Detection of focal cortical dysplasia: Development and multicentric evaluation of artificial intelligence models

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.