Learning to simulate realistic human diffuse reflectance spectra
Neural surrogate models can achieve MC-level accuracy and <i>in vivo</i> realism at negligible inference cost, enabling large-scale, compute-efficient data generation for biomedical optics and robust AI development for clinical applications.
Authors
- J. Brandt
- Kris K. Dreher (ORCID: https://orcid.org/0000-0002-9179-9414)
- Silvia Seidlitz (ORCID: https://orcid.org/0000-0002-1122-4793)
- Jan-Hinrich Nölke (ORCID: https://orcid.org/0000-0001-7600-3839)
- Marco Hübner
- Maike Rees (ORCID: https://orcid.org/0000-0002-7674-9144)
- Alexander Studier‐Fischer (ORCID: https://orcid.org/0000-0001-8682-9300)
- Jan Sellner (ORCID: https://orcid.org/0000-0003-4469-8343)
- A Seitel
- Felix Nickel
- Viet Tran Ba
- Ahmad Bin Qasim
- Janne Heinecke
- Karl-Friedrich Kowalewski
- Berkin Özdemir
- Leonardo Ayala
- Lena Maier-Hein
- Caelan Max Haney
Institutions
- German Cancer Research Center (DE)
- Heidelberg University (DE)
- University Hospital Heidelberg (DE)
- University Medical Centre Mannheim (DE)
Publication Details
- Journal
- Journal of Biomedical Optics
- Published
- 2026-02-26
- DOI
- https://doi.org/10.1117/1.jbo.31.2.026004
- Primary Topic
- Optical Imaging and Spectroscopy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Deutsches Krebsforschungszentrum
- European Commission
- Deutsche Forschungsgemeinschaft
- Universitätsklinikum Heidelberg