There is information in negative results - not only of algorithms, but also unsuccessful papers, grants or attempts at work-life balance. We could all learn from sharing such failures with each other.
Veronika Cheplygina is an assistant professor at the research group Medical Image Analysis of the department of Biomedical Engineering at Eindhoven University of Technology. She works on machine learning algorithms for medical image analysis, such as in detecting the chronic lung disease COPD in chest computed tomography scans. Her research also concerns more general aspects of machine learning, such as multiple instance learning, transfer learning, learning with similarities and learning from crowdsourced labels.
Veronika Cheplygina studied Media & Knowledge Engineering at Delft University of Technology, where she obtained her MSc in 2010. She then started PhD research at the Pattern Recognition Laboratory of the same university and obtained her doctorate in 2015 with her thesis "Dissimilarity-Based Multiple Instance Learning". In 2013, she was a Visiting Researcher at the Machine Learning and Computational Biology group at MPI Intelligent Systems, Tübingen, Germany. In 2015 and 2016, she was a postdoctoral researcher at the Biomedical Imaging Group Rotterdam (The Netherlands, part of the Erasmus Medical Center). In 2017, she was appointed assistant professor at the Medical Image Analysis group of Eindhoven University of Technology (TU/e, The Netherlands).
Crowd disagreement of medical images is informativearXiv (2018)
Feature learning based on visual similarity triplets in medical image analysisarXiv (2018)
Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysisarXiv (2018)
Multiple instance learning: a survey of problem characteristics and applicationsPattern Recognition (2018)
Exploring the similarity of medical imaging classification problems2nd International Workshop on Large-Scale Annotation of Biomedical Data and Expert Label Synthesis, (LABELS 2017), 10-14 September 2017, Quebec City, Canada (2017)
- DBL Image Analysis for cancer risk assessment
- Medical image analysis
No ancillary activities