Camille Pignolet

The paper identifies distinct progression paths in pancreatic papillary cystic neoplasms using integrated transcriptomics and histology, enabling phenotype-specific prediction of high-grade dysplasia.

This paper develops a self-supervised learning model to predict iCCA transcriptomic classes from histological images, achieving good to very good performance in multiple validation sets.

This study shows that loss of HNF1B contributes to IPMN initiation and identifies its role as a tumor suppressor in pancreatic ductal cells.