Institute of Astronomy

Quantifying the tumor vasculature environment using deep learning

SpeakerTalk DateTalk Series
Dr Tristan Whitmarsh (University of Cambridge)16 November 2022Institute of Astronomy Seminars


The tumor vascular density assessed from CD-31 immunohistochemistry (IHC) images has previously been shown to have prognostic value in breast cancer. Current methods to measure the vascular density, however, are time-consuming, suffer from a high inter-observer variability and are limited in describing the complex tumor vasculature morphometry. We therefore propose a method for automatically measuring a range of vascular parameters from CD-31 IHC images, which together provide a detailed description of the vasculature morphology.


Presentation unavailable