% 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{Wald:298593,
author = {T. Wald$^*$ and B. Hamm$^*$ and J. Holzschuh$^*$ and R. El
Shafie and A. Kudak$^*$ and B. Kovacs$^*$ and I. Pflüger
and B. von Nettelbladt and C. Ulrich$^*$ and M.
Baumgartner$^*$ and P. Vollmuth and J. Debus$^*$ and K.
Maier-Hein$^*$ and T. Welzel$^*$},
title = {{E}nhancing deep learning methods for brain metastasis
detection through cross-technique annotations on {SPACE}
{MRI}.},
journal = {European radiology experimental},
volume = {9},
number = {1},
issn = {2509-9280},
address = {[Cham]},
publisher = {Springer International Publishing},
reportid = {DKFZ-2025-00303},
pages = {15},
year = {2025},
note = {#EA:E230#},
abstract = {Gadolinium-enhanced 'sampling perfection with
application-optimized contrasts using different flip angle
evolution' (SPACE) sequence allows better visualization of
brain metastases (BMs) compared to 'magnetization-prepared
rapid acquisition gradient echo' (MPRAGE). We hypothesize
that this better conspicuity leads to high-quality
annotation (HAQ), enhancing deep learning (DL) algorithm
detection of BMs on MPRAGE images.Retrospective
contrast-enhanced (gadobutrol 0.1 mmol/kg) SPACE and MPRAGE
data of 157 patients with BM were used, either annotated on
MPRAGE resulting in normal annotation quality (NAQ) or on
coregistered SPACE resulting in HAQ. Multiple DL methods
were developed with NAQ or HAQ using either SPACE or MRPAGE
images and evaluated on their detection performance using
positive predictive value (PPV), sensitivity, and F1 score
and on their delineation performance using volumetric Dice
similarity coefficient, PPV, and sensitivity on one internal
and four additional test datasets (660 patients).The
SPACE-HAQ model reached 0.978 PPV, 0.882 sensitivity, and
0.916 F1-score. The MPRAGE-HAQ reached 0.867, 0.839, and
0.840, the MPRAGE NAQ 0.964, 0.667, and 0.798, respectively
(p ≥ 0.157). Relative to MPRAGE-NAQ, the MPRAGE-HAQ
F1-score detection increased on all additional test datasets
by 2.5-9.6 points (p < 0.016) and sensitivity improved on
three datasets by 4.6-8.5 points (p < 0.001). Moreover,
volumetric instance sensitivity improved by 3.6-7.6 points
(p < 0.001).HAQ improves DL methods without specialized
imaging during application time. HAQ alone achieves about
$40\%$ of the performance improvements seen with SPACE
images as input, allowing for fast and accurate, fully
automated detection of small (< 1 cm) BMs.Training with
higher-quality annotations, created using the SPACE
sequence, improves the detection and delineation sensitivity
of DL methods for the detection of brain metastases (BMs)on
MPRAGE images. This MRI cross-technique transfer learning is
a promising way to increase diagnostic
performance.Delineating small BMs on SPACE MRI sequence
results in higher quality annotations than on MPRAGE
sequence due to enhanced conspicuity. Leveraging
cross-technique ground truth annotations during training
improved the accuracy of DL models in detecting and
segmenting BMs. Cross-technique annotation may enhance DL
models by integrating benefits from specialized,
time-intensive MRI sequences while not relying on them.
Further validation in prospective studies is needed.},
keywords = {Humans / Brain Neoplasms: diagnostic imaging / Brain
Neoplasms: secondary / Deep Learning / Magnetic Resonance
Imaging: methods / Retrospective Studies / Male / Female /
Middle Aged / Contrast Media / Aged / Organometallic
Compounds / Adult / Brain neoplasms (Other) / Deep learning
(Other) / Image interpretation (computer-assisted) (Other) /
Image processing (computer-assisted) (Other) / Magnetic
resonance imaging (Other) / Contrast Media (NLM Chemicals) /
gadobutrol (NLM Chemicals) / Organometallic Compounds (NLM
Chemicals)},
cin = {E230 / E010 / E050 / HD01},
ddc = {610},
cid = {I:(DE-He78)E230-20160331 / I:(DE-He78)E010-20160331 /
I:(DE-He78)E050-20160331 / I:(DE-He78)HD01-20160331},
pnm = {315 - Bildgebung und Radioonkologie (POF4-315)},
pid = {G:(DE-HGF)POF4-315},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:39913077},
doi = {10.1186/s41747-025-00554-5},
url = {https://inrepo02.dkfz.de/record/298593},
}