Prostate Cancer (PCa) is the sixth most common cancer among men worldwide. Gleason score is a strong prognostic predictor for this cancer but challenging to evaluate because of the large degree of heterogeneity in the cellular and glandular patterns associated with each Gleason grade, leading to significant inter-observer variability, even among expert pathologists.
This project aims at the automatic Gleason grading of prostate cancer using deep learning methods from H&E-stained histopathology images on the basis of publicly available data provided during an international challenge (https://gleason2019.grand-challenge.org/Home/). An important aspect of this project will be to analyze how algorithm performance is evaluated for this type of problem where the ground truth is not perfectly established.
Prerequisite:
programming (Python), Machine Learning, Image analysis
Promoter:
Prof. Christine Decaestecker (cdecas@ulb.ac.be)
Contact:
Adrien Foucart (afoucart@ulb.ac.be)