Objective. To test the hypothesis that a multicenter-validated computer deep learning algorithm detects MRI-negative focal cortical dysplasia (FCD).

Methods. We used clinically acquired 3D T1-weighted and 3D FLAIR MRI of 148 patients (median age, 23 years [range, 2-55]; 47% female) with histologically verified FCD at nine centers to train a deep convolutional neural network (CNN) classifier. Images were initially deemed as MRI-negative in 51% of cases, in whom intracranial EEG determined the focus. For risk stratification, the CNN incorporated Bayesian uncertainty estimation as a measure of confidence. To evaluate performance, detection maps were compared to expert FCD manual labels. We also tested sensitivity in an independent cohort of 23 FCD cases (13±10 years). Applying the algorithm to 38 healthy and 63 temporal lobe epilepsy disease controls tested specificity.

Results. Overall sensitivity was 93% (137/148 FCD detected) using a leave-one-site-out cross-validation, with an average of six false positives per patient. Sensitivity in MRI-negative FCD was 85%. In 73% of patients, the FCD was among the clusters with the highest confidence; in half it ranked the highest. Sensitivity in the independent cohort was 83% (19/23; average of five false positives per patient). Specificity was 89% in healthy and disease controls.

Conclusions. This first multicenter-validated deep learning detection algorithm yields the highest sensitivity to date in MRI-negative FCD. By pairing predictions with risk stratification this classifier may assist clinicians to adjust hypotheses relative to other tests, increasing diagnostic confidence. Moreover, generalizability across age and MRI hardware makes this approach ideal for pre-surgical evaluation of MRI-negative epilepsy.

Classification of evidence. This study provides Class III evidence that deep learning on multimodal MRI accurately identifies FCD in epilepsy patients initially diagnosed as MRI-negative.

1. Description of methods used for collection/generation of data [noel_deepFCD_patch_16x16x16.h5]:
To create the HDF5 dataset, for each of the 148 FCD patients, we sampled at most 1,000 cortical patches (or # voxels in the lesion, whichever is lower) of size 16×16×16 within the lesion on pre-processed T1- and T2-weighted FLAIR MRI. The same number of cortical patches were sampled randomly outside the lesion. The resulting lesional and non-lesional patches were concatenated, shuffled (to add another layer of randomization), and saved along with their binary labels (as a compressed HDF5 dataset). Refer original publication and FCD_Detection_Neurology_Supplement.docx for more details

2. Methods for processing the data [noel_deepFCD_patch_16x16x16.h5]:
MRI pre-processing involved linear registration to the MNI152 symmetric template, non-uniformity correction, intensity standardization with scaling of values between 0 and 100, and skull-stripping using an in-house deep learning method (doi.org/10.5281/zenodo.4521716). Refer original publication and FCD_Detection_Neurology_Supplement.docx for details

3. Instrument- or software-specific information needed to interpret the data [noel_deepFCD_patch_16x16x16.h5]:
Python 3.5+ with h5py package (version >= 2.9.0)

FCD_Detection_Neurology_Supplement.docx contains:

1. Table e-1. MRI acquisition parameters across sites

2. Figure e-1. Hierarchical patch-based feature learning using CNN

3. Additional Methods:

   • Classifier design

   • Source code and data availability

4. Table e-2. Peak location of FCD lesions in MNI space

5. Table e-3. Peak location of false positive clusters in MNI space

6. eReferences

noel_deepFCD_patch_16x16x16.h5 (size: 6.4GB) contains two variables (data and labels):

also available from: https://doi.org/10.5281/zenodo.3239446

This data can be read in Python (using h5py => 2.9.0) using the included read_h5data.py function.

FCD_Detection_Neurology_STARD-Checklist.docx contains:

• STARD 2015 Checklist: An Updated List of Essential Items for Reporting Diagnostic Accuracy Studies. Please refer to https://www.equator-network.org/reporting-guidelines/stard/ for details.

only available from: https://doi.org/10.5281/zenodo.5173104