Veronika Cheplygina

Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.

? Tutorial for this page

Demo Data from SIGIR 2026 / reviewers in the wild / expert

dblp:91/10084 · DBLP profile ↗

← Back

18ranked-venue papers

9as first author

6since 2021 · last 2024

0000-0003-0176-9324ORCID · verified

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 12 · 5 first-author · 4 since 2021Applied, interdisciplinary, general and emerging computing · 6 · 4 first-author · 2 since 2021Graphics, computer vision, multimedia, augmented reality and games · 5 · 3 first-author · 2 since 2021Databases, data management, data science and information retrieval · 1 · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Interdisciplinary, comprehensive, and emerging computing 2 papers		Medical and health informatics · 100%
Artificial intelligence 2 papers		Deep learning architectures and training · 100%
Databases, data mining, and information retrieval 2 papers		Machine learning and data management · 100%

Topics — the 5 heaviest of 7, each with the papers that count most for it

Topic	Weight	Papers	Last	Evidence papers
Medical and health informatics › medical imaging › medical image data management medical imaging dataset curation	0.8	1	2024	Copycats: the many lives of a publicly available medical imaging dataset · NeurIPS 2024
Medical and health informatics › medical imaging medical image analysis	0.7	1	2023	Why is the Winner the Best? · CVPR 2023
Machine learning and data management predictive maintenance	0.6	1	2022	Predicting Bearings Degradation Stages for Predictive Maintenance in the Pharmaceutical Industry · KDD 2022
Machine learning and data management data management for machine learning	0.2	1	2024	Copycats: the many lives of a publicly available medical imaging dataset · NeurIPS 2024
Machine learning › Deep learning architectures and training autoencoder	0.2	1	2022	Predicting Bearings Degradation Stages for Predictive Maintenance in the Pharmaceutical Industry · KDD 2022

Methods — techniques the papers use, named apart from their topics

metadata analysis · 1.5dataset audit · 1.5statistical analysis · 1.3k-means · 1.1autoencoder · 1.1

Year	Publication	Venue	Position
2024	Confidence Intervals Uncovered: Are We Ready for Real-World Medical Imaging AI? Evangelia Christodoulou, Annika Reinke, Rola Houhou, Piotr Kalinowski, Selen Erkan, Carole H. Sudre, Ninon Burgos, Sofiène Boutaj, Sophie Loizillon, Maëlys Solal, Nicola Rieke, Veronika Cheplygina, Michela Antonelli, Leon D. Mayer, Minu Tizabi, Manuel Jorge Cardoso, Amber L. Simpson, Paul F. Jaeger, Annette Kopp-Schneider, Gaël Varoquaux, Olivier Colliot, Lena Maier-Hein	MICCAI (10)	12
2024	Copycats: the many lives of a publicly available medical imaging dataset abstract Medical Imaging (MI) datasets are fundamental to artificial intelligence in healthcare. The accuracy, robustness, and fairness of diagnostic algorithms depend on the data (and its quality) used to train and evaluate the models. MI datasets used to be proprietary, but have become increasingly available to the public, including on community-contributed platforms (CCPs) like Kaggle or HuggingFace. While open data is important to enhance the redistribution of data's public value, we find that the current CCP governance model fails to uphold the quality needed and recommended practices for sharing, documenting, and evaluating datasets. In this paper, we conduct an analysis of publicly available machine learning datasets on CCPs, discussing datasets' context, and identifying limitations and gaps in the current CCP landscape. We highlight differences between MI and computer vision datasets, particularly in the potentially harmful downstream effects from poor adoption of recommended dataset management practices. We compare the analyzed datasets across several dimensions, including data sharing, data documentation, and maintenance. We find vague licenses, lack of persistent identifiers and storage, duplicates, and missing metadata, with differences between the platforms. Our research contributes to efforts in responsible data curation and AI algorithms for healthcare. Amelia Jiménez-Sánchez, Natalia Rozalia Avlona, Dovile Juodelyte, Théo Sourget, Caroline Vang-Larsen, Anna Rogers, Hubert Dariusz Zajac, Veronika Cheplygina	NeurIPS	8
2023	Why is the Winner the Best? abstract International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work. Matthias Eisenmann, Annika Reinke, Vivienn Weru, Minu Tizabi, Fabian Isensee, Tim Adler, Sharib Ali, Vincent Andrearczyk, Marc Aubreville, Ujjwal Baid, Spyridon Bakas, Niranjan Balu, Sophia Bano, Jorge Bernal, Sebastian Bodenstedt, Alessandro Casella, Veronika Cheplygina, Marie Daum, Marleen de Bruijne, Adrien Depeursinge, Reuben Dorent, Jan Egger, David Gage Ellis, Sandy Engelhardt, Melanie Ganz-Benjaminsen, Noha M. Ghatwary, Gabriel Girard, Patrick Godau, Anubha Gupta, Lasse Hansen, Kanako Harada, Mattias P. Heinrich, Nicholas Heller, Alessa Hering, Arnaud Huaulmé, Pierre Jannin, A. Emre Kavur, Oldrich Kodym, Michal Kozubek 0001, Jianning Li 0002, Hongwei Li 0004, Jun Ma 0016, Carlos Martín-Isla, Bjoern Menze, J. Alison Noble, Valentin Oreiller, Nicolas Padoy, Sarthak Pati, Kelly Payette, Tim Rädsch, Jonathan Rafael-Patino, Vivek Singh Bawa, Stefanie Speidel, Carole H. Sudre, Kimberlin M. H. van Wijnen, Martin Wagner 0001, D. Wei, Amine Yamlahi, Moi Hoon Yap, C. Yuan, Maximilian Zenk, A. Zia, David Zimmerer, Dogu Baran Aydogan, Binod Bhattarai, Louise Bloch, Raphael Brüngel, J. Cho, C. Choi, Qi Dou 0001, Ivan Ezhov, Christoph M. Friedrich, C. Fuller, Rebati Raman Gaire, Adrian Galdran, Álvaro García-Faura, Maria Grammatikopoulou, S. Hong, Mostafa Jahanifar, I. Jang, Abdolrahim Kadkhodamohammadi, I. Kang, Florian Kofler, S. Kondo, Hugo J. Kuijf, M. Luu, Tomaz Martincic, Pedro Morais, Mohamed A. Naser, Bruno Oliveira 0002, David Owen 0001, S. Pang, Szymon Plotka, Élodie Puybareau, Nasir M. Rajpoot, K. Ryu, Numan Saeed, Adam J. Shephard, Dejan Stepec, Ronast Subedi, Guillaume Tochon, Helena R. Torres, Hélène Urien, João L. Vilaça, Kareem A. Wahid, Benedikt Wiestler, Marek Wodzinski, F. Xia, J. Xie, Z. Xiong, Sen Yang 0006, Klaus H. Maier-Hein, Paul F. Jaeger, Annette Kopp-Schneider, Lena Maier-Hein	CVPR	17
2022	Predicting Bearings Degradation Stages for Predictive Maintenance in the Pharmaceutical Industry abstract In the pharmaceutical industry, the maintenance of production machines must be audited by the regulator. In this context, the problem of predictive maintenance is not when to maintain a machine, but what parts to maintain at a given point in time. The focus shifts from the entire machine to its component parts and prediction becomes a classification problem. In this paper, we focus on rolling-elements bearings and we propose a framework for predicting their degradation stages automatically. Our main contribution is a k-means bearing lifetime segmentation method based on high-frequency bearing vibration signal embedded in a latent low-dimensional subspace using an AutoEncoder. Given high-frequency vibration data, our framework generates a labeled dataset that is used to train a supervised model for bearing degradation stage detection. Our experimental results, based on the publicly available FEMTO Bearing run-to-failure dataset, show that our framework is scalable and that it provides reliable and actionable predictions for a range of different bearings. Dovile Juodelyte, Veronika Cheplygina, Therese Graversen, Philippe Bonnet	KDD	2
2022	Ten simple rules for failing successfully in academia abstract Failure is an integral part of life and by extension academia. At the same time, failure is often ignored, with potentially negative consequences both for the science and the scientists involved. This article provides several strategies for learning from and dealing with failure instead of ignoring it. Hopefully, our recommendations are widely applicable, while still taking into account individual differences between academics. These simple rules allow academics to further develop their own strategies for failing successfully in academia. Stefan Gaillard, Tara van Viegen, Michele Veldsman, Melanie I. Stefan, Veronika Cheplygina	PLoS Comput. Biol.	5
2021	High-level prior-based loss functions for medical image segmentation: A survey abstract Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various imaging modalities and tasks. Despite early success, segmentation networks may still generate anatomically aberrant segmentations, with holes or inaccuracies near the object boundaries. To mitigate this effect, recent research works have focused on incorporating spatial information or prior knowledge to enforce anatomically plausible segmentation. If the integration of prior knowledge in image segmentation is not a new topic in classical optimization approaches, it is today an increasing trend in CNN based image segmentation, as shown by the growing literature on the topic. In this survey, we focus on high level prior, embedded at the loss function level. We categorize the articles according to the nature of the prior: the object shape, size, topology, and the inter-regions constraints. We highlight strengths and limitations of current approaches, discuss the challenge related to the design and the integration of prior-based losses, and the optimization strategies, and draw future research directions. Rosana El Jurdi, Caroline Petitjean, Paul Honeine, Veronika Cheplygina, Fahed Abdallah	Comput. Vis. Image Underst.	4
2020	Ten simple rules for getting started on Twitter as a scientist abstract Twitter is one of the most popular social media platforms, with over 320 million active users as of February 2019. Twitter users can enjoy free content delivered by other users whom they actively decide to follow. However, unlike in other areas where Twitter is used passively (e.g., to follow influential figures and/or information agencies), in science it can be used in a much more active, collaborative way: to ask for advice, to form new bonds and scientific collaborations, to announce jobs and find employees, to find new mentors and jobs. This is particularly important in the early stages of a scientific career, during which lack of collaboration or delayed access to information can have the most impact. For these reasons, using Twitter appropriately [1] can be more than just a social media activity; it can be a real career incubator in which researchers can develop their professional circles, launch new research projects and get helped by the community at various stages of the projects. Twitter is a tool that facilitates decentralization in science; you are able to present yourself to the community, to develop your personal brand, to set up a dialogue with people inside and outside your research field and to create or join professional environment in your field without mediators such as your direct boss. This article is written by a group of researchers who have a strong feeling that they have personally benefited from using Twitter, both research-wise and network-wise. We (@DrVeronikaCH, @Felienne, @CaAl, @nbielczyk_neuro, @ionicasmeets) share our personal experience and advice in the form of ten simple rules, and we hope that this material will help a number of researchers who are planning to start their journey on Twitter to take their first steps and advance their careers using Twitter. Veronika Cheplygina, Felienne Hermans, Casper J. Albers, Natalia Z. Bielczyk, Ionica Smeets	PLoS Comput. Biol.	1
2019	Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis Veronika Cheplygina, Marleen de Bruijne, Josien P. W. Pluim	Medical Image Anal.	1
2018	Multiple instance learning: A survey of problem characteristics and applications Marc-André Carbonneau, Veronika Cheplygina, Eric Granger, Ghyslain Gagnon	Pattern Recognit.	2
2018	Transfer Learning for Multicenter Classification of Chronic Obstructive Pulmonary Disease abstract Chronic obstructive pulmonary disease (COPD) is a lung disease that can be quantified using chest computed tomography scans. Recent studies have shown that COPD can be automatically diagnosed using weakly supervised learning of intensity and texture distributions. However, up till now such classifiers have only been evaluated on scans from a single domain, and it is unclear whether they would generalize across domains, such as different scanners or scanning protocols. To address this problem, we investigate classification of COPD in a multicenter dataset with a total of 803 scans from three different centers, four different scanners, with heterogenous subject distributions. Our method is based on Gaussian texture features, and a weighted logistic classifier, which increases the weights of samples similar to the test data. We show that Gaussian texture features outperform intensity features previously used in multicenter classification tasks. We also show that a weighting strategy based on a classifier that is trained to discriminate between scans from different domains can further improve the results. To encourage further research into transfer learning methods for the classification of COPD, upon acceptance of this paper we will release two feature datasets used in this study on http://bigr.nl/research/projects/copd. Veronika Cheplygina, Isabel Pino Peña, Jesper Johannes Holst Pedersen, David A. Lynch, Lauge Sørensen, Marleen de Bruijne	IEEE J. Biomed. Health Informatics	1
2016	Dissimilarity-Based Ensembles for Multiple Instance Learning abstract In multiple instance learning, objects are sets (bags) of feature vectors (instances) rather than individual feature vectors. In this paper, we address the problem of how these bags can best be represented. Two standard approaches are to use (dis)similarities between bags and prototype bags, or between bags and prototype instances. The first approach results in a relatively low-dimensional representation, determined by the number of training bags, whereas the second approach results in a relatively high-dimensional representation, determined by the total number of instances in the training set. However, an advantage of the latter representation is that the informativeness of the prototype instances can be inferred. In this paper, a third, intermediate approach is proposed, which links the two approaches and combines their strengths. Our classifier is inspired by a random subspace ensemble, and considers subspaces of the dissimilarity space, defined by subsets of instances, as prototypes. We provide insight into the structure of some popular multiple instance problems and show state-of-the-art performances on these data sets. Veronika Cheplygina, David M. J. Tax, Marco Loog	IEEE Trans. Neural Networks Learn. Syst.	1
2015	Label Stability in Multiple Instance Learning Veronika Cheplygina, Lauge Sørensen, David M. J. Tax, Marleen de Bruijne, Marco Loog	MICCAI (1)	1
2015	Single- vs. multiple-instance classification Ethem Alpaydin, Veronika Cheplygina, Marco Loog, David M. J. Tax	Pattern Recognit.	2
2015	Multiple instance learning with bag dissimilarities Veronika Cheplygina, David M. J. Tax, Marco Loog	Pattern Recognit.	1
2015	On classification with bags, groups and sets Veronika Cheplygina, David M. J. Tax, Marco Loog	Pattern Recognit. Lett.	1
2014	Classification of COPD with Multiple Instance Learning abstract Chronic obstructive pulmonary disease (COPD) is a lung disease where early detection benefits the survival rate. COPD can be quantified by classifying patches of computed tomography images, and combining patch labels into an overall diagnosis for the image. As labeled patches are often not available, image labels are propagated to the patches, incorrectly labeling healthy patches in COPD patients as being affected by the disease. We approach quantification of COPD from lung images as a multiple instance learning (MIL) problem, which is more suitable for such weakly labeled data. We investigate various MIL assumptions in the context of COPD and show that although a concept region with COPD-related disease patterns is present, considering the whole distribution of lung tissue patches improves the performance. The best method is based on averaging instances and obtains an AUC of 0.742, which is higher than the previously reported best of 0.713 on the same dataset. Using the full training set further increases performance to 0.776, which is significantly higher (DeLong test) than previous results. Veronika Cheplygina, Lauge Sørensen, David M. J. Tax, Jesper Johannes Holst Pedersen, Marco Loog, Marleen de Bruijne	ICPR	1
2012	Does one rotten apple spoil the whole barrel? Veronika Cheplygina, David M. J. Tax, Marco Loog	ICPR	1
2012	Bridging Structure and Feature Representations in Graph Matching abstract Structures and features are opposite approaches in building representations for object recognition. Bridging the two is an essential problem in pattern recognition as the two opposite types of information are fundamentally different. As dissimilarities can be computed for both the dissimilarity representation can be used to combine the two. Attributed graphs contain structural as well as feature-based information. Neglecting the attributes yields a pure structural description. Isolating the features and neglecting the structure represents objects by a bag of features. In this paper we will show that weighted combinations of dissimilarities may perform better than these two extremes, indicating that these two types of information are essentially different and strengthen each other. In addition we present two more advanced integrations than weighted combining and show that these may improve the classification performances even further. Wan-Jui Lee, Veronika Cheplygina, David M. J. Tax, Marco Loog, Robert P. W. Duin	Int. J. Pattern Recognit. Artif. Intell.	2