MIMRTL team members just published a new article in the Journal of Digital Imaging entitled ‘Robustifying Deep Networks for Medical Image Segmentation’.
This study investigated the robustness of UNets for brain tumor segmentation, in subjects with low- and high-grade gliomas, with respect to nearly unnoticeable adversarial perturbations, and suggest new methods to make these networks more robust to such perturbations.
See the article here!