1159/000552759 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digestion, online erschienen am 09.06.2026. Verfasst von Xiaoyu Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Hepato-Pancreato-Biliary Surgery, First Medical Center, Chinese PLA General Hospital, Beijing, China. Die Arbeit nennt 21 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Pancreaticobiliary maljunction (PBM) is closely related to biliary tract cancer. The early detection of PBM is crucial but challenging. We aimed to develop and validate a deep learning model for fully automatically detection of PBM using magnetic resonance cholangiopancreatography (MRCP) images.

Methods

Clinical and imaging data from patients who underwent MRCP examinations from January 2020 to December 2021 were retrospectively collected. A total of 200 patients (100 with confirmed PBM and 100 non-PBM controls) were enrolled. The dataset was randomly divided into training, validation, and test sets in a 6:2:2 ratio. The training and validation sets were used to train YOLOv5 and Inception-ResNetV2. The test set was used to evaluate the accuracy of the model.

Results

The PBM group had a higher proportion of females (62% vs. 42%, p = 0.01) and biliary tract cancer (11% vs. 3%, p = 0.03) than controls. The optimal model achieved a mean absolute error of 6.2% and an F1 score of 93.0%, with sensitivity, specificity, positive predictive value, and negative predictive value of 95.0%, 92.5%, 92.7%, and 94.9%, respectively.

Conclusion

The proposed deep learning model demonstrates high accuracy in automated PBM detection on MRCP images, offering potential to improve diagnostic efficiency and reduce interobserver variability.

Schlagwörter

Stichwörter der Autor:innen

Artificial intelligenceBiliary tract cancerDeep learningMagnetic resonance cholangiopancreatographyPancreaticobiliary maljunction

Autor:innen und Institutionen

  • Faculty of Hepato-Pancreato-Biliary Surgery, First Medical Center, Chinese PLA General Hospital, Beijing, China.
  • Nankai University, Tianjin, China.
  • Beijing Bolanggu Technology Co., Ltd, Beijing, China.
  • Faculty of Hepato-Pancreato-Biliary Surgery, First Medical Center, Chinese PLA General Hospital, Beijing, China, lvwenping301@126.com.

Zitieren

APA

Zhang, X., Liu, W., Chang, Z., Chai, C., & Lu, W. (2026). Fully Automated Detection of Pancreaticobiliary Maljunction Based on 3D Magnetic Resonance Cholangiopancreatography Using Deep Learning. Digestion, 1-10. https://doi.org/10.1159/000552759

Vancouver

Zhang X, Liu W, Chang Z, Chai C, Lu W. Fully Automated Detection of Pancreaticobiliary Maljunction Based on 3D Magnetic Resonance Cholangiopancreatography Using Deep Learning. Digestion. 2026:1-10. doi:10.1159/000552759

BibTeX
@article{Zhang2026,
  author = {Zhang, Xiaoyu and Liu, Weizheng and Chang, Ziyue and Chai, Chunyan and Lu, Wenping},
  title = {Fully Automated Detection of Pancreaticobiliary Maljunction Based on 3D Magnetic Resonance Cholangiopancreatography Using Deep Learning},
  journal = {Digestion},
  year = {2026},
  pages = {1--10},
  doi = {10.1159/000552759}
}
Kostenlos starten →