Partner contact: Ismail Labgaa
EPFL laboratory: Machine Learning and Optimization Laboratory (MLO), intelligent Global Health Research group
EPFL contact: Mary-Anne Hartley
Liver cancer ranks third in terms of cancer-related mortality and its incidence is dramatically increasing. Of note, it is the only cancer which mortality is predicted to increase by 2040. Hepatocellular carcinoma (HCC) accounts for 90% of primary liver cancers. Tremendous efforts have been pursued to establish HCC prognostic, including clinical, radiological, pathological and even molecular readouts. Regardless of the strategy, the performance of these tools remains modest. Macroscopic features of cancers are among the oldest options to investigate a tumor. Surprisingly, data on the potential prognostic value of macroscopy in HCC are strikingly scarce and likely underexploited.
Recent data using artificial intelligence (AI) on HCC histology (microscopy) have revealed promising results, with important clinical applications including diagnosis but also for the prediction of response to specific treatments. Of note, AI on macroscopy has not been investigated, to date.
We aim to submit pictures of liver cancers specimen after surgical resection or liver transplantation to AI models to generate algorithms allowing to establish prognosis for overall survival (OS), disease-free survival (DFS) and recurrence after surgery in HCC in a large-scale study including centers from North America, Europe and Asia.