EUS-FNA for pancreatic solid lesions yielded a high accuracy and low complication rate. Both cytological and cell-block preparations and on-site cytopathological evaluation contributed to improve the accuracy. The diagnostic ability of EUS-FNA was less for smaller lesions, and repeated procedures may be needed if malignancy is suspected.

Cisplatin and etoposide combination as the first-line chemotherapy for hepatobiliary or pancreatic poorly differentiated neuroendocrine carcinoma had only marginal antitumor activity and relatively severe toxicity compared with previous studies on extrapulmonary poorly differentiated neuroendocrine carcinoma treated with the same regimen.

OBJECTIVES: Intraductal papillary mucinous neoplasms (IPMNs) are precursor lesions of pancreatic adenocarcinoma. Artificial intelligence (AI) is a mathematical concept whose implementation automates learning and recognizing data patterns. The aim of this study was to investigate whether AI via deep learning algorithms using endoscopic ultrasonography (EUS) images of IPMNs could predict malignancy. METHODS: This retrospective study involved the analysis of patients who underwent EUS before pancreatectomy and had pathologically confirmed IPMNs in a single cancer center. In total, 3,970 still images were collected and fed as input into the deep learning algorithm. AI value and AI malignant probability were calculated. RESULTS: The mean AI value of malignant IPMNs was significantly greater than benign IPMNs (0.808 vs 0.104, P < 0.001). The area under the receiver operating characteristic curve for the ability to diagnose malignancies of IPMNs via AI malignant probability was 0.98 ( P < 0.001). The sensitivity, specificity, and accuracy of AI malignant probability were 95.7%, 92.6%, and 94.0%, respectively; its accuracy was higher than human diagnosis (56.0%) and the mural nodule (68.0%). Multivariate logistic regression analysis showed AI malignant probability to be the only independent factor for IPMN-associated malignancy (odds ratio: 295.16, 95% confidence interval: 14.13–6,165.75, P < 0.001). DISCUSSION: AI via deep learning algorithm may be a more accurate and objective method to diagnose malignancies of IPMNs in comparison to human diagnosis and conventional EUS features.

Despite its longer procedure time and higher perforation rate, ESD resulted in a higher en bloc resection rate and lower recurrence rate for larger colorectal tumors compared with EMR.

A prospective clinical study was conducted to evaluate the safety, feasibility, and efficacy of endoscopic ultrasound (EUS)-guided choledochoduodenostomy (CDS) with direct metallic stent placement using a prototype forward-viewing echoendoscope. The indication for EUS - CDS in this study was lower biliary obstruction only, and not failed endoscopic biliary drainage, because the aim was to evaluate EUS - CDS for first-line biliary drainage therapy. The technical and functional success rates were 94 % (17 /18) and 94 % (16 /17), respectively. Early complications (focal peritonitis) were encountered in two patients (11 %). No patients developed late complications. EUS - CDS with direct metallic stent placement using a forward-viewing echoendoscope was generally feasible and effective for malignant distal biliary tract obstruction. The forward-viewing echoendoscope was useful, especially for deploying the metallic stent.