P0043 - Decoding Biliary Strictures: A Transatlantic Multicenter Study on AI Performance Across Lesion Topography

Award: ACG Presidential Poster Award

Francisco Mendes, MD¹, Miguel Mascarenhas Saraiva, MD, PhD¹, António Costa, MD², Belen Agudo, MD², Jessica Widmer, DO³, Uzma Siddiqui, MD, FACG⁴, Tiago Ribeiro, MD¹, Miguel Martins, MD¹, Pedro Cardoso, MD¹, Joana Mota, MD¹, Maria João Almeida, MD¹, João Afonso, MD¹, Grace Kim, MD⁵, Daniel De la Iglesia garcia, MD², Ana Peréz Gonzalez, MD², Carlos Esteban Fernandez-Zarza, MD², Maria Moris, MD⁶, Matheus Ferreira de Carvalho, MD⁷, Marcos Eduardo Lera dos Santos, MD⁷, João Ferreira, PhD⁸, Tamas Gonda, MD⁹, André Santos, MD¹⁰, Filipe Vilas Boas, MD, PhD¹¹, Pedro Moutinho Ribeiro, MD, PhD¹¹, Pedro Pereira, MD, PhD¹, Mariano Gonzalez Haba, MD², Eduardo Hourneaux De Moura, MD, PhD¹², Guilherme Macedo, MD, PhD¹
1Centro Hospitalar Universitário São João, Porto, Porto, Portugal; 2Hospital Universitario Puerta de Hierro Majadahonda, Madrid, Madrid, Spain; 3NYU Langone Health, Mineola, NY; 4Center for Endoscopic Research and Therapeutics (CERT) and Advanced Endoscopy Training, University of Chicago, Illinois, IL; 5Center for Endoscopic Research and Therapeutics (CERT) and Advanced Endoscopy Training, University of Chicago, Chicago, IL; 6Hospital Universitario Marqués de Valdecilla, GI, Santander, Spain,, Santander, Cantabria, Spain; 7Hospital das Clínicas da Faculdade de Medicina da Universidade de Sao Paulo, São Paulo, Sao Paulo, Brazil; 8Faculdade de Engenharia da Universidade do Porto, Porto, Porto, Portugal; 9NYU Langone Health, Gastroenterology, New York, NY; 10Faculdade de Medicina da Universidade do Porto, Porto, Porto, Portugal; 11Centro Hospitalar Universitário de São João, Porto, Porto, Portugal; 12Hospital das Clínicas da Faculdade de Medicina da USP, São Paulo, Sao Paulo, Brazil

Introduction: Cholangiocarcinoma (CCa) is a complex neoplasm with poor prognosis, being tipically divided based on location in intrahepatic (iCCa), perihilar (pCCa) or distal (dCCa). Digital single-operator cholangioscopy (DSOC) is fundamental in CCa diagnosis despite some known limitations, such as suboptimal biopsy sensitivity, lack of a standardized morphology classification and technical issues. Emerging evidence highlights AI’s potential to enhance DSOC diagnostic capacity, but the differential performance according to tumor characteristics like topography remains unassessed. This study aimed to evaluate an AI algorithm’s effectiveness in detecting iCCa, pCCa, and dCCa.


Methods: A deep learning model based on a convolutional neural network (CNN) was designed to predict the malignancy status of biliary strictures. The model was built using DSOC images from six international high-volume centers in four countries. Images showing strictures due to histologically proven cholangiocarcinoma or benign conditions were included. The detection rate of the algorithm was compared for each location category.


Results: A total of 201.016 images from 72 patients and 2 different devices (SpyGlassTM DS II Direct Visualization System, EyeMaxTM Cholangioscope) were included. 45 patients were male (62.5%) and the mean age was 67 years (SD: 12.6 years). Common bile duct (CBD) strictures represented 51% of the total while intrahepatic and perihilar accounted for 25% and 24%, respectively. The algorithm’s detection rate of strictures representing CCa was 93.7% for iCCa, 94.0% for pCCa and 95.3% for dCCa. Pairwise comparisons revealed a significant difference in the detection rate between intrahepatic and perihilar (p< 0.001) and perihilar and CBD (p< 0.001).

Discussion: This is the first model to demonstrate accuracy across different types of biliary strictures and in diverse demographic populations, establishing a benchmark for AI-driven diagnostic tools in this domain. Topographic traits of biliary strictures influence the diagnostic performance of DSOC, often with difficult evaluation of intrahepatic and perihilar biliary strictures. While AI shows promise in improving the diagnostic capacity of DSOC, its performance is impacted by DSOC technical limitations. Developing models should address these issues before widespread clinical integration. This evidence stresses the importance of keeping a “human on the loop,” providing clinical reasoning to guide the application of AI algorithms.


Figure: Figure 1 - Study Design, biliary stricture location and detection rate of the deep learning model according to biliary stricture location. CBD - common bile duct

Disclosures:
Francisco Mendes indicated no relevant financial relationships.
Miguel Mascarenhas Saraiva indicated no relevant financial relationships.
António Costa indicated no relevant financial relationships.
Belen Agudo indicated no relevant financial relationships.
Jessica Widmer indicated no relevant financial relationships.
Uzma Siddiqui indicated no relevant financial relationships.
Tiago Ribeiro indicated no relevant financial relationships.
Miguel Martins indicated no relevant financial relationships.
Pedro Cardoso indicated no relevant financial relationships.
Joana Mota indicated no relevant financial relationships.
Maria João Almeida indicated no relevant financial relationships.
João Afonso indicated no relevant financial relationships.
Grace Kim indicated no relevant financial relationships.
Daniel De la Iglesia garcia indicated no relevant financial relationships.
Ana Peréz Gonzalez indicated no relevant financial relationships.
Carlos Esteban Fernandez-Zarza indicated no relevant financial relationships.
Maria Moris indicated no relevant financial relationships.
Matheus Ferreira de Carvalho indicated no relevant financial relationships.
Marcos Eduardo Lera dos Santos indicated no relevant financial relationships.
João Ferreira indicated no relevant financial relationships.
Tamas Gonda indicated no relevant financial relationships.
André Santos indicated no relevant financial relationships.
Filipe Vilas Boas indicated no relevant financial relationships.
Pedro Moutinho Ribeiro indicated no relevant financial relationships.
Pedro Pereira indicated no relevant financial relationships.
Mariano Gonzalez Haba indicated no relevant financial relationships.
Eduardo Hourneaux De Moura indicated no relevant financial relationships.
Guilherme Macedo indicated no relevant financial relationships.

Francisco Mendes, MD¹, Miguel Mascarenhas Saraiva, MD, PhD¹, António Costa, MD², Belen Agudo, MD², Jessica Widmer, DO³, Uzma Siddiqui, MD, FACG⁴, Tiago Ribeiro, MD¹, Miguel Martins, MD¹, Pedro Cardoso, MD¹, Joana Mota, MD¹, Maria João Almeida, MD¹, João Afonso, MD¹, Grace Kim, MD⁵, Daniel De la Iglesia garcia, MD², Ana Peréz Gonzalez, MD², Carlos Esteban Fernandez-Zarza, MD², Maria Moris, MD⁶, Matheus Ferreira de Carvalho, MD⁷, Marcos Eduardo Lera dos Santos, MD⁷, João Ferreira, PhD⁸, Tamas Gonda, MD⁹, André Santos, MD¹⁰, Filipe Vilas Boas, MD, PhD¹¹, Pedro Moutinho Ribeiro, MD, PhD¹¹, Pedro Pereira, MD, PhD¹, Mariano Gonzalez Haba, MD², Eduardo Hourneaux De Moura, MD, PhD¹², Guilherme Macedo, MD, PhD¹. P0043 - Decoding Biliary Strictures: A Transatlantic Multicenter Study on AI Performance Across Lesion Topography, ACG 2025 Annual Scientific Meeting Abstracts. Phoenix, AZ: American College of Gastroenterology.