No abstract

Intraductal papillary neoplasm of the bile duct (IPNB) is a grossly visible papillary biliary neoplasm with morphological variations and occasional invasion. Recently a new classification of IPNB into type 1 and type 2 was proposed in which the type 1 IPNBs consist of fine papillary neoplastic glands and the type 2 IPNBs consist of complex branching glands, seldom with foci of solid-tubular components. However, clinicopathological and molecular characteristics of these types of IPNBs are yet to be identified. We aimed to uncover clinicopathological and molecular characteristics of the types of IPNBs. Thirty-six IPNBs were studied retrospectively. Clinicopathological features as well as molecular alterations of 31 genes were evaluated by means of targeted next-generation sequencing and immunohistochemical examination of expression of mucin and cancer-associated molecules. The 36 IPNBs were classified into 22 of type 1 and 14 of type 2. The type 1 IPNBs were associated with a non-invasive phenotype, intestinal and oncocytic subtypes, development in the intrahepatic bile duct, overt mucin production, and a relatively good prognosis. The type 2 IPNBs were associated with an invasive phenotype, the pancreatobiliary subtype, development within the extrahepatic bile duct, and worse prognosis compared with the type 1 IPNBs. In the molecular analysis, recurrent mutations were found in RNF43 (5.7%). Mutations in KRAS and GNAS were enriched in the type 1 IPNBs, whereas mutations in TP53, SMAD4, and KMT2C were enriched in the type 2 IPNBs. These results indicate that IPNBs consist of two distinct types of neoplasms specifically associated with clinicopathological features and molecular phenotypes.No conflicts of interest were declared.

Histopathological diagnosis of pancreatic ductal adenocarcinoma (PDAC) on endoscopic ultrasonography-guided fine-needle biopsy (EUS-FNB) specimens has become the mainstay of preoperative pathological diagnosis. However, on EUS-FNB specimens, accurate histopathological evaluation is difficult due to low specimen volume with isolated cancer cells and high contamination of blood, inflammatory and digestive tract cells. In this study, we performed annotations for training sets by expert pancreatic pathologists and trained a deep learning model to assess PDAC on EUS-FNB of the pancreas in histopathological whole-slide images. We obtained a high receiver operator curve area under the curve of 0.984, accuracy of 0.9417, sensitivity of 0.9302 and specificity of 0.9706. Our model was able to accurately detect difficult cases of isolated and low volume cancer cells. If adopted as a supportive system in routine diagnosis of pancreatic EUS-FNB specimens, our model has the potential to aid pathologists diagnose difficult cases.

No abstract