Publication result detail

Unified Framework for Foreground and Anonymization Area Segmentation in CT and MRI Data

NOHEL, M.; ULRICH, C.; SUPRIJADI, J.; WALD, T.; MAIER-HEIN, K.

Original Title

Unified Framework for Foreground and Anonymization Area Segmentation in CT and MRI Data

English Title

Unified Framework for Foreground and Anonymization Area Segmentation in CT and MRI Data

Type

Paper in proceedings (conference paper)

Original Abstract

This study presents an open-source toolkit to address critical challenges in preprocessing data for self-supervised learning (SSL) for 3D medical imaging, focusing on data privacy and computational efficiency. The toolkit comprises two main components: a segmentation network that delineates foreground regions to optimize data sampling and thus reduce training time, and a segmentation network that identifies anonymized regions, preventing erroneous supervision in reconstruction-based SSL methods. Experimental results demonstrate high robustness, with mean Dice scores exceeding 98.5 across all anonymization methods and surpassing 99.5 for foreground segmentation tasks, highlighting the toolkit’s efficacy in supporting SSL applications in 3D medical imaging for both CT and MRI images. The weights and code is available at https://github.com/MIC-DKFZ/Foreground-and-Anonymization-Area-Segmentation.

English abstract

This study presents an open-source toolkit to address critical challenges in preprocessing data for self-supervised learning (SSL) for 3D medical imaging, focusing on data privacy and computational efficiency. The toolkit comprises two main components: a segmentation network that delineates foreground regions to optimize data sampling and thus reduce training time, and a segmentation network that identifies anonymized regions, preventing erroneous supervision in reconstruction-based SSL methods. Experimental results demonstrate high robustness, with mean Dice scores exceeding 98.5 across all anonymization methods and surpassing 99.5 for foreground segmentation tasks, highlighting the toolkit’s efficacy in supporting SSL applications in 3D medical imaging for both CT and MRI images. The weights and code is available at https://github.com/MIC-DKFZ/Foreground-and-Anonymization-Area-Segmentation.

Keywords

segmentation

Key words in English

segmentation

Authors

NOHEL, M.; ULRICH, C.; SUPRIJADI, J.; WALD, T.; MAIER-HEIN, K.

Released

02.03.2025

Publisher

Springer Vieweg

Location

Wiesbaden

ISBN

978-3-658-47421-8

Book

Bildverarbeitung für die Medizin 2025

Periodical

Informatik aktuell

State

Federal Republic of Germany

Pages from

242

Pages to

247

Pages count

6

URL

https://link.springer.com/chapter/10.1007/978-3-658-47422-5_53

BibTex

@inproceedings{BUT197344,
  author="Michal {Nohel} and Constantin {Ulrich} and Jonathan {Suprijadi} and Tassilo {Wald} and Klaus {Maier-Hein}",
  title="Unified Framework for Foreground and Anonymization Area Segmentation in CT and MRI Data",
  booktitle="Bildverarbeitung für die Medizin 2025",
  year="2025",
  journal="Informatik aktuell",
  pages="242--247",
  publisher="Springer Vieweg",
  address="Wiesbaden",
  doi="10.1007/978-3-658-47422-5\{_}53",
  isbn="978-3-658-47421-8",
  issn="1431-472X",
  url="https://link.springer.com/chapter/10.1007/978-3-658-47422-5_53"
}