Leveraging weak complementary labels to improve semantic segmentation of hepatocellular carcinoma and cholangiocarcinoma in H&E-stained slides

no code implementations • 3 Feb 2023 • Miriam Hägele, Johannes Eschrich, Lukas Ruff, Maximilian Alber, Simon Schallenberg, Adrien Guillot, Christoph Roderburg, Frank Tacke, Frederick Klauschen

Motivated by the medical application, we demonstrate for general segmentation tasks that including additional patches with solely weak complementary labels during model training can significantly improve the predictive performance and robustness of a model.

Segmentation Semantic Segmentation +1