biostudies-literatureUnknown15Hoyer DPUniversität Duisburg-Essen<h4>Introduction</h4>Perihilar cholangiocarcinoma (PHCC) is a rare malignancy with limited survival prediction accuracy. Artificial intelligence (AI) and digital pathology advancements have shown promise in predicting outcomes in cancer. We aimed to improve prognosis prediction for PHCC by combining AI-based histopathological slide analysis with clinical factors.<h4>Methods</h4>We retrospectively analyzed 317 surgically treated PHCC patients (January 2009-December 2018) at the University Hospital of Essen. Clinical data, surgical details, pathology, and outcomes were collected. Convolutional neural networks (CNN) analyzed whole-slide images. Survival models incorporated clinical and histological features.<h4>Results</h4>Among 142 eligible patients, independent survival predictors were tumoJournal of pathology informatics100345https://www.ebi.ac.uk/biostudies/studies/S-EPMC10698537biostudies-literatureAI-based digital histopathology for perihilar cholangiocarcinoma: A step, not a jump.PMC10698537Ting SBaldini GKoitka STreckmann JHaubold JStuben BONensa FFlaschel NHoyer DPRogacka NHosch RMalamutmann EfalseAI-based digital histopathology for perihilar cholangiocarcinoma: A step, not a jump.<h4>Introduction</h4>Perihilar cholangiocarcinoma (PHCC) is a rare malignancy with limited survival prediction accuracy. Artificial intelligence (AI) and digital pathology advancements have shown promise in predicting outcomes in cancer. We aimed to improve prognosis prediction for PHCC by combining AI-based histopathological slide analysis with clinical factors.<h4>Methods</h4>We retrospectively analyzed 317 surgically treated PHCC patients (January 2009-December 2018) at the University Hospital of Essen. Clinical data, surgical details, pathology, and outcomes were collected. Convolutional neural networks (CNN) analyzed whole-slide images. Survival models incorporated clinical and histological features.<h4>Results</h4>Among 142 eligible patients, independent survival predictors were tumo2024-01-01T00:00:00Z2024 Dec2026-06-03T11:43:12.261Z2025-04-05T10:50:09.733ZS-EPMC106985373807501510.1016/j.jpi.2023.100345