Automatic differentiation of solid pancreatic lesions in Endoscopic Ultrasound using – a multicentre study.

This article discusses the development of a deep learning model for the automatic differentiation of solid pancreatic lesions using endoscopic ultrasound (EUS). The model was trained using a dataset of 27,756 images from 107 EUS exams conducted in two specialized centers. The model achieved high sensitivity, specificity, positive and negative predictive values, and accuracy in identifying pancreatic ductal adenocarcinoma (PDAC) and pancreatic neuroendocrine tumors (pNETs). The authors conclude that deep learning models can help improve the accuracy of diagnosing pancreatic adenocarcinoma. [Extracted from the article]