EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

Deep Learning-Based Detection of Malignant Bile Duct Stenosis in Fluoroscopy Images of Endoscopic Retrograde Cholangiopancreatography

Kien Vu Trung, Marcus Hollenbach, Gregory Patrick Veldhuizen, Oliver Lester Saldanha, Jakob Garbe, Jonas Rosendahl, Sebastian Krug, Patrick Michl, Jürgen Feisthammel, Thomas Karlas, Jochen Hampe, Albrecht Hoffmeister und 1 weitere

Digestion · 2024

DOI: 10.1159/000543049 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Digestion, 2024. Verfasst von Kien Vu Trung und 12 weiteren Autor:innen. Beteiligte Einrichtung: Division of Gastroenterology, Medical Department II, University of Leipzig Medical Center, Leipzig, Germany, kien.v.trung@gmail.com. Hauptthemen laut MEDLINE: Cholangiopancreatography, Endoscopic Retrograde, Deep Learning, Cholestasis, Bile Duct Neoplasms. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

The accurate distinction between benign and malignant biliary strictures (BSs) poses a significant challenge. Despite the use of bile duct biopsies and brush cytology via endoscopic retrograde cholangiopancreaticography (ERCP), the results remain suboptimal. Single-operator cholangioscopy can enhance the diagnostic yield in BS, but its limited availability and high costs are substantial barriers. Convolutional neural network-based systems may improve the diagnostic process and enhance reproducibility. Therefore, we assessed the feasibility of using deep learning to differentiate BS using fluoroscopy images during ERCP.

Methods

We conducted a retrospective review of adult patients (n = 251) from three university centers in Germany (Leipzig, Dresden, Halle) who underwent ERCP. We developed and evaluated a deep learning-based model using fluoroscopy images. The performance of the classifier was evaluated by measuring the area under the receiver operating characteristic curve (AUROC), and we utilized saliency map analyses to understand the decision-making process of the model.

Results

In cross-validation experiments, malignant BSs were detected with a mean AUROC of 0.89 ± 0.03. The test set of the Leipzig cohort demonstrated an AUROC of 0.90. In two independent external validation cohorts (Dresden, Halle), the deep learning-based classifier achieved an AUROC of 0.72 and 0.76, respectively. The artificial intelligence model’s predictions identified plausible characteristics within the fluoroscopy images.

Conclusion

By using a deep learning model, we were able to discriminate malignant BS from benign biliary conditions. The application of artificial intelligence enhances the diagnostic yield of malignant BS and should be validated in a prospective design.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cholangiopancreatography, Endoscopic RetrogradeDeep LearningCholestasisBile Duct NeoplasmsHumansRetrospective StudiesFluoroscopyFemaleMaleMiddle AgedAgedFeasibility StudiesReproducibility of ResultsROC CurveBile DuctsAdultAged, 80 and overConstriction, PathologicGermany

Stichwörter der Autor:innen

Artificial intelligenceBile duct stenosisEndoscopic retrograde cholangiopancreaticographyEndoscopy

Autor:innen und Institutionen

  • Division of Gastroenterology, Medical Department II, University of Leipzig Medical Center, Leipzig, Germany, kien.v.trung@gmail.com.
  • Division of Gastroenterology, Medical Department II, University of Leipzig Medical Center, Leipzig, Germany.
  • Department of Gastroenterology, Endocrinology, Metabolism and Clinical Infectiology, University Hospital Marburg, Marburg, Germany.
  • Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden, Dresden, Germany.
  • Medical Department I, Martin-Luther University Halle-Wittenberg, Halle, Germany.
  • Department of Medicine, Internal Medicine IV, University Hospital Heidelberg, Heidelberg, Germany.

Zitieren

APA

Vu Trung, K., Hollenbach, M., Veldhuizen, G. P., Saldanha, O. L., Garbe, J., Rosendahl, J., Krug, S., Michl, P., Feisthammel, J., Karlas, T., Hampe, J., Hoffmeister, A., & Kather, J. N. (2024). Deep Learning-Based Detection of Malignant Bile Duct Stenosis in Fluoroscopy Images of Endoscopic Retrograde Cholangiopancreatography. Digestion. https://doi.org/10.1159/000543049

Vancouver

Vu Trung K, Hollenbach M, Veldhuizen GP, Saldanha OL, Garbe J, Rosendahl J, et al. Deep Learning-Based Detection of Malignant Bile Duct Stenosis in Fluoroscopy Images of Endoscopic Retrograde Cholangiopancreatography. Digestion. 2024. doi:10.1159/000543049

BibTeX
@article{VuTrung2024,
  author = {Vu Trung, Kien and Hollenbach, Marcus and Veldhuizen, Gregory Patrick and Saldanha, Oliver Lester and Garbe, Jakob and Rosendahl, Jonas and Krug, Sebastian and Michl, Patrick and Feisthammel, Jürgen and Karlas, Thomas and Hampe, Jochen and Hoffmeister, Albrecht and Kather, Jakob Nikolas},
  title = {Deep Learning-Based Detection of Malignant Bile Duct Stenosis in Fluoroscopy Images of Endoscopic Retrograde Cholangiopancreatography},
  journal = {Digestion},
  year = {2024},
  doi = {10.1159/000543049}
}
Kostenlos starten →