Project 2.1 - Weakly Labeled Learning

We focus on deep learning with large amounts of images that are only weakly labeled (e.g. only overall diagnosis or treatment outcome is available). We develop techniques that exploit a small set of images with detailed annotations and a large pool of weakly or completely unlabeled data. We exploit shared representations between learning tasks with different localization levels and use active learning where medical experts are asked for feedback on automatically selected cases.

Project Leader

Eindhoven University of Technology
Prof.dr. Josien Pluim Eindhoven University of Technology j.pluim@tue.nl

Co-Applicants

Erasmus Medical Center
Dr. Marleen de Bruijne Erasmus Medical Center marleen.debruijne@erasmusmc.nl
Eindhoven University of Technology
Dr. Mitko Veta Eindhoven University of Technology M.Veta@tue.nl

Researchers

Eindhoven University of Technology
Suzanne Wetstein Eindhoven University of Technology s.c.wetstein@tue.nl
Eindhoven University of Technology
Friso Heslinga Eindhoven University of Technology f.g.heslinga@tue.nl
Erasmus Medical Center
Gerda Bortsova Erasmus Medical Center g.bortsova@erasmusmc.nl

Publications