A comparison between hyperspectral imaging and RGB-based tissue perfusion assessment of human skin using convolutional neural networks
CNNs are generally suitable for determining the perfusion indices. However, none of the four parameters could be reliably determined from RGB images. Increasing the number of ground truth and improving the models could improve prediction accuracy. The introduced MPE could be useful as a performance measure for models trained to assess tissue status.
Authors
- Veronika Volgger (ORCID: https://orcid.org/0000-0002-4688-5321)
- Kevin A. Strauss (ORCID: https://orcid.org/0000-0002-6429-8657)
- Maximilian Aumiller (ORCID: https://orcid.org/0000-0002-1343-6669)
- Matthäus Linek
- Ronald Sroka (ORCID: https://orcid.org/0000-0001-7952-2407)
- Isabel Schrader
- Adrian Rühm
Institutions
- LMU Klinikum (DE)
- Technical University of Munich (DE)
- Ludwig-Maximilians-Universität München (DE)
Publication Details
- Journal
- Computers in Biology and Medicine
- Published
- 2025-12-02
- DOI
- https://doi.org/10.1016/j.compbiomed.2025.111363
- Primary Topic
- Optical Imaging and Spectroscopy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00