V
Veronika Cheplygina
Researcher at Eindhoven University of Technology
Publications - 80
Citations - 2198
Veronika Cheplygina is an academic researcher from Eindhoven University of Technology. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 18, co-authored 68 publications receiving 1314 citations. Previous affiliations of Veronika Cheplygina include Erasmus University Rotterdam & Delft University of Technology.
Papers
More filters
Journal ArticleDOI
Ten simple rules for failing successfully in academia
TL;DR: In this article , the authors provide several strategies for learning from and dealing with failure instead of ignoring it, while still taking into account individual differences between academics, and these simple rules allow academics to further develop their own strategies for failing successfully.
A Surprisingly Effective Perimeter-based Loss for Medical Image Segmentation
Rosana El Jurdi,Caroline Petitjean,Paul Honeine,Veronika Cheplygina,Veronika Cheplygina,Fahed Abdallah +5 more
TL;DR: In this paper, the authors proposed a novel loss constraint that optimizes the perimeter length of the segmented object relative to the ground-truth segmentation, which can take into account border irregularities within organs while still being efficient.
Posted Content
How I failed machine learning in medical imaging -- shortcomings and recommendations
TL;DR: In this article, the authors reviewed several problems related to choosing datasets, methods, evaluation metrics, and publication strategies and provided a broad range of recommendations on how to further these address problems in the future.
Posted Content
Predicting Scores of Medical Imaging Segmentation Methods with Meta-Learning
TL;DR: In this paper, the authors investigate meta-learning for segmentation across ten datasets of different organs and modalities and propose four ways to represent each dataset by meta-features: one based on statistical features of the images and three are based on deep learning features.
Book ChapterDOI
Feature learning based on visual similarity triplets in medical image analysis : A case study of emphysema in chest CT scans
Silas Nyboe Ørting,Jens Petersen,Veronika Cheplygina,Laura H. Thomsen,Mathilde M. W. Wille,Marleen de Bruijne,Marleen de Bruijne +6 more
TL;DR: To the authors' knowledge, this is the first medical image application where similarity triplets has been used to learn a feature representation that can be used for embedding unseen test images in supervised feature learning using convolutional neural networks.