% 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”.
@INBOOK{Kchele:300814,
author = {J. Kächele$^*$ and M. Zenk$^*$ and M. Rokuss$^*$ and C.
Ulrich$^*$ and T. Wald$^*$ and K. Maier-Hein$^*$},
title = {{E}nhanced nn{U}-{N}et {A}rchitectures for {A}utomated
{MRI} {S}egmentation of {H}ead and {N}eck {T}umors in
{A}daptive {R}adiation {T}herapy.},
volume = {15273},
address = {Cham},
publisher = {Springer Nature Switzerland},
reportid = {DKFZ-2025-00928},
isbn = {978-3-031-83273-4 (print)},
series = {Lecture Notes in Computer Science},
pages = {50 - 64},
year = {2025},
comment = {Head and Neck Tumor Segmentation for MR-Guided Applications
/ Wahid, Kareem A. (Editor)
[https://orcid.org/0000-0002-0503-0175] ; Cham : Springer
Nature Switzerland, 2025, Chapter 3 ; ISSN:
0302-9743=1611-3349 ; ISBN:
978-3-031-83273-4=978-3-031-83274-1 ;
doi:10.1007/978-3-031-83274-1},
booktitle = {Head and Neck Tumor Segmentation for
MR-Guided Applications / Wahid, Kareem
A. (Editor)
[https://orcid.org/0000-0002-0503-0175]
; Cham : Springer Nature Switzerland,
2025, Chapter 3 ; ISSN:
0302-9743=1611-3349 ; ISBN:
978-3-031-83273-4=978-3-031-83274-1 ;
doi:10.1007/978-3-031-83274-1},
abstract = {The increasing utilization of MRI in radiation therapy
planning for head and neck cancer (HNC) highlights the need
for precise tumor segmentation to enhance treatment efficacy
and reduce side effects. This work presents segmentation
models developed for the HNTS-MRG 2024 challenge by the team
mic-dkfz, focusing on automated segmentation of HNC tumors
from MRI images at two radiotherapy (RT) stages: before
(pre-RT) and 2-4 weeks into RT (mid-RT). For Task 1 (pre-RT
segmentation), we built upon the nnU-Net framework,
enhancing it with the larger Residual Encoder architecture.
We incorporated extensive data augmentation and applied
transfer learning by pre-training the model on a diverse set
of public 3D medical imaging datasets. For Task 2 (mid-RT
segmentation), we adopted a longitudinal approach by
integrating registered pre-RT images and their segmentations
as additional inputs into the nnU-Net framework. On the test
set, our models achieved mean aggregated Dice Similarity
Coefficient (aggDSC) scores of 81.2 for Task 1 and 72.7 for
Task 2. Especially the primary tumor (GTVp) segmentation is
challenging and presents potential for further optimization.
These results demonstrate the effectiveness of combining
advanced architectures, transfer learning, and longitudinal
data integration for automated tumor segmentation in
MRI-guided adaptive radiation therapy.},
keywords = {Head and Neck Cancer (Other) / Longitudinal Data
Integration (Other) / MRI-guided Radiation Therapy (Other) /
Transfer Learning (Other) / Tumor Segmentation (Other) /
nnU-Net (Other)},
cin = {E230 / HD01},
cid = {I:(DE-He78)E230-20160331 / I:(DE-He78)HD01-20160331},
pnm = {315 - Bildgebung und Radioonkologie (POF4-315)},
pid = {G:(DE-HGF)POF4-315},
typ = {PUB:(DE-HGF)7},
pubmed = {pmid:40291013},
pmc = {pmc:PMC12023904},
doi = {10.1007/978-3-031-83274-1_3},
url = {https://inrepo02.dkfz.de/record/300814},
}