Applications of Artificial Intelligence in Gastrointestinal Endoscopic Ultrasound: Current Developments, Limitations and Future Directions

Abstract

Endoscopic ultrasound (EUS) effectively diagnoses malignant and pre-malignant gastrointestinal lesions. In the past few years, artificial intelligence (AI) has shown promising results in enhancing EUS sensitivity and accuracy, particularly for subepithelial lesions (SELs) like gastrointestinal stromal tumors (GISTs). Furthermore, AI models have shown high accuracy in predicting malignancy in gastric GISTs and distinguishing between benign and malignant intraductal papillary mucinous neoplasms (IPMNs). The utility of AI has also been applied to existing and emerging technologies involved in the performance and evaluation of EUS-guided biopsies. These advancements may improve training in EUS, allowing trainees to focus on technical skills and image interpretation. This review evaluates the current state of AI in EUS, covering imaging diagnosis, EUS-guided biopsies, and training advancements. It discusses early feasibility studies and recent developments, while also addressing the limitations and challenges. This article aims to review AI applications to EUS and its applications in clinical practice while addressing pitfalls and challenges.

Keywords: applications; artificial intelligence; developments; endoscopic ultrasound; future.

Figure 1

Images of AI in EUS for evaluating GISTs from Hirai et al.: (a) EUS image depicting a GIST without AI detection; (b) image with AI detection.

Figure 2

Images for an application of AI to ROSE by Fujii et al.: (a) original biopsy image; (b) image after evaluation by the AI with heat map representing the AI’s confidence in there being cancer.