TY  - JOUR
AU  - Walger, Lennart
AU  - Schmitz, Matthias H
AU  - Bauer, Tobias
AU  - Kügler, David
AU  - Schuch, Fabiane
AU  - Arendt, Christophe
AU  - Baumgartner, Tobias
AU  - Birkenheier, Johannes
AU  - Borger, Valeri
AU  - Endler, Christoph
AU  - Grau, Franziska
AU  - Immanuel, Christian
AU  - Kölle, Markus
AU  - Kupczyk, Patrick
AU  - Lakghomi, Asadeh
AU  - Mackert, Sarah
AU  - Neuhaus, Elisabeth
AU  - Nordsiek, Julia
AU  - Odenthal, Anna-Maria
AU  - Dague, Karmele Olaciregui
AU  - Ostermann, Laura
AU  - Pukropski, Jan
AU  - Racz, Attila
AU  - von der Ropp, Klaus
AU  - Schmeel, Frederic Carsten
AU  - Schrader, Felix
AU  - Sitter, Aileen
AU  - Unruh-Pinheiro, Alexander
AU  - Voigt, Marilia
AU  - Vychopen, Martin
AU  - von Wedel, Philip
AU  - von Wrede, Randi
AU  - Attenberger, Ulrike
AU  - Vatter, Hartmut
AU  - Philipsen, Alexandra
AU  - Becker, Albert
AU  - Reuter, Martin
AU  - Hattingen, Elke
AU  - Radbruch, Alexander
AU  - Surges, Rainer
AU  - Rüber, Theodor
TI  - A public benchmark for human performance in the detection of focal cortical dysplasia.
JO  - Epilepsia open
VL  - 10
IS  - 3
SN  - 2470-9239
CY  - Hoboken, NJ
PB  - Wiley
M1  - DZNE-2025-00716
SP  - 778 - 786
PY  - 2025
AB  - This study aims to report human performance in the detection of Focal Cortical Dysplasias (FCDs) using an openly available dataset. Additionally, it defines a subset of this data as a 'difficult' test set to establish a public baseline benchmark against which new methods for automated FCD detection can be evaluated.The performance of 28 human readers with varying levels of expertise in detecting FCDs was originally analyzed using 146 subjects (not all of which are openly available), we analyzed the openly available subset of 85 cases. Performance was measured based on the overlap between predicted regions of interest (ROIs) and ground-truth lesion masks, using the Dice-Soerensen coefficient (DSC). The benchmark test set was chosen to consist of 15 subjects most predictive for human performance and 13 subjects identified by at most 3 of the 28 readers.Expert readers achieved an average detection rate of 68
KW  - Humans
KW  - Benchmarking
KW  - Malformations of Cortical Development: diagnostic imaging
KW  - Malformations of Cortical Development: diagnosis
KW  - Magnetic Resonance Imaging
KW  - Female
KW  - Male
KW  - Adult
KW  - Focal Cortical Dysplasia
KW  - artificial intelligence (Other)
KW  - computer‐aided detection (Other)
KW  - human performance (Other)
KW  - reader study (Other)
LB  - PUB:(DE-HGF)16
C6  - pmid:40167314
DO  - DOI:10.1002/epi4.70028
UR  - https://pub.dzne.de/record/279188
ER  -