The Segment Anything foundation model achieves favorable brain tumor auto-segmentation accuracy in MRI to support radiotherapy treatment planning
The Segment Anything foundation segmentation model can achieve high accuracy for glioma brain tumor segmentation in MRI datasets. The results suggest that foundation segmentation models could facilitate RT treatment planning when properly integrated in a clinical application.
Authors
- Udo S. Gaipl (ORCID: https://orcid.org/0000-0001-6375-5476)
- Sabine Semrau (ORCID: https://orcid.org/0000-0001-7049-6003)
- Florian Putz (ORCID: https://orcid.org/0000-0003-3966-2872)
- Rainer Fietkau (ORCID: https://orcid.org/0000-0001-8295-7145)
- Benjamin Frey (ORCID: https://orcid.org/0000-0001-6743-3351)
- Sebastian Lettmaier (ORCID: https://orcid.org/0000-0001-6805-1558)
- Philipp Schubert (ORCID: https://orcid.org/0009-0006-0353-6283)
- Johanna Grigo
- Manuel Schmidt (ORCID: https://orcid.org/0000-0002-8560-2582)
- Christoph Bert (ORCID: https://orcid.org/0000-0002-8539-6600)
- Daniel Höfler
- Yixing Huang (ORCID: https://orcid.org/0000-0003-2627-3077)
- Thomas Weißmann (ORCID: https://orcid.org/0000-0002-1443-5422)
- Matthias May (ORCID: https://orcid.org/0000-0002-2540-850X)
- Ahmed M. Gomaa (ORCID: https://orcid.org/0009-0007-6884-2350)
- Luitpold Valentin Distel (ORCID: https://orcid.org/0000-0002-8040-3226)
- Ben Tkhayat Hassen
- Sogand Beirami
Institutions
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- Universitätsklinikum Erlangen (DE)
- Comprehensive Cancer Center Erlangen (DE)
Publication Details
- Journal
- Strahlentherapie und Onkologie
- Published
- 2024-11-06
- DOI
- https://doi.org/10.1007/s00066-024-02313-8
- Citations
- 25
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 9.70
Funders
- Universitätsklinikum Erlangen