% 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{Hofmann:300292,
author = {F. O. Hofmann$^*$ and C. Heiliger and T. Tschaidse and S.
Jarmusch and L. A. Auhage and U. Aghamaliyev and A. B.
Gesenhues and T. S. Schiergens and H. Niess and M. Ilmer$^*$
and J. Werner and B. W. Renz$^*$},
title = {{V}alidation of body composition parameters extracted via
deep learning-based segmentation from routine computed
tomographies.},
journal = {Scientific reports},
volume = {15},
number = {1},
issn = {2045-2322},
address = {[London]},
publisher = {Springer Nature},
reportid = {DKFZ-2025-00745},
pages = {11909},
year = {2025},
abstract = {Sarcopenia and body composition metrics are strongly
associated with patient outcomes. In this study, we
developed and validated a flexible, open-access pipeline
integrating available deep learning-based segmentation
models with pre- and postprocessing steps to extract body
composition measures from routine computed tomography (CT)
scans. In 337 surgical oncology patients, total skeletal
muscle tissue (SMtotal), psoas muscle tissue (SMpsoas),
visceral adipose tissue (VAT), and subcutaneous adipose
tissue (SAT) were quantified both manually and using the
pipeline. Automated and manual measurements showed strong
correlations (SMpsoas: r = 0.776, VAT: r = 0.993, SAT: r =
0.984; all P < 0.001). Measurement discrepancies primarily
resulted from segmentation errors, anatomical anomalies or
image irregularities. SMpsoas measurements showed
substantial variability depending on slice selection,
whereas SMtotal, averaged across all L3 levels, provided
greater measurement stability. Overall, SMtotal performed
comparably to SMpsoas in predicting overall survival (OS).
In summary, body composition measures derived from the
pipeline strongly correlated with manual measurements and
were prognostic for OS. The increased stability of SMtotal
across vertebral levels suggests it may serve as a more
reliable alternative to psoas-based assessments. Future
studies should address the identified areas of improvement
to enhance the accuracy of automated segmentation models.},
keywords = {Humans / Deep Learning / Body Composition / Tomography,
X-Ray Computed: methods / Male / Female / Aged / Middle Aged
/ Psoas Muscles: diagnostic imaging / Muscle, Skeletal:
diagnostic imaging / Intra-Abdominal Fat: diagnostic imaging
/ Sarcopenia: diagnostic imaging / Aged, 80 and over /
Subcutaneous Fat: diagnostic imaging / Image Processing,
Computer-Assisted: methods / Body composition (Other) /
Computed tomography (Other) / Oncology (Other) / Sarcopenia
(Other) / Tissue segmentation (Other)},
cin = {MU01},
ddc = {600},
cid = {I:(DE-He78)MU01-20160331},
pnm = {899 - ohne Topic (POF4-899)},
pid = {G:(DE-HGF)POF4-899},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:40195401},
doi = {10.1038/s41598-025-96238-6},
url = {https://inrepo02.dkfz.de/record/300292},
}