Open Platform for the De-identification of Burned-in Texts in Medical Images using Deep Learning

Quentin Langlois, Nicolas Szelagowski, Jean Vanderdonckt, Jean Vanderdonckt, Sébastien Jodogne

2024

Abstract

While the de-identification of DICOM tags is a standardized, well-established practice, the removal of protected health information that is burned into the pixels of medical images is a more complex challenge for which Deep Learning is especially well adapted. Unfortunately, there is currently a lack of accurate, effective, and freely available tools to this end. This motivates the release of a new benchmark dataset, together with free and open-source software that implements suitable Deep Learning algorithms, with the objective of improving patient confidentiality. The proposed methods consist in adapting regular scene-text detection models (SSD and TextBoxes) to the task of image de-identification. It is shown that the fine-tuning of such generic scene-text detection models on medical images significantly improves performance. The developed algorithms can be applied either from the command line or using a Web interface that is tightly integrated with a free and open-source PACS server.

Paper Citation

in Harvard Style

Langlois Q., Szelagowski N., Vanderdonckt J. and Jodogne S. (2024). Open Platform for the De-identification of Burned-in Texts in Medical Images using Deep Learning. In Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING; ISBN 978-989-758-688-0, SciTePress, pages 297-304. DOI: 10.5220/0012430300003657

in Bibtex Style

@conference{bioimaging24,
author={Quentin Langlois and Nicolas Szelagowski and Jean Vanderdonckt and Sébastien Jodogne},
title={Open Platform for the De-identification of Burned-in Texts in Medical Images using Deep Learning},
booktitle={Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING},
year={2024},
pages={297-304},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012430300003657},
isbn={978-989-758-688-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING
TI - Open Platform for the De-identification of Burned-in Texts in Medical Images using Deep Learning
SN - 978-989-758-688-0
AU - Langlois Q.
AU - Szelagowski N.
AU - Vanderdonckt J.
AU - Jodogne S.
PY - 2024
SP - 297
EP - 304
DO - 10.5220/0012430300003657
PB - SciTePress