% 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{Kersting:278020,
author = {Kersting, Lennart N and Walger, Lennart and Bauer, Tobias
and Gnatkovsky, Vadym and Schuch, Fabiane and David, Bastian
and Neuhaus, Elisabeth and Keil, Fee and Tietze, Anna and
Rosenow, Felix and Kaindl, Angela M and Hattingen, Elke and
Huppertz, Hans-Jürgen and Radbruch, Alexander and Surges,
Rainer and Rüber, Theodor},
title = {{D}etection of focal cortical dysplasia: {D}evelopment and
multicentric evaluation of artificial intelligence models.},
journal = {Epilepsia},
volume = {66},
number = {4},
issn = {0013-9580},
address = {Oxford [u.a.]},
publisher = {Wiley-Blackwell},
reportid = {DZNE-2025-00530},
pages = {1165 - 1176},
year = {2025},
abstract = {Focal cortical dysplasia (FCD) is a common cause of
drug-resistant focal epilepsy but can be challenging to
detect visually on magnetic resonance imaging. Three
artificial intelligence models for automated FCD detection
are publicly available (MAP18, deepFCD, MELD) but have only
been compared on single-center data. Our first objective is
to compare them on independent multicenter test data.
Additionally, we train and compare three new models and make
them publicly available.We retrospectively collected FCD
cases from four epilepsy centers. We chose three novel
models that take two-dimensional (2D) slices (2D-nnUNet),
2.5D slices (FastSurferCNN), and large 3D patches
(3D-nnUNet) as inputs and trained them on a subset of Bonn
data. As core evaluation metrics, we used voxel-level Dice
similarity coefficient (DSC), cluster-level F1 score,
subject-level detection rate, and specificity.We collected
329 subjects, 244 diagnosed with FCD (27.7 ± 14.4 years
old, $54\%$ male) and 85 healthy controls (7.1 ± 2.4 years
old, $51\%$ female). We used 118 subjects for model training
and kept the remaining subjects as an independent test set.
3D-nnUNet achieved the highest F1 score of .58, the highest
DSC of .36 $(95\%$ confidence interval [CI] = .30-.41), a
detection rate of $55\%,$ and a specificity of $86\%.$
deepFCD showed the highest detection rate $(82\%)$ but had
the lowest specificity $(0\%)$ and cluster-level precision
(.03, $95\%$ CI = .03-.04, F1 score = .07). MELD showed the
least performance variation across centers, with detection
rates between $46\%$ and $54\%.This$ study shows the
variance in performance for FCD detection models in a
multicenter dataset. The two models with 3D input data
showed the highest sensitivity. The 2D models performed
worse than all other models, suggesting that FCD detection
requires 3D data. The greatly improved precision of
3D-nnUNet may make it a sensible choice to aid FCD
detection.},
keywords = {Humans / Male / Female / Malformations of Cortical
Development: diagnostic imaging / Adult / Magnetic Resonance
Imaging: methods / Retrospective Studies / Young Adult /
Child / Artificial Intelligence / Adolescent / Imaging,
Three-Dimensional / Focal Cortical Dysplasia / MRI (Other) /
computer‐aided detection (Other) / epilepsy (Other) /
lesion detection (Other) / model comparison (Other)},
cin = {AG Radbruch / AG Stöcker},
ddc = {610},
cid = {I:(DE-2719)5000075 / I:(DE-2719)1013026},
pnm = {353 - Clinical and Health Care Research (POF4-353) / 354 -
Disease Prevention and Healthy Aging (POF4-354)},
pid = {G:(DE-HGF)POF4-353 / G:(DE-HGF)POF4-354},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:39739580},
pmc = {pmc:PMC11997906},
doi = {10.1111/epi.18240},
url = {https://pub.dzne.de/record/278020},
}