Weakly-supervised

Weakly-Supervised Localization and Classification of Proximal Femur Fractures

Reduce the strong data requirements in data-driven approaches of medical problems.

We want to investigate different methodologies to face typical challenges in medical datasets. Namely, class-imbalance and considering datasets with a reduced number of annotations. We plan to investigate alternatives to supervised learning.

Automatic Classification of Proximal Femur Fractures Based on Attention Models