Théo Sourget | PURRlab @ IT University of Copenhagen

References

Mask of truth: model sensitivity to unexpected regions of medical images

Théo Sourget, Michelle Hestbek-Møller, Amelia Jiménez-Sánchez, Jack Junchi Xu, and Veronika Cheplygina

Journal of Imaging Informatics in Medicine, 2025

@article{sourget2024mask,
  title = {Mask of truth: model sensitivity to unexpected regions of medical images},
  author = {Sourget, Th{\'e}o and Hestbek-M{\o}ller, Michelle and Jim{\'e}nez-S{\'a}nchez, Amelia and Junchi Xu, Jack and Cheplygina, Veronika},
  journal = {Journal of Imaging Informatics in Medicine},
  pages = {1--18},
  year = {2025},
  publisher = {Springer},
}

In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review

Amelia Jiménez-Sánchez, Natalia-Rozalia Avlona, Sarah Boer, Vı́ctor M. Campello, Aasa Feragen, and 24 more authors

In Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, , 2025

Abs DOI URL

Datasets play a critical role in medical imaging research, yet issues such as label quality, shortcuts, and metadata are often overlooked. This lack of attention may harm the generalizability of algorithms and, consequently, negatively impact patient outcomes. While existing medical imaging literature reviews mostly focus on machine learning (ML) methods, with only a few focusing on datasets for specific applications, these reviews remain static – they are published once and not updated thereafter. This fails to account for emerging evidence, such as biases, shortcuts, and additional annotations that other researchers may contribute after the dataset is published. We refer to these newly discovered findings of datasets as research artifacts. To address this gap, we propose a living review that continuously tracks public datasets and their associated research artifacts across multiple medical imaging applications. Our approach includes a framework for the living review to monitor data documentation artifacts, and an SQL database to visualize the citation relationships between research artifact and dataset. Lastly, we discuss key considerations for creating medical imaging datasets, review best practices for data annotation, discuss the significance of shortcuts and demographic diversity, and emphasize the importance of managing datasets throughout their entire lifecycle. Our demo is publicly available at http://inthepicture.itu.dk/.

Fairness and Robustness of CLIP-Based Models for Chest X-rays

Théo Sourget, David Restrepo, Céline Hudelot, Enzo Ferrante, Stergios Christodoulidis, and 1 more author

In MICCAI Workshop on Fairness of AI in Medical Imaging, 2025

URL Bib Code

@inproceedings{sourget2025fairness,
  title = {Fairness and Robustness of CLIP-Based Models for Chest X-rays},
  author = {Sourget, Th{\'e}o and Restrepo, David and Hudelot, C{\'e}line and Ferrante, Enzo and Christodoulidis, Stergios and Vakalopoulou, Maria},
  booktitle = {MICCAI Workshop on Fairness of AI in Medical Imaging},
  pages = {11--21},
  year = {2025},
  organization = {Springer},
}

[Citation needed] Data usage and citation practices in medical imaging conferences

Théo Sourget, Ahmet Akkoç, Stinna Winther, Christine Lyngbye Galsgaard, Amelia Jiménez-Sánchez, and 3 more authors

In Medical Imaging with Deep Learning, 2024

URL Bib PDF Code Poster

@inproceedings{sourget2024citation,
  title = {[Citation needed] Data usage and citation practices in medical imaging conferences},
  author = {Sourget, Th{\'e}o and Akko{\c{c}}, Ahmet and Winther, Stinna and Galsgaard, Christine Lyngbye and Jim{\'e}nez-S{\'a}nchez, Amelia and Juodelyte, Dovile and Petitjean, Caroline and Cheplygina, Veronika},
  booktitle = {Medical Imaging with Deep Learning},
  year = {2024},
}

Copycats: the many lives of a publicly available medical imaging dataset

Amelia Jiménez-Sánchez, Natalia-Rozalia Avlona, Dovile Juodelyte, Théo Sourget, Caroline Vang-Larsen, and 3 more authors

In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2024

URL PDF Poster

Can SegFormer be a true competitor to U-Net for medical image segmentation?

Théo Sourget, Syed Nouman Hasany, Fabrice Mériaudeau, and Caroline Petitjean

In Annual Conference on Medical Image Understanding and Analysis, 2023

URL Bib Code

@inproceedings{sourget2023can,
  title = {Can SegFormer be a true competitor to U-Net for medical image segmentation?},
  author = {Sourget, Th{\'e}o and Hasany, Syed Nouman and M{\'e}riaudeau, Fabrice and Petitjean, Caroline},
  booktitle = {Annual Conference on Medical Image Understanding and Analysis},
  pages = {111--118},
  year = {2023},
  organization = {Springer},
}

Segmentation, and Numbering in Oral Rare Diseases: Focus on Data Augmentation and Inpainting Techniques

Hocine Kadi, Théo Sourget, Marzena Kawczynski, Sara Bendjama, Bruno Grollemund, and 1 more author

In 2023 International Conference on Computational Science and Computational Intelligence (CSCI), 2023

URL Bib

@inproceedings{kadi2023segmentation,
  title = {Segmentation, and Numbering in Oral Rare Diseases: Focus on Data Augmentation and Inpainting Techniques},
  author = {Kadi, Hocine and Sourget, Th{\'e}o and Kawczynski, Marzena and Bendjama, Sara and Grollemund, Bruno and Bloch-Zupan, Agn{\'e}s},
  booktitle = {2023 International Conference on Computational Science and Computational Intelligence (CSCI)},
  pages = {1358--1363},
  year = {2023},
  organization = {IEEE},
}