Publications

My work focuses on machine learning for 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. Because obtaining ground-truth annotations is time-consuming, I am in particular interested in learning scenarios where few labels are available, such as:

  • multiple instance learning
  • transfer learning or domain adaptation
  • crowdsourcing

You can read more about these topics on my research page. My publications are below and also on Google Scholar.

Preprints

Cheplygina, V., Perez-Rovira, A., Kuo, W., Tiddens, H. A. W. M., & de Bruijne, M. (2020) Crowdsourcing Airway Annotations in Chest Computed Tomography Images. arXiv | Github

El Jurdi, R., Petitjean, C., Honeine, P.,  Cheplygina, V. & Abdallah, F. (2020) High-level prior-based loss functions for medical image segmentation: a survey. arXiv.

Hesse, L. S., Jong, P. A. D., Pluim, J.P. W. & Cheplygina, V. (2020). Primary tumor origin classification of lung nodules in spectral CT using transfer learning. arXiv.

Raumanns, R., Kontar, E., Schouten, G., & Cheplygina, V. (2020) Multi-task learning with crowdsourced features improves skin lesion diagnosis.  arXiv preprint arXiv:2004.14745. arXiv

2020

Abbasi-Sureshjani, S., Raumanns, R., Michels, B. E. J., Schouten, G., & Cheplygina, V. (2020). Risk of Training Diagnostic Algorithms on Data with Demographic Bias. MICCAI LABELS 2020. arXiV
van Sonsbeek, T., & Cheplygina, V. (2020). Predicting Scores of Medical Imaging Segmentation Methods with Meta-Learning. MICCAI LABELS 2020. arXiV | Github
Ørting, S., Doyle, A., van Hilten, A., Hirth, M. , Inel, O., Madan, C. R., Mavridis, P., Spiers, H. & Cheplygina, V. (2019). A survey of crowdsourcing in medical image analysis. Accepted in Human Computation Journal. arXiV | Data
Cheplygina, V., Hermans, F., Albers, C., Bielczyk, N., & Smeets, I. (2020). Ten simple rules for getting started on Twitter as a scientist. PLoS Computational Biology 16(2): e1007513. Publisher (Open access)
Bielczyk, N.,  et. al. (2020). Effective Self-Management for Early Career Researchers in the Natural and Life Sciences. Neuron, 106(2), 212-217. Publisher

2019

Cheplygina, Veronika, Marleen de Bruijne, and Josien P W Pluim. “Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis.” Medical Image Analysis, in press. arXiV | Publisher | Data
Cheplygina, Veronika. “Cats or CAT scans: transfer learning from natural or medical image source datasets?”. Current Opinion in Biomedical Engineering, in press, 2019.  arXiv | Publisher

2018

Peña, Isabel Pino, Veronika Cheplygina, Sofia Paschaloudi, Morten Vuust, Jesper Carl, Ulla Møller Weinreich, Lasse Riis Østergaard, and Marleen de Bruijne. “Automatic Emphysema Detection using Weakly Labeled HRCT Lung Images.” PLoS ONE, 13(10): e0205397, 2018. arXiV | Publisher | Data | Code
Cheplygina, Veronika and Josien P W Pluim. “Crowd disagreement about medical images is informative”.  Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis (MICCAI LABELS), pp. 105-111. Springer, 2018. arXiv | Publisher | Data
Ørting, Silas, Jens Petersen, Veronika Cheplygina, Laura H. Thomsen, Mathilde M W Wille, and Marleen de Bruijne. Feature learning based on visual similarity triplets in medical image analysis: A case study of emphysema in chest CT scans. Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis (MICCAI LABELS), pp. 140-149. Springer, 2018. arXiV
Carbonneau, Marc-André, Veronika Cheplygina, Eric Granger, and Ghyslain Gagnon. “Multiple instance learning: A survey of problem characteristics and applications.” Pattern Recognition (2018). arXiV | Publisher | Code

2017

Cheplygina, Veronika, Pim Moeskops, Mitko Veta, Behdad Dashtbozorg, and Josien P W Pluim. “Exploring the similarity of medical imaging classification problems.” In Intravascular Imaging and Computer Assisted Stenting, and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis (MICCAI LABELS), pp. 59-66. Springer, 2017. arXiV | Publisher
Ørting, Silas Nyboe, Veronika Cheplygina, Jens Petersen, Laura H. Thomsen, Mathilde M W Wille, and Marleen de Bruijne. “Crowdsourced emphysema assessment.” In Intravascular Imaging and Computer Assisted Stenting, and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis (MICCAI LABELS), pp. 126-135. Springer, 2017. PDF | Publisher
Cheplygina, Veronika, Isabel Pino Pena, Jesper Holst Pedersen, David A. Lynch, Lauge Sorensen, and Marleen de Bruijne. “Transfer learning for multi-center classification of chronic obstructive pulmonary disease.” IEEE Journal of Biomedical and Health Informatics (2017). arXiV | Publisher

2016

Cheplygina, Veronika, David MJ Tax, and Marco Loog. “Dissimilarity-based ensembles for multiple instance learning.” IEEE transactions on neural networks and learning systems 27, no. 6 (2016): 1379-1391. arXiV | Publisher | MATLAB Code
Cheplygina, Veronika, Adria Perez-Rovira, Wieying Kuo, Harm AWM Tiddens, and Marleen de Bruijne. “Early experiences with crowdsourcing airway annotations in chest CT.” In Deep Learning and Data Labeling for Medical Applications, pp. 209-218. Springer, 2016. arXiV | Publisher | Poster
Tax, David MJ, Veronika Cheplygina, Robert PW Duin, and Jan van de Poll. “The Similarity Between Dissimilarities.” In Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR), pp. 84-94. Springer, 2016. PDF | Publisher
Cheplygina, Veronika, Annegreet van Opbroek, M. Arfan Ikram, Meike W. Vernooij, and Marleen de Bruijne. “Asymmetric similarity-weighted ensembles for image segmentation.” In Biomedical Imaging (ISBI), 2016 IEEE 13th International Symposium on, pp. 273-277. IEEE, 2016. PDF | Publisher | Blog Post

2015

Cheplygina, Veronika. “Dissimilarity-Based Multiple Instance Learning.” PhD thesis, Delft University of Technology (2015). PDF | Cover | Online
Cheplygina, Veronika, Lauge Sørensen, David MJ Tax, Marleen de Bruijne, and Marco Loog. “Label stability in multiple instance learning.” In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 539-546. Springer, 2015. arXiV | Publisher | PosterVideo | Blog Post |
Cheplygina, Veronika, and David MJ Tax. “Characterizing multiple instance datasets.” In International Workshop on Similarity-Based Pattern Recognition, pp. 15-27. Springer, 2015. PDF | Publisher | Poster | Slides
Cheplygina, Veronika, David MJ Tax, and Marco Loog. “On classification with bags, groups and sets.” Pattern Recognition Letters 59 (2015): 11-17. arXiV | Publisher
Alpaydın, Ethem, Veronika Cheplygina, Marco Loog, and David MJ Tax. “Single-vs. multiple-instance classification.” Pattern Recognition 48, no. 9 (2015): 2831-2838. PDF | Publisher
Cheplygina, Veronika, David MJ Tax, and Marco Loog. “Multiple instance learning with bag dissimilarities.” Pattern Recognition 48, no. 1 (2015): 264-275. arXiV | Publisher | MATLAB Code

2014

Cheplygina, Veronika, David MJ Tax, Marco Loog, and Aasa Feragen. “Network-guided group feature selection for classification of autism spectrum disorder.” In International Workshop on Machine Learning in Medical Imaging, pp. 190-197. Springer, 2014. PDF | Publisher

Cheplygina, Veronika, Lauge Sørensen, David MJ Tax, Jesper Holst Pedersen, Marco Loog, and Marleen de Bruijne. “Classification of COPD with multiple instance learning.” In Pattern Recognition (ICPR), 2014 22nd International Conference on, pp. 1508-1513. IEEE, 2014. arXiV | Publisher

2013

Plasencia-Calaña, Yenisel, Veronika Cheplygina, Robert PW Duin, Edel B. García-Reyes, Mauricio Orozco-Alzate, David MJ Tax, and Marco Loog. “On the informativeness of asymmetric dissimilarities.” In International Workshop on Similarity-Based Pattern Recognition, pp. 75-89. Springer, Berlin, Heidelberg, 2013. PDF

Cheplygina, Veronika, David MJ Tax, and Marco Loog. “Combining instance information to classify bags.” In International Workshop on Multiple Classifier Systems, pp. 13-24. Springer, Berlin, Heidelberg, 2013. PDF | Publisher

2012

Cheplygina, Veronika, David MJ Tax, and Marco Loog. “Does one rotten apple spoil the whole barrel?.” In Pattern Recognition (ICPR), 2012 21st International Conference on, pp. 1156-1159. IEEE, 2012. PDF | Publisher

Lee, Wan-Jui, Veronika Cheplygina, David MJ Tax, Marco Loog, and Robert PW Duin. “Bridging structure and feature representations in graph matching.” International Journal of Pattern Recognition and Artificial Intelligence 26, no. 05 (2012): 1260005. PDF

Cheplygina, Veronika, David MJ Tax, and Marco Loog. “Class-dependent dissimilarity measures for multiple instance learning.” In Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR), pp. 602-610. Springer, Berlin, Heidelberg, 2012. PDF

2011

Cheplygina, Veronika, and David MJ Tax. “Pruned random subspace method for one-class classifiers.” In International Workshop on Multiple Classifier Systems, pp. 96-105. Springer, Berlin, Heidelberg, 2011. PDF | Publisher

Tax, David MJ, Marco Loog, Robert PW Duin, Veronika Cheplygina, and Wan-Jui Lee. “Bag dissimilarities for multiple instance learning.” In International Workshop on Similarity-Based Pattern Recognition, pp. 222-234. Springer, Berlin, Heidelberg, 2011. PDF | Publisher

2010

Cheplygina, Veronika, and David MJ Tax. “Random subspace method for one-class classifiers.” Master’s thesis, Delft University of Technology, 2010. PDF

%d bloggers like this: