% 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{Langner:301263,
author = {D. Langner and M. Nachbar and M. L. Russo and S. Boeke and
C. Gani and M. Niyazi and D. Thorwarth$^*$},
title = {{C}omparative analysis of open-source against commercial
{AI}-based segmentation models for online adaptive
{MR}-guided radiotherapy.},
journal = {Zeitschrift für medizinische Physik},
volume = {nn},
issn = {0939-3889},
address = {Amsterdam [u.a.]},
publisher = {Elsevier},
reportid = {DKFZ-2025-00948},
pages = {nn},
year = {2025},
note = {epub},
abstract = {Online adaptive magnetic resonance-guided radiotherapy
(MRgRT) has emerged as a state-of-the-art treatment option
for multiple tumour entities, accounting for daily
anatomical and tumour volume changes, thus allowing sparing
of relevant organs at risk (OARs). However, the annotation
of treatment-relevant anatomical structures in context of
online plan adaptation remains challenging, often relying on
commercial segmentation solutions due to limited
availability of clinically validated alternatives. The aim
of this study was to investigate whether an open-source
artificial intelligence (AI) segmentation network can
compete with the annotation accuracy of a commercial
solution, both trained on the identical dataset, questioning
the need for commercial models in clinical practice.For 47
pelvic patients, T2w MR imaging data acquired on a 1.5 T
MR-Linac were manually contoured, identifying prostate,
seminal vesicles, rectum, anal canal, bladder, penile bulb,
and bony structures. These training data were used for the
generation of an in-house AI segmentation model, a nnU-Net
with residual encoder architecture featuring a streamlined
single image inference pipeline, and re-training of a
commercial solution. For quantitative evaluation, 20 MR
images were contoured by a radiation oncologist, considered
as ground truth contours (GTC) and compared with the
in-house/commercial AI-based contours (iAIC/cAIC) using Dice
Similarity Coefficient (DSC), $95\%$ Hausdorff distances
(HD95), and surface DSC (sDSC). For qualitative evaluation,
four radiation oncologists assessed the usability of
OAR/target iAIC within an online adaptive workflow using a
four-point Likert scale: (1) acceptable without
modification, (2) requiring minor adjustments, (3) requiring
major adjustments, and (4) not usable.Patient-individual
annotations were generated in a median [range] time of 23
[16-34] s for iAIC and 152 [121-198] s for cAIC,
respectively. OARs showed a maximum median DSC of 0.97/0.97
(iAIC/cAIC) for bladder and minimum median DSC of 0.78/0.79
(iAIC/cAIC) for anal canal/penile bulb. Maximal respectively
minimal median HD95 were detected for rectum with 17.3/20.6
mm (iAIC/cAIC) and for bladder with 5.6/6.0 mm (iAIC/cAIC).
Overall, the average median DSC/HD95 values were 0.87/11.8mm
(iAIC) and 0.83/10.2mm (cAIC) for OAR/targets and
0.90/11.9mm (iAIC) and 0.91/16.5mm (cAIC) for bony
structures. For a tolerance of 3 mm, the highest and lowest
sDSC were determined for bladder (iAIC:1.00, cAIC:0.99) and
prostate in iAIC (0.89) and anal canal in cAIC (0.80),
respectively. Qualitatively, $84.8\%$ of analysed contours
were considered as clinically acceptable for iAIC, while
$12.9\%$ required minor and $2.3\%$ major adjustments or
were classed as unusable. Contour-specific analysis showed
that iAIC achieved the highest mean scores with 1.00 for the
anal canal and the lowest with 1.61 for the prostate.This
study demonstrates that open-source segmentation framework
can achieve comparable annotation accuracy to commercial
solutions for pelvic anatomy in online adaptive MRgRT. The
adapted framework not only maintained high segmentation
performance, with $84.8\%$ of contours accepted by
physicians or requiring only minor corrections $(12.9\%)$
but also enhanced clinical workflow efficiency of online
adaptive MRgRT through reduced inference times. These
findings establish open-source frameworks as viable
alternatives to commercial systems in supervised clinical
workflows.},
keywords = {Automatic annotation (Other) / Deep Learning (Other) /
MR-Linac (Other) / medical image segmentation (Other) /
online adaptive radiotherapy (Other)},
cin = {TU01},
ddc = {610},
cid = {I:(DE-He78)TU01-20160331},
pnm = {899 - ohne Topic (POF4-899)},
pid = {G:(DE-HGF)POF4-899},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:40345918},
doi = {10.1016/j.zemedi.2025.04.008},
url = {https://inrepo02.dkfz.de/record/301263},
}