Assessing the ovarian cancer microenvironment with optical coherence tomography and artificial intelligence
Ovarian cancer is one of the deadliest gynaecological conditions in the developed world, as it is often detected late into progression. Efforts to improve surgical and chemotherapeutic approaches have only made marginal improvements to patient outcomes over the past 30 years, but there remains potential within immunotherapeutic approaches. Understanding the tumor microenvironment, and particularly the immune response to cancers and pre-cancers, is critical to selecting appropriate therapies. A novel dataset of volumetric structural imaging of ex vivo fallopian tubes, the origin of the most prevalent ovarian cancers, has been collected with corresponding histopathology. This work explores whether there are imaging biomarkers associated with immune response such as t-cell infiltration in the tumor microenvironment that can be distinguished using deep learning vision models.