Evaluation and understanding of automated urinary stone recognition methods

To assess the potential of automated machine learning methods for recognising urinary stones in endoscopy. Endoscopic stone recognition is a real challenge. But few urologists have sufficient expertise to have a diagnosis performance comparable to morpho‐constitutional analysis. Artificial Intelligence can be a solution, with promising results for pure stones. However, further studies on a larger panel of stones (pure and mixed) are needed to develop these methods further.