Improving PIPAC therapy responses in cancer patients with peritoneal metastases using robust computer vision

Peritoneal metastasis (PM) occurs in advanced stages of ovarian and gastro-intestinal cancers. Patients with PM have a poor prognosis and their quality of life is severely compromised. Pressurized intraperitoneal aerosol chemotherapy (PIPAC) is a promising treatment option but responses are hard to predict. Indeed, standard clinical, microscopic, and medical imaging modalities are currently limited in their potential to quantify PM and evaluate PIPAC responses. The goal of this research project is to tackle both problems by bringing together expertise in cancer oncology and artificial intelligence. Specifically, we will develop novel computer vision techniques, based on deep machine learning, to quantify PM and evaluate PIPAC responses in a reproducible manner, trading off data requirements with computational complexity, model effectiveness, and model robustness.