Automatic Identification of Papillary Projections in Indeterminate Biliary Strictures Using Digital Single-Operator Cholangioscopy

Tiago Ribeiro; Miguel Mascarenhas Saraiva; João Afonso; João P S Ferreira; Filipe Vilas Boas; Marco P L Parente; Renato N Jorge; Pedro Pereira; Guilherme Macedo

doi:10.14309/ctg.0000000000000418

Automatic Identification of Papillary Projections in Indeterminate Biliary Strictures Using Digital Single-Operator Cholangioscopy

Clin Transl Gastroenterol. 2021 Oct 27;12(11):e00418. doi: 10.14309/ctg.0000000000000418.

Authors

Tiago Ribeiro^{1

2}, Miguel Mascarenhas Saraiva^{1

2

3}, João Afonso^{1

2}, João P S Ferreira^{4

5}, Filipe Vilas Boas^{1

2

3}, Marco P L Parente^{4

5}, Renato N Jorge^{4

5}, Pedro Pereira^{1

2

3}, Guilherme Macedo^{1

2

3}

Affiliations

¹ Department of Gastroenterology, São João University Hospital, Alameda Professor Hernâni Monteiro, Porto, Portugal.
² WGO Gastroenterology and Hepatology Training Center, Porto, Portugal.
³ Faculty of Medicine of the University of Porto, Alameda Professor Hernâni Monteiro, Porto, Portugal.
⁴ Department of Mechanical Engineering, Faculty of Engineering of the University of Porto, Rua Dr. Roberto Frias, Porto, Portugal.
⁵ INEGI-Institute of Science and Innovation in Mechanical and Industrial Engineering, Rua Dr. Roberto Frias, Porto, Portugal.

Abstract

Introduction: Characterization of biliary strictures is challenging. Papillary projections (PP) are often reported in biliary strictures with high malignancy potential during digital single-operator cholangioscopy. In recent years, the development of artificial intelligence (AI) algorithms for application to endoscopic practice has been intensely studied. We aimed to develop an AI algorithm for automatic detection of PP in digital single-operator cholangioscopy images.

Methods: A convolutional neural network (CNN) was developed. Each frame was evaluated for the presence of PP. The CNN's performance was measured by the area under the curve, sensitivity, specificity, and positive and negative predictive values.

Results: A total of 3,920 images from 85 patients were included. Our model had a sensitivity and specificity 99.7% and 97.1%, respectively. The area under the curve was 1.00.

Discussion: Our CNN was able to detect PP with high accuracy. Future development of AI tools may optimize the macroscopic characterization of biliary strictures.

Publication types

Research Support, Non-U.S. Gov't
Validation Study

MeSH terms

Bile Ducts / pathology
Cholestasis / diagnosis*
Cholestasis / pathology*
Constriction, Pathologic / diagnosis
Deep Learning*
Diagnosis, Computer-Assisted / methods*
Endoscopy, Digestive System / methods*
Humans
Proof of Concept Study
Reproducibility of Results