About

I am an assistant professor at the Medical Image Analysis group at Eindhoven University of Technology. Before this I was a postdoc at the Biomedical Imaging Group Rotterdam, Erasmus Medical Center. Before that, I was a PhD student at the Pattern Recognition Laboratory, Delft University of Technology, and a visiting PhD student at the Max Planck Institute for Intelligent Systems in Tuebingen, Germany.

My research focuses on machine learning in medical image analysis. Machine learning algorithms learn from examples in order to make predictions about novel data. For example, by learning from medical scans with annotated abnormalities, the algorithms can detect abnormalities in previously unseen patients. In particular I focus on scenarios where not enough annotated data is available, such as multiple instance learning, transfer learning and crowdsourcing. See my research/publications page for more details.

Another project is my blog, where I try to improve the experiences that others have in academia by sharing my own experiences as a PhD student, postdoc, and now faculty. Some popular posts are:

I also like trivia quizzes, beer and cats.

If any of this sounds like your thing, get in touch!

Events

20 December 2017: Invited talk at TiCC colloquium, Tilburg University, The Netherlands

13 November 2017: Invited talk at Predictive Radiology in Precision Medicine workshop, Lausanne University Hospital, Switzerland

10-14 September 2017: MICCAI 2017, LABELS workshop in Quebec City, Canada

June 2017: Talk on label stability in multiple instance learning at Benelearn 2017

Event archive

Recent news

We won the Lorentz-eScience Competition with our proposal for the “Crowdsourcing for Medical Image Analysis” workshop. This is an initiative together with Lora Aroyo (VU), Alessandro Bozzon (Delft University of Technology), Danna Gurari (University of Texas at Austin) and Zoltán Szlavik (IBM Center for Advanced Studies Benelux).  Read more about it on the TU/e website

July 2017: Two papers accepted at LABELS 2017: meta-learning in medical image analysis and crowdsourcing in chest CT images

January 2017: New preprint on classification of COPD now available on arXiV

December 2016: Our survey on multiple instance learning is now available on arXiv. Hats off to Marc-André Carbonneau who did most of the work!

December 2016: My tudelft.nl and erasmusmc.nl email addresses will soon no longer be active, please use v.cheplygina[at]tue.nl instead

Read all news here

Leave a Reply