2 papers
eess.IV2023
Non-Redundant Combination of Hand-Crafted and Deep Learning Radiomics: Application to the Early Detection of Pancreatic Cancer
Rebeca Vétil, Clément Abi-Nader, Alexandre Bône +4
We address the problem of learning Deep Learning Radiomics (DLR) that are not redundant with Hand-Crafted Radiomics (HCR). To do so, we extract DLR features using a VAE while enfor…
cs.CV2023
Weakly-supervised positional contrastive learning: application to cirrhosis classification
Emma Sarfati, Alexandre Bône, Marc-Michel Rohé +2
Large medical imaging datasets can be cheaply and quickly annotated with low-confidence, weak labels (e.g., radiological scores). Access to high-confidence labels, such as histolog…