Current status of artificial intelligence analysis for the diagnosis of gallbladder diseases using ultrasonography: a scoping review.

Background: Ultrasound (US) is the first-line imaging method for gallbladder diseases (GBDs), with advantages of easy accessibility, real-time dynamic imaging, and no radiation. However, using only visual judgment from US images to stratify the risk of gallbladder (GB) lesions is challenging. In addition, the diagnostic ability of sonographers is highly correlated with their knowledge reserves, clinical experience, and proficiency in operation. Recently, the application of artificial intelligence (AI) in medical image recognition has attracted widespread attention. This review aims to provide a comprehensive summary and analysis of the application of US-based AI technology in various GBDs. In addition, the diagnostic ability of US-based AI technology in GBDs based on the findings of published articles was evaluated.

Methods: We searched the PubMed and Wiley databases using predefined keywords for articles published over the past two decades (from January 2003 to December 2023) to evaluate research progress in this field. Articles were screened for relevant publications about US-based AI applications in GBDs. Then, we conducted a comprehensive summary and analysis of the application of US-based AI technology in various GBDs and evaluated its diagnostic performance.

Results: Following PRISMA-ScR guidelines, 16 studies were included in this review. These studies involve a relatively narrow spectrum of GBDs, including GB polyps, gallbladder cancer (GBC), GB stones, and biliary atresia (BA). The most widely used applications of AI in GBDs are GB polyps and GBC. AI has achieved satisfactory sensitivity, specificity, or accuracy in the differential diagnosis of GB polypoid lesions. AI has certain application value in the GB stone measurement and auxiliary diagnosis of GBC and BA.

Conclusions: The current status, limitations, and future perspectives of AI-assisted ultrasonography in GBDs were reported. In the near future, the AI has the potential to become a breakthrough in the diagnosis of GBDs, supporting doctors in improving the diagnostic ability of GBDs with ultrasonography.