Authors:
Quentin Langlois
1
;
Nicolas Szelagowski
2
;
Jean Vanderdonckt
1
;
2
and
Sébastien Jodogne
1
Affiliations:
1
Institute for Information and Communication Technologies, Electronics and Applied Mathematics (ICTEAM), UCLouvain, Belgium
;
2
Louvain Research Institute in Management and Organizations (LRIM), UCLouvain, Belgium
Keyword(s):
Medical imaging, Deep Learning, Text detection, Image de-identification, Open-source software
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 ser
ver.
(More)