My research focuses on applied and theoretical machine learning for its application to biomedical sciences. I am interested in methods for the responsible use of machine learning in biomedical imaging, including the development algorithms that are robust, interpretable and fair. Moreover, my work leverages data-driven priors for biomedical image processing and computer vision problems, such as detection, classification, segmentation and image reconstruction and estimation. My contributions typically involve by the deployment of parsimonious priors for tasks in medical imaging, both analytically and in a data-driven manner, enabling the regularization of otherwise ill-posed problems. My group is interested in the development of interpretable machine learning predictors, which could be used for the discovery of biomarkers for disease prognosis and treatment response.
