Projects
I focus my research efforts on developing AI methods that answer specific needs and constraints of the medical imaging data (e.g., low-data regime, data biases, lack of labeling data) leveraging multiple modalities, clinical knowledge and (healthy) unlabeled data. From a methodological perspective, my research follows three main axes:
- Modeling medical knowledge and anatomy and integrating it into machine learning models.
- Learning compact, relevant and explanatory representations of anatomical imaging data.
- Transferring anatomical representations between domains (i.e., different modalities, data-sets, populations) to increase downstream performance (e.g., segmentation, classification, regres- sion) or to discover new pathological biomarkers.
Here, you can find a list of (some of) my current and past projects
