% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Baumann:305208,
author = {A. Baumann$^*$ and L. Ayala$^*$ and A. Studier-Fischer$^*$
and J. Sellner$^*$ and B. Özdemir$^*$ and K.-F.
Kowalewski$^*$ and S. Ilic and S. Seidlitz$^*$ and L.
Maier-Hein$^*$},
title = {{N}eural illumination calibration for surgical
workflow-optimized spectral imaging.},
journal = {International journal of computer assisted radiology and
surgery},
volume = {nn},
issn = {1861-6410},
address = {Heidelberg [u.a.]},
publisher = {Springer},
reportid = {DKFZ-2025-02056},
pages = {nn},
year = {2025},
note = {#EA:E130#LA:E130# / epub},
abstract = {Hyperspectral imaging (HSI) is emerging as a promising
novel imaging modality with various potential surgical
applications. Currently available cameras, however, suffer
from poor integration into the clinical workflow because
they require the lights to be switched off or the camera to
be manually recalibrated as soon as lighting conditions
change.We propose a novel learning-based approach to
recalibration of hyperspectral cameras during surgery that
predicts the corresponding white reference image from an
uncalibrated hyperspectral input, enabling spatially
resolved, automatic, and sterile calibration under varying
illumination conditions. Our key novelty lies in (i) the
disentanglement of the space of possible illuminations from
the space of possible tissue configurations and (ii)
combining real-world white reference measurements with
physics-inspired simulated illuminations to create a diverse
and representative training set.Based on a total of 1,890
HSI cubes from a phantom, porcine subjects, rats, and
humans, we derive the following key insights: Firstly,
dynamically changing lighting conditions in the operating
room dramatically reduce the performance of methods for
physiological parameter estimation and surgical scene
segmentation. Secondly, our method is not only sufficiently
accurate to replace the tedious process of white
reference-based recalibration, but also outperforms
previously proposed methods by a large margin. Finally, our
approach generalizes across species, lighting conditions,
and image processing tasks.Our method enables seamless
integration of hyperspectral imaging into surgical workflows
by providing rapid and automated illumination calibration.
Its robust generalization across diverse conditions
significantly enhances the reliability and practicality of
spectral imaging in clinical settings, paving the way for
broader adoption of HSI in surgery.},
keywords = {Deep Learning (Other) / Hyperspectral Imaging (Other) /
Illumination Calibration (Other) / Intra-Operative Imaging
(Other)},
cin = {E130 / E140 ; E140},
ddc = {610},
cid = {I:(DE-He78)E130-20160331 / I:(DE-He78)E140-20160331},
pnm = {315 - Bildgebung und Radioonkologie (POF4-315)},
pid = {G:(DE-HGF)POF4-315},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:41055831},
doi = {10.1007/s11548-025-03525-8},
url = {https://inrepo02.dkfz.de/record/305208},
}