An endoscopic ultrasound-based interpretable deep learning model and nomogram for distinguishing pancreatic neuroendocrine tumors from pancreatic cancer.

Following this, a series of rigorous statistical analyses—including t-test analysis, correlation analysis, and LASSO regression—enabled the identification of a subset of 27 DL features that were found to be highly significant and definitively associated with PNETs and applied to further analysis.

also in 132,142 other papers