Premium
External validation of automated focal cortical dysplasia detection using morphometric analysis
Author(s) -
David Bastian,
KröllSeger Judith,
Schuch Fabiane,
Wagner Jan,
Wellmer Jörg,
Woermann Friedrich,
Oehl Bernhard,
Van Paesschen Wim,
Breyer Tobias,
Becker Albert,
Vatter Hartmut,
Hattingen Elke,
Urbach Horst,
Weber Bernd,
Surges Rainer,
Elger Christian Erich,
Huppertz HansJürgen,
Rüber Theodor
Publication year - 2021
Publication title -
epilepsia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.687
H-Index - 191
eISSN - 1528-1167
pISSN - 0013-9580
DOI - 10.1111/epi.16853
Subject(s) - cortical dysplasia , magnetic resonance imaging , epilepsy , data set , medicine , artificial intelligence , artificial neural network , cross validation , computer science , radiology , psychiatry
Objective Focal cortical dysplasias (FCDs) are a common cause of drug‐resistant focal epilepsy but frequently remain undetected by conventional magnetic resonance imaging (MRI) assessment. The visual detection can be facilitated by morphometric analysis of T1‐weighted images, for example, using the Morphometric Analysis Program (v2018; MAP18), which was introduced in 2005, independently validated for its clinical benefits, and successfully integrated in standard presurgical workflows of numerous epilepsy centers worldwide. Here we aimed to develop an artificial neural network (ANN) classifier for robust automated detection of FCDs based on these morphometric maps and probe its generalization performance in a large, independent data set. Methods In this retrospective study, we created a feed‐forward ANN for FCD detection based on the morphometric output maps of MAP18. The ANN was trained and cross‐validated on 113 patients (62 female, mean age ± SD =29.5 ± 13.6 years) with manually segmented FCDs and 362 healthy controls (161 female, mean age ± SD =30.2 ± 9.6 years) acquired on 13 different scanners. In addition, we validated the performance of the trained ANN on an independent, unseen data set of 60 FCD patients (28 female, mean age ± SD =30 ± 15.26 years) and 70 healthy controls (42 females, mean age ± SD = 40.0 ± 12.54 years). Results In the cross‐validation, the ANN achieved a sensitivity of 87.4% at a specificity of 85.4% on the training data set. On the independent validation data set, our method still reached a sensitivity of 81.0% at a comparably high specificity of 84.3%. Significance Our method shows a robust automated detection of FCDs and performance generalizability, largely independent of scanning site or MR‐sequence parameters. Taken together with the minimal input requirements of a standard T1 image, our approach constitutes a clinically viable and useful tool in the presurgical diagnostic routine for drug‐resistant focal epilepsy.