Endoscopic Ultrasound最新文献

EUS-guided hepaticogastrostomy (EUS-HGS) is one of the preferred methods in biliary drainage where ERCP fails or is contraindicated. The clinical outcomes of EUS-HGS are not well studied because of variability in procedure technique. We conducted a search of multiple electronic databases and conference proceedings from inception through January 2023. The clinical outcomes studied were pooled technical success, clinical success, and adverse events. Standard meta-analysis methods were used using the random-effects model, and heterogeneity was studied by I ² statistics. We analyzed 44 studies, which included 19 prospective and 25 retrospective studies. The pooled technical success rate of EUS-HGS was 94.4% (confidence interval [CI], 92.4%-95.9%; I ² = 0%), and the pooled clinical success rate was 88.6% (CI, 83.7%-92.2%; I ² = 0%). The pooled adverse outcomes with EUS-HGS were 23.8% (CI, 19.6%-28.5%; I ² = 0%). The mild adverse event rate associated with HGS was 5.8% (4.2%-8.1%; I ² = 0%), moderate adverse event rate was 12.1% (9.1%-15.8%; I ² = 16%), and severe adverse event rate was 4.2% (3.0%-5.7%; I ² = 61%), whereas fatal adverse event rate was 3.2% (1.9%-5.4%; I ² = 62%). On subgroup analysis, the pooled rate of adverse events of EUS-guided hepaticogastrostomy with antegrade stenting was 13.3% (95% CI, 8.2%-21.0%). The pooled technical success with EUS-guided hepaticogastrostomy with antegrade stenting was 89.7% (95% CI, 82.6%-94.2%), and clinical success was 92.5% (95% CI, 77.9%-97.7%). On the basis of our analysis of EUS-HGS, the overall technical success was 94.4%, and the clinical success rate was 88.6%, and the overall adverse events were reported to be 23.8%. These data can also help improve the clinical benefits of EUS-HGS in the selected patients in whom it is performed.

Rare malignant pancreatic lesions are systematically reported in this review. The focus is on the imaging appearance of the rare epithelial pancreatic tumors such as the solid pseudopapillary neoplasm, acinar cell carcinoma, rare subtypes of adenocarcinoma, and pancreatoblastoma as seen on ultrasound, EUS, and contrast-enhanced ultrasound or EUS. The present overview summarizes the data and shows that not every pancreatic tumor is likely to be the most common entities of ductal adenocarcinoma or neuroendocrine tumor.

Rare malignant mesenchymal pancreatic tumors are systematized and reported in this review. The focus is on the appearance on imaging. The present overview summarizes the data and shows that not every pancreatic tumor corresponds to the most common entities of ductal adenocarcinoma or neuroendocrine tumor.

Artificial intelligence (AI) is an epoch-making technology, among which the 2 most advanced parts are machine learning and deep learning algorithms that have been further developed by machine learning, and it has been partially applied to assist EUS diagnosis. AI-assisted EUS diagnosis has been reported to have great value in the diagnosis of pancreatic tumors and chronic pancreatitis, gastrointestinal stromal tumors, esophageal early cancer, biliary tract, and liver lesions. The application of AI in EUS diagnosis still has some urgent problems to be solved. First, the development of sensitive AI diagnostic tools requires a large amount of high-quality training data. Second, there is overfitting and bias in the current AI algorithms, leading to poor diagnostic reliability. Third, the value of AI still needs to be determined in prospective studies. Fourth, the ethical risks of AI need to be considered and avoided.