Artificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation

Abstract

The advancement of artificial intelligence (AI) has facilitated its application in medical fields. However, there has been little research for AI-assisted endoscopy, despite the clinical significance of the efficiency and safety of cannulation in the endoscopic retrograde cholangiopancreatography (ERCP). In this study, we aim to assist endoscopists performing ERCP through automatic detection of the ampulla and the identification of cannulation difficulty. We developed a novel AI-assisted system based on convolutional neural networks that predict the location of the ampulla and the difficulty of cannulation to the ampulla. ERCP data of 531 and 451 patients were utilized in the evaluation of our model for each task. Our model detected the ampulla with mean intersection-over-union 64.1%, precision 76.2%, recall 78.4%, and centroid distance 0.021. In classifying the cannulation difficulty, it achieved the recall of 71.9% for the class of easy cases and that of 61.1% for that of difficult cases. Remarkably, our model accurately detected AOV with varying morphological shape, size, and texture on par with the level of a human expert and showed promising results for recognizing cannulation difficulty. It demonstrated its potential to improve the quality of ERCP by assisting endoscopists.

Applications of Artificial Intelligence in Gastroenterology and Hepatology

“…One way for AI to assist endoscopists performing ERCPs is by helping to identify the ampulla in patients with difficult anatomy. A study utilizing a convolutional neural network that works during ERCP procedures to identify the ampulla was found to be 76% precise [77]. This may lead to easier cannulation in patients with anatomical variations of the ampulla, including diverticula.…”

Current status of artificial intelligence analysis for the treatment of pancreaticobiliary diseases using endoscopic ultrasonography and endoscopic retrograde cholangiopancreatography

“…Two articles on AI evaluation of the difficulty of ERCP have been published (Table 3). 54,55 Huang et al developed an AI system using CasNet, a segmentation architecture of DL trained on 1381 cholangiogram images. This AI could detect common bile duct stones.…”

Surgical strategies for challenging common bile duct stones in the endoscopic era: A comprehensive review of current evidence

“…Additionally, the integration of artificial intelligence (AI) in CBDS management represents a significant advancement in the field of endoscopy. AI-based models offer the potential to enhance predictive accuracy and streamline decision-making of cannulation, as well as improve difficulty scoring systems for endoscopic stone removal[ 9 - 12 ]. Nonetheless, surgical management continues to play a crucial role in subsequent prophylactic cholecystectomy to prevent biliary-related sequelae.…”