BACKGROUND: Biliary cancers are rare, and few reported cases of brain metastases from primary biliary cancers exist, especially describing patients in the United States. This report assesses the proportion and incidence of brain metastases arising from primary biliary cancers [cholangiocarcinoma (CCA) and gallbladder cancer] at Stanford University and the University of California, San Francisco, describes clinical characteristics, and provides a case series. METHODS: We queried 3 clinical databases at Stanford and the University of California, San Francisco to retrospectively identify and review the charts of 15 patients with brain metastases from primary biliary cancers occurring between 1990 to 2020. RESULTS: Among patients with brain metastases analyzed at Stanford (3,585), 6 had a primary biliary cancer, representing 0.17% of all brain metastases. Among biliary cancer patients at the University of California, San Francisco (1,055), 9 had brain metastases, representing an incidence in biliary cancer of 0.85%. A total of 15 biliary cancer patients with brain metastases were identified at the two institutions. Thirteen out of 15 patients (86.7%, 95% CI: 59.5-98.3) were female. The median overall survival from primary biliary cancer diagnosis was 214 days (95% CI: 71.69-336.82 days) and subsequent OS from the time of brain metastasis diagnosis was 57 days (95% CI: 13.43-120.64 days). Death within 90 days of brain metastasis diagnosis occurred in 66.67% of patients (95% CI: 38.38-88.17). CONCLUSIONS: Brain metastases from primary biliary cancers are rare, with limited survival once diagnosed. This report can aid health care providers in caring for patients with brain metastases from primary biliary cancers.

Pancreatic ductal adenocarcinoma (PDAC) has been left behind in the evolution of personalized medicine. Predictive markers of response to therapy are lacking in PDAC despite various histological and transcriptional classification schemes. We report an artificial intelligence (AI) approach to histologic feature examination that extracts a signature predictive of disease-specific survival (DSS) in patients with PDAC receiving adjuvant gemcitabine. We demonstrate that this AI-generated histologic signature is associated with outcomes following adjuvant gemcitabine, while three previously developed transcriptomic classification systems are not (n = 47). We externally validate this signature in an independent cohort of patients treated with adjuvant gemcitabine (n = 46). Finally, we demonstrate that the signature does not stratify survival outcomes in a third cohort of untreated patients (n = 161), suggesting that the signature is specifically predictive of treatment-related outcomes but is not generally prognostic. This imaging analysis pipeline has promise in the development of actionable markers in other clinical settings where few biomarkers currently exist.